PreprintPDF Available

Unsupervised machine learning analysis to identify patterns of ICU medication use for fluid overload prediction

March 2024

DOI:10.1101/2024.03.21.24304663

License
CC BY-NC-ND 4.0

Authors:

Andrea Sikora Newsome

The University of Georgia College of Pharmacy

Preprints and early-stage research may not have been peer reviewed yet.

INTRODUCTION: Intravenous (IV) medications are a fundamental cause of fluid overload (FO) in the intensive care unit (ICU); however, the association between IV medication use (including volume), administration timing, and FO occurrence remains unclear. METHODS: This retrospective cohort study included consecutive adults admitted to an ICU ≥72 hours with available fluid balance data. FO was defined as a positive fluid balance ≥7% of admission body weight within 72 hours of ICU admission. After reviewing medication administration record (MAR) data in three-hour periods, IV medication exposure was categorized into clusters using principal component analysis (PCA) and Restricted Boltzmann Machine (RBM). Medication regimens of patients with and without FO were compared within clusters to assess for temporal clusters associated with FO using the Wilcoxon rank sum test. Exploratory analyses of the medication cluster most associated with FO for medications frequently appearing and used in the first 24 hours was conducted. RESULTS: FO occurred in 127/927 (13.7%) of the patients enrolled. Patients received a median (IQR) of 31 (13-65) discrete IV medication administrations over the 72-hour period. Across all 47,803 IV medication administrations, ten unique IV medication clusters were identified with 121-130 medications in each cluster. Among the ten clusters, cluster 7 had the greatest association with FO; the mean number of cluster 7 medications received was significantly greater in patients in the FO cohort compared to patients who did not experience FO (25.6 vs.10.9. p<0.0001). 51 of the 127 medications in cluster 7 (40.2%) appeared in > 5 separate 3-hour periods during the 72-hour study window. The most common cluster 7 medications included continuous infusions, antibiotics, and sedatives/analgesics. Addition of cluster 7 medications to a prediction model with APACHE II score and receipt of diuretics improved the ability for the model to predict fluid overload (AUROC 5.65, p =0.0004). CONCLUSIONS: Using ML approaches, a unique IV medication cluster was strongly associated with FO. Incorporation of this cluster improved the ability to predict development of fluid overload in ICU patients compared with traditional prediction models. This method may be further developed into real-time clinical applications to improve early detection of adverse outcomes.

Available via license: CC BY-NC-ND 4.0

Content may be subject to copyright.

Unsupervised machine learning analysis to identify patterns of ICU medication use for

fluid overload prediction

Kelli Keats, PharmD, MPA, BCCCP (corresponding author)

kkeats@augusta.edu

Augusta University Medical Center, Department of Pharmacy, Augusta, GA

Shiyuan Deng

Shiyuan.deng@uga.edu

University of Georgia Franklin College of Arts and Sciences, Department of Statistics, Athens,

GA, USA

Xianyan Chen, PhD

xychen@uga.edu

University of Georgia Franklin College of Arts and Sciences, Department of Statistics, Athens,

GA, USA

Tianyi Zhang

Tianyi.zhang@uga.edu

University of Georgia Franklin College of Arts and Sciences, Department of Statistics, Athens,

GA, USA

John W. Devlin, PharmD, BCCCP, MCCM, FCCP

Northeastern University School of Pharmacy, Boston, MA

Brigham and Women’s Hospital, Division of Pulmonary and Critical Care Medicine, Boston,

David J. Murphy, MD, PhD

david.j.murphy@emory.edu

Emory University, Division of Pulmonary, Allergy, Critical Care and Sleep Medicine, Atlanta,

GA, USA

Susan E. Smith, PharmD

Susan.smith@uga.edu

University of Georgia College of Pharmacy, Department of Clinical and Administrative

Pharmacy, Athens, GA, USA

Brian Murray, PharmD

Brian.2.Murray@cuanschutz.edu

University of Colorado Skaggs School of Pharmacy, Aurora, CO, USA

Rishikesan Kamaleswaran, PhD

rkamaleswaran@emory.edu

Department of Biomedical Informatics, Emory University School of Medicine, Atlanta, GA,

USA

Department of Biomedical Engineering, Georgia Institute of Technology, Atlanta, GA, USA

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

is the author/funder, who has granted medRxiv a license to display the preprint in perpetuity. (which was not certified by peer review) The copyright holder for this preprint this version posted March 22, 2024. ; https://doi.org/10.1101/2024.03.21.24304663doi: medRxiv preprint

NOTE: This preprint reports new research that has not been certified by peer review and should not be used to guide clinical practice.

Andrea Sikora, PharmD, MSCR, BCCCP, FCCM, FCCP

1120 15th Street, HM-118 Augusta, GA 30912

(706)-721-3826

sikora@uga.edu

University of Georgia College of Pharmacy, Department of Clinical and Administrative

Pharmacy, Augusta, GA, USA

On behalf of the MRC-ICU Investigator Team

Conflicts of Interest: The authors have no conflicts of interest.

Funding: Funding through Agency of Healthcare Research and Quality for Drs. Devlin,

Murphy, Sikora, Smith, and Kamaleswaran was provided through R21HS028485 and

R01HS029009.

Acknowledgements: Data acquisition were supported by NC TraCS, funded by Grant Number

UL1TR002489 from the National Center for Advancing Translations Sciences at the National

Institutes of Health, and Data Analytics at the University of North Carolina Medical Center

Department of Pharmacy.

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

ABSTRACT

INTRODUCTION: Intravenous (IV) medications are a fundamental cause of fluid overload

(FO) in the intensive care unit (ICU); however, the association between IV medication use

(including volume), administration timing, and FO occurrence remains unclear.

METHODS: This retrospective cohort study included consecutive adults admitted to an ICU

≥

72 hours with available fluid balance data. FO was defined as a positive fluid balance

≥

7% of

admission body weight within 72 hours of ICU admission. After reviewing medication

administration record (MAR) data in three-hour periods, IV medication exposure was

categorized into clusters using principal component analysis (PCA) and Restricted Boltzmann

Machine (RBM). Medication regimens of patients with and without FO were compared within

clusters to assess for temporal clusters associated with FO using the Wilcoxon rank sum test.

Exploratory analyses of the medication cluster most associated with FO for medications

frequently appearing and used in the first 24 hours was conducted.

RESULTS: FO occurred in 127/927 (13.7%) of the patients enrolled. Patients received a median

(IQR) of 31 (13-65) discrete IV medication administrations over the 72-hour period. Across all

47,803 IV medication administrations, ten unique IV medication clusters were identified with

121-130 medications in each cluster. Among the ten clusters, cluster 7 had the greatest

association with FO; the mean number of cluster 7 medications received was significantly

greater in patients in the FO cohort compared to patients who did not experience FO (25.6

vs.10.9. p<0.0001). 51 of the 127 medications in cluster 7 (40.2%) appeared in > 5 separate 3-

hour periods during the 72-hour study window. The most common cluster 7 medications

included continuous infusions, antibiotics, and sedatives/analgesics. Addition of cluster 7

medications to a prediction model with APACHE II score and receipt of diuretics improved the

ability for the model to predict fluid overload (AUROC 5.65, p =0.0004).

CONCLUSIONS: Using ML approaches, a unique IV medication cluster was strongly

associated with FO. Incorporation of this cluster improved the ability to predict development of

fluid overload in ICU patients compared with traditional prediction models. This method may be

further developed into real-time clinical applications to improve early detection of adverse

outcomes.

KEYWORDS: critical care; fluid overload; prediction; medication regimen complexity;

machine learning

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

KEY POINTS

Questions: Can machine learning detect the presence of time-dependent medication

administration patterns that are associated with risk of fluid overload in critically ill patients?

Findings: Using unsupervised machine learning, a unique IV medication cluster was identified

that, when combined with the APACHE II score and diuretic use, improved the ability to predict

fluid overload in ICU patients.

Meaning: These findings suggest that machine learning may be an important tool for analyzing

IV mediation administration patterns to predict development of fluid overload. Such models may

provide insight into areas where medication administration practices could be optimized to

mitigate the risk of fluid overload in this patient population.

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

INTRODUCTION

While intravenous (IV) medications are integral to the management of critically ill patients, the

associated diluent volume contributes to the development of fluid overload (FO) and its sequalae,

including mortality, increased intensive care unit (ICU) length of stay (LOS), increased acute

kidney injury (AKI), and increased likelihood of mechanical intubation.1-3 Mitigating fluid

overload with timely achievement of euvolemia is associated with improved outcomes.4-7 Given

the complexity and prolific nature of mediation use in the ICU, data driven strategies are

increasingly being employed to parse meaningful patterns for fluid overload prediction.8-10

While research is ongoing regarding identification of predictors for fluid overload, minimal

research has evaluated the impact of medications as potential contributors.11,12 These studies

have shown that medication regimen complexity, as measured by the medication regimen

complexity-ICU (MRC-ICU), was related to fluid overload risk, using both traditional regression

and supervised machine learning approaches.8-10 This score has also been shown to predict

mortality13, LOS14, and prolonged duration of mechanical ventilation.15-21 Moreover,

pharmacophenotyping based approaches including MRC-ICU and employing a common data

model (CDM) for ICU medications (ICURx) have previously been created to allow for

unsupervised cluster analysis machine learning that showed unique patterns of medication use

and ICU complications, including FO.22,23 Therefore, quantifying patient-specific, medication-

related data may be an important strategy in the prediction of fluid overload in critically adults.

No study has evaluated timing of medication administration in relation to fluid overload by

reviewing the entire medication administration record (MAR) to identify patterns associated with

medication administration. Unsupervised machine learning may be an optimal strategy for

identifying factors associated with medication use and timing in relation to fluid overload. The

purpose of this study was to employ unsupervised machine learning methods to uncover

medication administration patterns that are correlated with the occurrence of FO. We

hypothesized that unique clusters of medication use, particularly early in the ICU stay, would

have a strong association with FO development.

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

MATERIALS AND METHODS

This was a retrospective, observational study of adults admitted to critical care units at the

University of North Carolina Health System (UNCHS) who had fluid overload data recorded.

The protocol for this study was reviewed and approved by the UNHCS Institutional Review

Board (approval number: (Study Number 20-2330); approval date: September 2020). Waivers of

informed consent and HIPAA authorization were granted based on study design. All procedures

were conducted with ethical standards of the UNHCS Institutional Review Board and the most

recent version of the Helsinki Declaration of 1975.24 The reporting of this study adheres to the

STrengthening and reporting of OBservational data in Epidemiology statement (STROBE).25

Population

A trained Carolina Data Warehouse (CDW) analyst developed a random sample of 1,000 adult

ICU patients (

≥

18 years) between October 2015 and October 2020 and extracted requested data

from electronic health record (EHR) data (Epic Systems, Verona, WI). Patients were excluded if

the data provided was not from their index ICU admission. These methods have been previously

published.9,10

Data Collection and Outcomes

The primary outcome was presence of fluid overload at 72 hours after initial ICU admission.

Fluid overload was defined as a positive fluid balance (intake > output) in milliliters (mL)

greater than or equal to 7% of the patient’s admission body weight in kilograms (kg).1,3 For

example, a patient weighing 80kg at ICU admission with a positive fluid balance at 72 hours of

12,000 mL (or 12kg) would be classified as having fluid overload (positive fluid balance of 12kg

is 15% of initial body weight).

Relevant patient demographics were extracted including: age, sex, race, ICU type, admission

diagnosis, utilization of end-organ support including mechanical ventilation and renal

replacement therapy, presence of AKI, use of vasopressors, Acute Physiology and Chronic

Health Evaluation (APACHE) II score at 24 hours, and sequential organ failure assessment

(SOFA) score at 24 hours. Additionally, patient outcomes, including in-hospital mortality,

maximum fluid overload over 72 hours, and ICU LOS were collected.

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

The 72 hour study period was divided into 24 sets of three-hour intervals. Within this timeframe,

the frequency of IV medication administration was calculated for each patient. All IV

medications (any type of medication) as well as both oral and IV diuretics (e.g., furosemide,

torsemide, chlorothiazide) were organized based on time of administration and separated into 3-

hour groups (e.g., vancomycin given at hour 1 of ICU admission would be considered a different

entity than vancomycin given at hour 12 of ICU admission). This allowed for both the

medication and the timing of medication administration to be included in the unsupervised

machine learning analysis. Medications were reviewed to combine any listed medications that

were the same dose and volume (e.g., cefepime 1000mg/100 mL in normal saline (NS) mini-bag

plus and cefepime 1000m/100mL NS infusion would be considered the same drug).

Antimicrobials that were infused over an extended interval (e.g., piperacillin-tazobactam) were

not combined with the same antimicrobial infused over a standard duration. Additionally, the

ICURx CDM was incorporated into analysis to provide additional information regarding specific

ICU medications, including medication class and mode of administration (e.g. IV push versus

continuous infusion).17,26

Data Analysis

Unsupervised machine learning analysis. Principal Component Analysis (PCA) was performed at the

patient level to create principal components (PCs) with a cumulative variance of over 85%.27,28 This

dimension reduction approach was essential as it laid a robust foundation for the subsequent stages of our

analysis, enabling us to effectively manage the complexity of the dataset.27,28 PCA helps remove

redundant information and reduces the risk of overfitting, making the dimension-reduced representation

more robust to noise and irrelevant features.27,28 Building upon the reduced dimensionality established by

the PCA, we proceeded with the implementation of the Restricted Boltzmann Machine (RBM) which

allowed us to identify the underlying structure in medication administration.29,30 By using the insights

captured by the PCs, the RBM unveiled concealed layers.29,30 Following thorough hyperparameter tuning,

which included adjustments to the number of neurons (hidden units), learning rate, and other factors, this

process culminated in the successful classification of medications into distinct clusters.31 RBM can learn

sparse representations of data, which means that only a subset of neurons (hidden units) is active at any

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

given time.29,30 This sparsity can lead to more robust and interpretable representations, particularly in

cases of the medication administration record where there are redundant or noisy features.29,30

The entire process is summarized in Figure 1.

Test for the association between clusters and fluid overload. The rank sum test was employed to assess

association between each cluster and the occurrence of fluid overload. Clusters demonstrating positive

correlations were recognized through p-values lower than 0.05, accompanied by higher mean ranks

among patients with fluid overload compared to those without fluid overload. Additionally, logistic

regression analyses were performed to support the rank sum test, facilitating the identification and

examination of the cluster with the highest association. For these ten logistic regression models (which

corresponded to the ten medication clusters), the binary dependent outcome was fluid overload and each

cluster’s standardized medication proportion was the independent variable. All analyses were performed

in Python (version 3.0) and R (version 4.2.1).

Predictive modeling: Proportion of medications within the cluster most associated with FO was added to a

logistic regression that included APACHE II score & diuretic use to determine if this feature would add to

the ability of the model to predict fluid overload in individual patients. This was also done by time period

(24, 48, 72 hours) to determine when the proportion of medications matching the cluster most associated

with FO was most important in relation to development of fluid overload.

Descriptive characterization of clusters most associated with FO. Upon identification of medication

clusters associated with FO, descriptive statistics were planned to explore and characterize these clusters.

Analyses included categorization of medications in each cluster by medication class and analysis of

frequency of medications occurring within each cluster (ex. Vancomycin appeared within the cluster X

times). Additionally, the clusters were split into 24 hour periods to analyze which medications appeared

in the cluster within specific ICU days (i.e. medications that appeared only within the first 24 hours of

admission versus medications that appeared within the cluster multiple times throughout the 72 hour

analysis period) to assess for a temporal relationship between medication administration and fluid

overload. An exploratory analysis including variables of timing such as intermittent and bolus

administration was also conducted.

RESULTS

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

Among the 927 patients included in the study after removal of patients without fluid balance information

(see Appendix for consort diagram), a total of 127 individuals (13.7%) experienced fluid overload. In the

fluid overload cohort, the median fluid balance at 72 hours was 5934.17mL (3359.3-9156.4mL) vs.

300mL (IQR -894.1-1576.6 mL) in the non-fluid overload cohort. A total of 47,803 medication

administrations occurred within the first 72 hours of ICU stay. Of these medication administrations, there

were a total of 2,229 distinct combinations of medication plus timing of administration (ex. Cefazolin

hours 0-3 of ICU stay, cefazolin hours 4-6 of ICU stay, etc.). Over the first 72 hours of ICU stay, all

patients received a median of 31 distinct IV medication administrations (interquartile range: 13-65), with

patients in the fluid overload group receiving a higher number of medication administrations compared to

the non-fluid overload group (Table 1). Patients were mostly cared for in the medical ICU. Patients with

fluid overload had a higher severity of illness as demonstrated by the APACHE II and SOFA scores at 24

hours, higher frequency of end-organ support including mechanical ventilation and renal replacement

therapy, longer ICU LOS, and worse patient-centered outcomes including morbidity (e.g., AKI) and

mortality. Patients in the fluid overload group received more medications overall as well as more

vasopressors, sedatives, antibiotics, fluids, analgesics, gastric agents, anticonvulsants, and

antidotes/rescue therapy compared to the non-FO group. Table 1 provides a complete summary of

demographics.

The PCA was conducted to identify clusters of medications. While early models of the PCA included

patient-specific information including SOFA score, age, sex, etc., these factors were not significant in

identifying the clusters and were excluded from the final model, which included only medications and

timing of administration. The proposed unsupervised machine learning modeling yielded 10 distinct

clusters (Figure 1). There were a median of 532 (interquartile range (IQR) 520-539.8) medications in

each cluster when medications were associated with an administration time (ex. vancomycin 1g at hour 3

is considered a separate medication than vancomycin 1g at hour 8), and 121-130 medications in each

cluster when administration time was not considered. 97 medications were identical in every cluster when

timing was not considered, but when timing of medication administration was factored in, the clusters

were significantly different with no medication plus timing combinations being identical in all clusters.

Figures 2 & 3 show overlap between clusters when categorizing medications within each cluster by

medication administrations (Figure 2) and medication names (Figure 3). The medications appearing in

each cluster are listed in the Digital Supplementary Materials. Additionally, medications were

categorized by class, and these proportions are reported in Table 2.

Clusters 5 and 7 had a positive association with fluid overload based on the rank sum test (Table 3).

Patients who experienced fluid overload received a higher mean number of Cluster 5 (18.7 medications vs.

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

7.7 medications, p < 0.0001) and Cluster 7 medications (25.6 medications vs. 10.9 medications, p <

0.0001) in comparison to patients who did not experience fluid overload. Ten logistic regression models

were employed, yielding similar results to those of the rank sum test (Table 4). While Cluster 5 also was

associated with fluid overload, its association was weaker than that of Cluster 7. Analyses of Cluster 5

can be found in the Supplementary Appendix.

Notably, Cluster 7, which consisted of 127 unique IV medications, exhibited the highest estimated value

and the smallest p-value, signifying its substantial contribution to the development of fluid overload. The

medications found within Cluster 7 were diverse, with high representation among continuous infusions,

antibiotics, as well as sedatives and analgesics (Table 2). A total of 51 medications (40%) were

administered in >5 separate 3-hour intervals, and fifteen medications within Cluster 7 were administered

exclusively within the initial 24 hours of ICU admission (Table 5). Patients with fluid overload were

more likely to have medications appear within Cluster 7 than patients without fluid overload (Table 6).

Table 7 provides a list of medications appearing on each of the first 3 days of ICU admission within

Cluster 7. Figure 4 shows all of the medications within Cluster 7 and how frequently they appeared based

on timing of administration. Figure 5 reveals medications and timing of medication administrations

within Cluster 7 ordered from most frequent to least frequent appearance within the Cluster. Table 6

splits the medications from Cluster 7 into each day of ICU stay (first 72 hours), and Figure 6 includes

timing of medication administrations separated by medication class. Figure 7 represents the frequency at

which each 3-hour time slot appeared within Cluster 7 (ex. 27 medications given within 0-3 hours of ICU

admission appeared within Cluster 7 compared to only 17 medications within the 69-72 hour time slot).

Additionally, Cluster 7 improved predictive models for fluid overload. A logistic regression model

including Cluster 7, APACHE score at 24 hours of ICU admission, and levels of diuretic administration

demonstrated an improvement in the model (Table 8). This was evidenced by a reduction in the AIC from

673.6 to 663.43, with a notably significant estimated p-value of <0.0005. Additionally, integrating this

feature in the model led to an enhanced ROC curve, elevating the AUC from 0.7193 to 0.7413 (Figure 8).

An additional visualization of the impact of Cluster 7 on predictive modeling can be seen in Figure 9.

Additionally, when dividing Cluster 7 into proportion of medications within Cluster 7 given at each day

of ICU stay, a higher proportion of Cluster 7 medications on Days 1 and 3 of ICU admission was

associated with increased risk of fluid overload (Table 9). Figure 10 shows the distribution of patients in

each group (fluid overload and non-fluid overload) based on proportion of their medications that matched

Cluster 7. Figure 11 is an example of the marginal effect of proportion of medications matching Cluster 7

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

and association with fluid overload when normalized to APACHE II score of 14 and receipt of no

diuretics.

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

DISCUSSION

This first of its kind analysis represents the integration of four novel concepts in the domain of

data-driven medication use optimization: (1) the application of unsupervised machine learning

methods to the entire MAR (including drug and dose), (2) incorporation of temporal data for

medication administration, (3) fluid overload prediction in the ICU, and (4) application of the

ICURx CDM. These methods identified a cluster of medications that both statistically and

clinically correlated with fluid overload and serves as a proof-of-concept for future

implementation studies evaluating how machine learning approaches could be integrated with

real-time EHR data to provide predictions at the bedside.

Building on unsupervised machine learning methods that analyzed just the names (i.e., excluding

dose, formulation, route) of medications received in the first 24 hours17,23,32, this is first time that

unsupervised machine learning methods have been applied to the comprehensive medication

regimen (i.e., including dose, formulation, route) up to 72 hours with an intent to explore how

patterns in medication use relate to clinically relevant outcomes. These findings bring together

two bodies of research: pharmacophenotyping as a means of identifying high risk patients, and

fluid overload prediction using machine learning methods. In two prior pharmacophenotyping

approaches, six pharmacophenotypes were identified that had unique patterns of associations

with patient outcomes; however, these groupings were notably quite large with limited ability for

clinical interpretation. Here, we found a more interpretable cluster, particularly when temporal

data were added. Indeed, we observed that incorporating timing of medication administration

into the unsupervised analysis provided further insight into development of fluid overload and

specific medications, which may have a more substantial impact if given early within the ICU

stay, and as such, marks an important exploration into the temporal component of medication

administration as it relates to outcomes.

The discerned connection between the distinct IV medication cluster and the heightened risk of

fluid overload underscores the need for a proactive and precise approach to medication

management in the ICU. Such an approach may entail meticulous evaluation of factors such as

timing, dosage, and the selection of specific IV medications, especially those falling within the

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

identified subgroup. These findings align with other fluid overload prediction algorithms, which

showed improvement when using machine learning and also that medications were highly ranked

on feature importance graphs.32-34 While all of the clusters contained a similar list of medications

(Figure 3), these clusters became more distinct and unique when the timing of medications was

included in the original cluster development (Figure 2). When including the timing of

medications, Cluster 7 was statistically correlated with fluid overload and also improved the

prediction model for fluid overload. This may indicate that the timing of medications is more

important than we realize and that artificial intelligence may represent the key to discovering

these complex relationships. Cluster 7 had a higher number of medications administered within

the first 24 hours compared to hours 25-48 or 49-72, which may be reflective of the importance

of the first 24 hours of ICU stay. This temporal distribution of medication administration implies

a potential association between early medication use and subsequent instances of fluid overload.

Additionally, the medications that appeared within Cluster 7 included a large number of

medications that clinically would be associated with fluid overload, including fluids themselves

and continuous infusions such as vasopressors and inotropes. This adds to the validity of the

clustering methods as the results are clinically correlated. As the proportion of medications

appearing in Cluster 7 increased, patients were more likely to develop fluid overload as indicated

in Figure 11, although this association is harder to discern when the proportion of medications

appearing in Cluster 7 is >20% due to the limited number of patients who met this criteria. The

greatest likelihood of developing fluid overload occurred when patients had between 10% and 20%

of their medications matching the Cluster 7 list. Logistic regressions for various breakpoints of

proportion of medications matching Cluster 7 can be found in the Supplementary Appendix.

From a clinical perspective, this could allow for incorporation of clinical decision support by

alerting practitioners to patients that have proportions of >10% matching Cluster 7, warranting

increased monitoring and evaluation of need for concentrating medications, restricting fluids, or

administration of diuretics. Overall, this lends more credence that medication data have a role in

improving ICU modeling.13,35

Finally, this study represents further application of the ICURx CDM, which was employed to

provide the algorithms with further information during the clustering process.17,36 While

information from ICURx CDM was not included in the final methodology for the clustering

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

process itself, it was used to provide further information about specific medications that were

used for subsequent analyses (IV push versus continuous infusion and sorting of medications

into classes). Results from this analysis could not fully evaluate the impact of medications in

different volumes of fluid which could be important clinically (e.g., giving cefepime as an IV

push medication compared to an intermittent infusion in 100mL of NS over 30 minutes) as the

initial data set did not include administration rate.

Our study has several limitations including a small sample size and retrospective data collection.

Additionally, due to the retrospective nature of this dataset, we chose a numerical definition for

fluid overload as opposed to a clinical assessment which may have under-identified those with

clinical fluid overload. Subsequently, bias may exist due to the availability of fluid balance data

for the included patients. Causal relationships cannot be assessed by the current study, so it is

unknown whether the high fluid overload observed in Patient Cluster 7 was partly caused by the

unique distribution of medication patterns versus other factors (although notably, Cluster 7

shared similarities among groups). Additionally, while it is very encouraging that we were able

to identify a cluster of medications that was statistically significantly associated with fluid

overload through AI methods, at this time, there are multiple limitations in trying to apply this

information to a clinical scenario. While there are many hypotheses generated from this

information, including which medications may have an undiscovered temporal effect with fluid

overload, there must be further research to apply this information at the bedside to have a clinical

impact. Even with these limitations, this analysis marks the first time the complete medication

profile has been incorporated into outcomes analysis for ICU patients. Future analyses with more

granular cluster groupings or more programmed directives incorporating data from a myriad of

ICUs and centers may improve the face validity. Artificial intelligence may provide clinical

outcome prediction and serve as a supplement to clinicians given its ability to process large

amounts of data in real-time.37-40 Ability to predict events in a critical care setting is highly

relevant and desirable given the challenge to predict outcomes in patients with rapidly changing

disease states and management.41,42 Overall, this evaluation is a first step and proof-of-concept

exploration into how unsupervised clustering methods may be applied to ICU medications,

particularly as it relates to the addition of temporal data.

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

CONCLUSION

Unsupervised machine learning uncovered a distinctive cluster of IV medications that exhibited a

robust correlation with the occurrence of fluid overload in the ICU setting. Delineating how

medications and their administration timing may influence development of fluid overload using

data driven methods may support future fluid overload prediction and mitigation strategies.

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

Table 1. Study population characteristics

Feature All

(n=927) Fluid overload

(n=127) No fluid

overload (n=800)

p-value

Age

, mean (SD)

60.9 (17.5) 55.7 (18.3) 61.7 (17.2) 0.0008

Female

, n (%)

398 (42.9) 68 (53.5) 330 (36.7) 0.01

Race, n (%) Caucasian

611 (65.9) 72 (56.7) 539 (59.9)

0.04

Black

218 (23.5) 35 (27.6) 183 (20.3)

Other

98 (10.6) 20 (15.7) 78 (8.7)

ICU type, n (%) Medical

368 (39.7) 58 (45.7) 310 (34.4)

<0.0001

Cardiac

286 (30.8) 14 (11.0) 272 (30.2)

Surgical

97 (10.5) 34 (26.8) 63 (7)

Neurosciences

91 (9.8) 7 (5.5) 84 (9.3)

Burn

65 (7) 11 (8.7) 54 (6.0)

Other

20 (2.2) 3 (2.4) 17 (1.9)

Admission diagnosis, n (%)

Cardiovascular

228 (24.6) 7 (5.5) 221 (24.6)

<0.0001

Neurology

117 (12.6) 9 (7.1) 108 (12)

Pulmonary

74 (8.0) 11 (8.7) 63 (7)

Trauma

49 (5.3) 15 (11.8) 34 (3.8)

Infection including sepsis

70 (7.6) 10 (7.9) 60 (6.7)

Gastrointestinal

69 (7.4) 18 (14.2) 51 (5.7)

Neoplasm

49 (5.3) 6 (4.7) 43 (4.8)

Dermatology

15 (1.6) 5 (3.9) 10 (1.1)

Renal

23 (2.5) 3 (2.4) 20 (2.2)

Endocrine

21 (2.3) 4 (3.1) 17 (1.9)

Other

212 (22.9) 39 (30.7) 273 (30.3)

Use of mechanical

ventilation, n (%) 305 (32.9) 72 (56.7) 233 (25.9) <0.0001

Renal Replacement

Therapy, n (%) 35 (3.8) 16 (12.6) 19 (2.4) <0.0001

Acute Kidney Injury

n (%)

148 (16) 45 (35.4) 103 (12.9) <0.0001

Medication Administrations

mean (SD) 51.2 (56.4) 96.4 (81.3) 44 (47.7) <0.0001

Medication Classes

, mean (SD)

Analgesics

7.9 (12.3) 17.6 (18.6) 6.4 (10.1) <0.0001

Antiarrhythmics

0.6 (3.5) 0.3 (1.7) 0.6 (3.7) 0.22

Antibiotics

3.2 (5.3) 6.4 (7) 2.7 (4.8) <0.0001

Anticoagulants

3.1 (9) 3.3 (9.7) 3.1 (8.9) 0.82

Anticonvulsants

0.1 (0.8) 17.6 (1.7) 6.4 (0.4) <0.0001

Antidotes/ Rescue Therapies

0 (0.1) 0 (0) 0 (0.1) 0.05

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

Antifungals

0 (0.3) 0.1 (0.4) 0 (0.3) 0.50

Antihypertensives

1.3 (6.2) 0.5 (5.3) 1.4 (6.3) 0.08

Antiplatelets

0.1 (0.8) 0 (0) 0.1 (0.9) 0.06

Diabetic Agents

2.6 (4.9) 2.7 (4.9) 2.6 (5) 0.84

Diuretics

0 (0.3) 0 (0.1) 0 (0.3) 0.42

Fluids

11.2 (14.2) 20.3 (17.2) 9.7 (13.1) <0.0001

Gastric Agents

1.6 (2.5) 2.5 (2.6) 1.5 (2.4) <0.0001

Hypertonic Saline

0.2 (2.4) 0.3 (2.6) 0.2 (2.4) 0.87

Immunosuppressants

0 (0.1) 0 (0.4) 0 (0) 0.32

Inotropic Agents

0.7 (4.4) 0.3 (2.2) 0.8 (4.7) 0.05

Neuromuscular Blocking

Agents)

0.1 (0.5) 0.1 (0.3) 0.1 (0.5) 0.49

Sedatives

9.4 (17.7) 19.2 (27.3) 7.8 (15) <0.0001

Somatostatic Agents

0 (0.1) 0 (0.3) 0 (0.2) 0.27

Total parenteral nutrition

0.1 (1.1) 0.4 (2.7) 0 (0.4) 0.16

Vasopressors

8.9 (23.3) 22.1 (40.6) 6.8 (18.4) <0.0001

Severity scores at 24 hours of ICU admission

APACHE II

, mean (SD)

14.5 (6.4) 17.4 (6.9) 14 (6.2) <0.0001

SOFA

, mean (SD)

8.1 (3.3) 10.5 (3.4) 7.8 (3.2) <0.0001

Patient outcomes

hospital

Mortality

, n (%)

88 (9.5) 23 (18.1) 65 (8.1) 0.0007

Maximum Fluid Overload at

72 h, mL, mean (SD) 2364.9

(3995.5) 9519.9 (5629.2) 1229 (2018.7) <0.0001

ICU length of stay

, days,

mean (SD) 2.9 (9.8) 9.7 (13.9) 4.5 (8.7) <0.0001

Data are presented as n (%) or mean (standard deviation (SD)) unless otherwise stated.

SOFA sequential organ failure assessment, APACHE II Acute Physiology and Chronic Health

Evaluation; ICU intensive care unit. P-values from t.test (variables with mean and SD) and chi-square

test (variables with count and %).

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

Table 2. Distribution of medication classes within each medication cluster

Cluster

(N=121)

(N=128)

(N=130)

(N=125)

(N=126)

(N=127)

(N=125)

(N=123)

(N=125)

Analgesic (N=175)

12.4

13.28

14.62

13.6

14.29

14.17

13.39

14.4

14.63

14.4

Antiarrhythmic (N=66)

4.96

5.47

4.62

5.6

5.56

4.72

5.51

4.8

5.69

5.6

Antibiotic (N=248)

20.66

18.75

21.54

19.05

20.47

18.9

20.8

19.51

17.6

Anticoagulant (N=109)

9.09

8.59

8.46

8.8

8.73

9.45

8.66

8.94

Anticonvulsants (N=27)

2.48

2.34

2.31

2.4

2.38

0.79

2.36

2.4

1.63

2.4

Antifungal Agent(N=10)

0.83

0.78

0.77

0.8

0.79

0.8

0.81

0.8

Antihypertensive (N=30)

2.48

2.34

2.31

2.4

2.38

2.36

2.4

2.44

2.4

Antiplatelet (N=10)

0.83

0.78

0.77

0.8

0.79

0.8

0.81

0.8

Antifungal (N=9)

0.83

0.78

0.77

0.8

0.79

0.8

Diabetic Agents (N=10)

0.83

0.78

0.77

0.8

0.79

0.8

0.81

0.8

Diuretic (N=14)

0.83

1.56

0.77

0.8

1.59

1.57

0.8

0.81

0.8

Fluids (N=143)

11.57

10.94

11.54

11.9

11.02

11.2

11.38

11.2

Gastric Agent (N=40)

3.31

3.13

3.08

3.2

3.17

3.15

3.2

3.25

3.2

Hypertonic Saline (N=19)

1.65

1.56

1.54

1.6

1.59

1.57

1.6

0.81

1.6

Inotropic Agent (N=40)

3.31

3.13

3.08

3.2

3.17

3.15

3.2

3.25

3.2

Neuromuscular blocking

agents (N=40) 3.31 3.91 2.31 3.2 2.38 2.36 3.94 3.2 2.44 4.8

Sedative (N=138)

11.57

10.94

10.4

11.11

11.02

11.2

11.38

11.2

Somatostatic Agents

(N=10) 0.83 0.78 0.77 0.8 0.79 0.79 0.79 0.8 0.81 0.8

TPN (N=10)

0.83

0.78

0.77

0.8

0.79

0.8

0.81

0.8

Vasopressor (N=97)

7.44

7.81

7.69

7.14

7.87

7.09

8.13

Antidotes/

Rescue Therapy (N=5) 0 0.78 0.77 0 0 0.79 0.79 0 0.81 0

Immunosuppressant (N=7)

0.78

0.77

0.79

0.81

0.8

N represents the number of medications, with each column summing to 100%

Table 3. Rank Sum Test for Each Medication Cluster

Rank Sum Test Results for Medication Clusters (Standardized Proportions across Patients) and Fluid

Overload

Cluster Non-fluid overload Fluid overload p-value

Cluster 1 0.09 (0.07) 0.08 (0.03) 0.34

Cluster 2 0.11 (0.08) 0.12 (0.04) 0.19

Cluster 3 0.10 (0.07) 0.10 (0.04) 0.93

Cluster 4 0.10 (0.06) 0.10 (0.04) 0.78

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

Cluster 5 0.07 (0.06) 0.08 (0.04) 0.0009*

Cluster 6 0.11 (0.07) 0.10 (0.04) 0.13

Cluster 7 0.10 (0.06) 0.11 (0.04) 0.002*

Cluster 8 0.10 (0.06) 0.10 (0.04) 0.90

Cluster 9 0.11 (0.08) 0.11 (0.04) 0.49

Cluster 10 0.10 (0.08) 0.10 (0.05) 0.06

*statistical significance with p

≤

0.05

Table 4. Logistic Regression for Each Cluster

Results of 10 Fitted Logistic Regression Models: Dependent Variable - Fluid Overload, Independent

Variable - Medication Clusters (Standardized Proportions across Patients).

10 Logistic

Regression

Models Estimated Value P Value

Cluster 1 -2.10 0.22

Cluster 2 0.42 0.73

Cluster 3 -1.41 0.38

Cluster 4 0.16 0.92

Cluster 5 2.68 0.07

Cluster 6 -2.97 0.08

Cluster 7 2.96 0.05*

Cluster 8 -0.87 0.58

Cluster 9 -0.12 0.93

Cluster 10 0.56 0.64

*statistical significance with p

≤

0.05

Table 5. Frequency of Medications Appearing in Cluster 7

Medication Frequency

albumin, human 25 % intravenous solution 6

albumin, human 5 % intravenous solution 8

alteplase 0.81 mg/kg stroke infusion 2

amiodarone 150 mg/100 ml (1.5 mg/ml) in dextrose, iso-

osmotic iv 6

amiodarone 360 mg/200 ml (1.8 mg/ml) in dextrose, iso-

osmotic iv 6

amiodarone 450 mg/250 ml (1.8 mg/ml) in dextrose 5 %

intravenous solution 4

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

aztreonam 1 gram solution for iv push 1

aztreonam 2 gram solution for iv push 1

cefazolin 1 gram/50 ml in dextrose (iso-osmotic) intravenous

piggyback 5

cefazolin 2 gram/100 ml in dextrose(iso-osmotic)

intravenous piggyback 3

cefazolin 2 gram/50 ml in dextrose (iso-osmotic) intravenous

piggyback 4

cefazolin 3 gram/100 ml in 0.9 % sodium chloride intravenous

piggyback 3

cefepime 1 gram solution for injection 4

cefepime 2 gram/100 ml in dextrose (iso-osmotic) intravenous

piggyback 4

ceftriaxone 1 gram solution for injection 1

ceftriaxone 1 gram/50 ml in dextrose (iso-osmotic) intravenous

piggyback 1

ceftriaxone 2 gram/50 ml in dextrose (iso-osmotic) intravenous

piggyback 1

cisatracurium 2 mg/ml intravenous solution 1

clevidipine 25 mg/50 ml intravenous emulsion 10

clindamycin 600 mg/50 ml in 5 % dextrose intravenous

piggyback 8

clindamycin 900 mg/50 ml in 5 % dextrose intravenous

piggyback 7

cyclosporine 1 mg/ml ns aviva iv 3

dexmedetomidine 200 mcg/50 ml (4 mcg/ml) in 0.9 % sodium

chloride iv 3

dexmedetomidine 400 mcg/100 ml (4 mcg/ml) in 0.9 % sodium

chloride iv 8

dextrose 10 % in water (d10w) intravenous solution 4

dextrose 10 % iv bolus 3

dextrose 5 % and 0.45 % sodium chloride intravenous solution 4

dextrose 5 % and 0.9 % sodium chloride intravenous solution 3

dextrose 5 % and lactated ringers intravenous solution 6

dextrose 5 % in water (d5w) intravenous solution 6

diazepam 5 mg/ml injection syringe 6

digoxin 250 mcg/ml (0.25 mg/ml) injection solution 2

dobutamine 1,000 mg/250 ml(4,000 mcg/ml) in 5 % dextrose iv 5

dobutamine 250 mg/250 ml (1 mg/ml) in 5 % dextrose

intravenous 9

dobutamine 500 mg/250 ml (2,000 mcg/ml) in 5 % dextrose

iv 4

dopamine 400 mg/250 ml (1,600 mcg/ml) in 5 % dextrose

intravenous solution 3

dopamine 800 mg/500 ml (1,600 mcg/ml) in 5 % dextrose 6

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

intravenous solution

epinephrine hcl 8 mg/250 ml (32 mcg/ml) in 5 % dextrose

intravenous 3

eptifibatide 0.75 mg/ml intravenous solution 4

esmolol 2,500 mg/250 ml (10 mg/ml) in sodium chloride (iso-

osmotic) iv 2

etomidate 2 mg/ml intravenous solution 3

famotidine (pf) 20 mg/2 ml intravenous solution 6

famotidine (pf) 20 mg/50 ml in 0.9 % sodium chloride (iso)

intravenous piggyback 11

famotidine 10 mg/ml inj solution (multi-vial size) 4

fat emulsion 20 % intravenous 6

fentanyl (pf) 10 mcg/ml in 0.9 % sodium chloride intravenous

wrapper 6

fentanyl (pf) 2,500 mcg/50 ml (50 mcg/ml) intravenous pca

syringe 2

fentanyl (pf) 50 mcg/ml injection solution 8

fentanyl (sublimaze) 100 mcg in ns 50ml (rex or) 1

fluconazole 200 mg/100 ml in sod. chloride (iso) intravenous

piggyback 4

fluconazole 400 mg/200 ml in sod. chloride(iso) intravenous

piggyback 3

heparin (porcine) 1,000 unit/500 ml in 0.9% sodium chloride iv

(combined) 1

heparin (porcine) 1,000 unit/ml injection solution 6

heparin (porcine) 10,000 unit/1,000 ml in 0.9 % sod. chloride iv

solution 1

heparin (porcine) 10,000 unit/ml injection solution 2

heparin (porcine) 100 unit/ml bolus from infusion 3

heparin (porcine) 100 unit/ml load from infusion 1

heparin (porcine) 25,000 unit/250 ml in 0.45 % sodium chloride

iv solution 4

heparin (porcine) for crrt 25,000 unit/250 ml in 0.45 % sodium

chloride iv solution 5

heparin 30,000 units (cell saver) in 1000 ml ns 1

heparin, porcine (pf) 10 unit/ml intravenous syringe 3

heparin, porcine (pf) 100 unit/ml intravenous syringe 4

hydromorphone (pf) 1 mg/ml injection solution 2

hydromorphone 1 mg/ml in ns infusion wrapper 5

hydromorphone 1 mg/ml injection syringe 5

hydromorphone 2 mg/ml injection syringe 9

hydromorphone 50 mg/50 ml (1 mg/ml) in 0.9 % sodium

chloride iv pump resevoir 3

insulin u-100 regular human 100 unit/ml injection solution 4

lactated ringers intravenous solution 8

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

lactated ringers irrigation solution 1

lactated ringers iv bolus 4

levofloxacin 500 mg/100 ml in 5 % dextrose intravenous

piggyback 2

levofloxacin 750 mg/150 ml in 5 % dextrose intravenous

piggyback 7

lidocaine (pf) 100 mg/5 ml (2 %) intravenous syringe 2

lidocaine (pf) 4 mg/ml (0.4 %) in 5 % dextrose intravenous

solution 4

linezolid in 5% dextrose in water 600 mg/300 ml intravenous

piggyback 9

lorazepam 2 mg/ml injection syringe 7

lorazepam 2 mg/ml injection wrapper 6

mannitol 20 % intravenous solution 3

mannitol 25 % intravenous solution 2

meperidine (pf) 25 mg/ml injection syringe 5

metronidazole 500 mg/100 ml-sodium chloride(iso) intravenous

piggyback 5

midazolam (pf) 1 mg/ml in 0.9 % sodium chloride intravenous

solution 6

midazolam (pf) 1 mg/ml injection solution 3

midazolam (pf) 5 mg/ml injection solution 1

midazolam 1 mg/ml in 0.9 % sodium chloride intravenous 5

midazolam 1 mg/ml injection solution 7

midazolam 5 mg/ml (combined) injection solution wrapper 3

milrinone 20 mg/100 ml(200 mcg/ml) in 5 % dextrose

intravenous piggyback 2

morphine (pf) 1 mg/ml in 0.9% sodium chloride intravenous

solution 1

morphine 1 mg/ml in 0.9 % sodium chloride injectable pump

reservoir 3

morphine 1 mg/ml in dextrose 5 % intravenous solution 6

morphine 10 mg/ml injection solution 5

morphine 2 mg/ml injection pf wrapper 7

morphine 2 mg/ml intravenous cartridge 6

morphine 4 mg/ml intravenous cartridge 7

nitroglycerin 100 mg/250 ml (400 mcg/ml) in 5 % dextrose

intravenous 3

nitroglycerin 50 mg/250 ml (200 mcg/ml) in 5 % dextrose

intravenous 5

norepinephrine bitartrate 8 mg/250 ml (32 mcg/ml) in 0.9 %

sodium chloride iv 6

norepinephrine bitartrate 8 mg/250 ml (32 mcg/ml) in dextrose

5 % iv 3

octreotide acetate 100 mcg/ml injection solution 4

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

pantoprazole 40 mg intravenous solution 8

pentobarbital 2500mg/50 ml adult infusion 2

pentobarbital sodium 50 mg/ml injection solution 1

phenobarbital sodium 65 mg/ml injection solution 7

phenylephrine 20 mg/250 ml (80 mcg/ml) in 0.9 % sodium

chloride iv 6

piperacillin-tazobactam 2.25 gram/50 ml in dextrose(iso) iv

piggyback 2

piperacillin-tazobactam 3.375 gm/50ml dextrose (extended

duration) 14

piperacillin-tazobactam 3.375 gram/50 ml dextrose(iso-

osmotic) iv piggyback 5

piperacillin-tazobactam 4.5 gram/100 ml dextrose(iso-osmotic)

iv piggyback 3

propofol 10 mg/ml intravenous emulsion 4

propofol infusion 10 mg/ml 9

rocuronium 10 mg/ml intravenous solution 1

sodium chloride 0.45 % intravenous solution 6

sodium chloride 0.9 % intravenous solution 4

sodium chloride 3 % intravenous bolus solution 1

sodium chloride 3 % intravenous injection solution 4

sodium chloride 4 meq/ml intravenous solution 4

succinylcholine chloride 20mg/ml syringe/vial wrapper 1

vancomycin 1 gram/200 ml in dextrose 5 % intravenous

piggyback 8

vancomycin 1.25 gram/250 ml in 0.9 % sodium chloride

intravenous 2

vancomycin 1.5 gram/500 ml in 0.9 % sodium chloride

intravenous solution 3

vasopressin (pitressin) infusion 40 units/100 ml 7

vasopressin (pitressin) infusion 50 unit/50 ml 1

vasopressin 40 units/50 ml (0.8 unit/ml) ssc premade

infusion 4

vecuronium bromide 10 mg intravenous solution 1

vecuronium bromide 20 mg intravenous solution 1

*bolded medications indicate those that only appeared in Cluster 7 if given during the first 24 hours of

ICU admission

Table 6. Proportion of Medications Appearing in Cluster 7 by Day and Fluid Overload Status

Proportion of Medications

Matching Cluster 7, median Fluid Overload Group Non-Fluid Overload Group

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

(IQR)

Hours 0-24 of ICU admission 52.4 (33.9-70.4) 33.3 (14.3-51.2)

Hours 25-48 of ICU admission 50 (22.2-65.4) 18.8 (5.6-40.7)

Hours 49-72 of ICU admission 32.4 (11.8-50) 7.7 (0-22.5)

Hours 0-72 of ICU admission 46.3 (30.4,60.7) 25.2 (11.8-40)

Proportions are calculated on a patient-specific level; the percentage is reported is the median

proportion of medications matching Cluster 7 using individual patient data rather than aggregate

data. For example, of the medications received in the first 24 hours of ICU stay, 52.4% of those

medications were also present in Cluster 7 for the median patient in the fluid overload group,

compared to 33.3% of medications in the non-fluid overload group.

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

Table 7. Cluster 7 medications by ICU day

Distribution of Medications in Cluster 7 Across ICU Days (Day 1: 0-24 hours, Day 2: 24-48

hours, Day 3: 48-72 hours), N is total number of medications that appeared within that day

DAY1 (N= 190)

DAY2 (N= 179)

DAY3 (N=171)

albumin, human 25 % intravenous solution

albumin, human 25 % intravenous

solution

albumin, human 5 % intravenous solution

alteplase 0.81 mg/kg stroke infusion

amiodarone 150 mg/100 ml (1.5 mg/ml) in

dextrose, iso-osmotic iv

amiodarone 150 mg/100 m

l (1.5 mg/ml) in

dextrose, iso-osmotic iv

amiodarone 150 mg/100 ml (1.5 mg/ml) in

dextrose, iso-osmotic iv

amiodarone 360 mg/200 ml (1.8 mg/ml) in

dextrose, iso-osmotic iv

amiodarone 360 mg/200 ml (1.8 mg/ml) in

dextrose, iso-osmotic iv

amiodarone 360

mg/200 ml (1.8 mg/ml) in

dextrose, iso-osmotic iv

amiodarone 450 mg/250 ml (1.8 mg/ml) in

dextrose 5 % intravenous solution

amiodarone 450 mg/250 ml (1.8 mg/ml) in

dextrose 5 % intravenous solution

amiodarone 450 mg/250 ml (1.8 mg/ml) in

dextrose 5 % intravenous solution

aztreonam 2 gram solution for iv push

cefazolin 1 gram/50 ml in dextrose (iso

osmotic) intravenous piggyback

aztreonam 1 gram solution for iv push

cefepime 1 gram solution for injection

cefazolin 2 gram/100 ml in dextrose(iso

osmotic) intravenous piggyback

cefazolin 1 gram/50 ml in dextrose (iso

osmotic) intravenous piggyback

cefepime 2 gram/100 ml in dextrose (iso

osmotic) intravenous piggyback

cefazolin 2 gram/50 ml in dextrose (iso

osmotic) intravenous piggyback

cefazolin 2 gram/100 m

l in dextrose(iso

osmotic) intravenous piggyback

ceftriaxone 2 gram/50 ml in dextrose (iso

osmotic) intravenous piggyback

cefepime 1 gram solution for injection

cefazolin 2 gram/50 ml in dextrose (iso

osmotic) intravenous piggyback

clevidipine

25 mg/50 ml intravenous emulsion

cefepime 2 gram/100 ml in dextrose (iso

osmotic) intravenous piggyback

cefazolin 3 gram/100 ml in 0.9 % sodium

chloride intravenous piggyback

clindamycin 600 mg/50 ml in 5 % dextrose

intravenous piggyback

ceftriaxone 1

gram/50 ml in dextrose (iso

osmotic) intravenous piggyback

cefepime 1 gram solution for injection

clindamycin 900 mg/50 ml in 5 % dextrose

intravenous piggyback

clevidipine 25 mg/50 ml intravenous emulsion

cefepime 2 gram/100 ml in dextrose (iso

osmotic) intravenous piggyback

cyclosporine 1 mg/ml ns aviva iv

clindamycin 600 mg/50 ml in 5 % dextrose

intravenous piggyback

ceftriaxone 1 gram solution for injection

dexmedetomidine 200 mcg/50 ml (4 mcg/ml) in

0.9 % sodium chloride iv

clindamycin 900 mg/50 ml

in 5 % dextrose

intravenous piggyback

cisatracurium 2 mg/ml intravenous solution

dexmedetomidine 400 mcg/100 ml (4 mcg/ml)

in 0.9 % sodium chloride iv

cyclosporine 1 mg/ml ns aviva iv

clevidipine 25 mg/50 ml intravenous emulsion

dextrose 10 % in water

(d10w) intravenous

solution

dexmedetomidine 200 mcg/50 ml (4 mcg/ml) in

0.9 % sodium chloride iv

clindamycin 600 mg/50 ml in 5 % dextrose

intravenous piggyback

dextrose 10 % iv bolus

dexmedetomidine 400 mcg/100 ml (4 mcg/ml)

in 0.9 % sodium chloride iv

lindamycin 900 mg/50 ml in 5 % dextrose

intravenous piggyback

dextrose 5 % and 0.45 % sodium chloride

intravenous solution

dextrose 10 % in water (d10w) intravenous

solution

dexmedetomidine 400 mcg/100 ml (4 mcg/ml)

in 0.9 % sodium chloride iv

dextrose 5

% and 0.9 % sodium chloride

intravenous solution

dextrose 10 % iv bolus

dextrose 5 % and 0.9 % sodium chloride

intravenous solution

dextrose 5 % and lactated ringers intravenous

solution

dextrose 5 % and 0.45 % sodium chloride

intravenous solution

dextrose 5 % and lactated ringers intravenous

solution

dextrose 5 % in water (d5w) intravenous

solution

dextrose 5 % and lactated ringers intravenous

solution

dextrose 5 % in water (d5w) intravenous

solution

diazepam 5 mg/ml injection syringe

dextrose 5 %

in water (d5w) intravenous

solution

diazepam 5 mg/ml injection syringe

dobutamine 250 mg/250 ml (1 mg/ml) in 5 %

dextrose intravenous

diazepam 5 mg/ml injection syringe

digoxin 250 mcg/ml (0.25 mg/ml) injection

solution

dobutamine 500 mg/250 ml (2,000

mcg/ml) in

5 % dextrose iv

dobutamine 1,000 mg/250 ml(4,000 mcg/ml) in

5 % dextrose iv

dobutamine 1,000 mg/250 ml(4,000 mcg/ml) in

5 % dextrose iv

dopamine 400 mg/250 ml (1,600 mcg/ml) in

5 % dextrose intravenous solution

dobutamine 250 mg/250 ml (1

mg/ml) in 5 %

dextrose intravenous

dobutamine 250 mg/250 ml (1 mg/ml) in 5 %

dextrose intravenous

dopamine 800 mg/500 ml (1,600 mcg/ml) in

5 % dextrose intravenous solution

dopamine 800 mg/500 ml (1,600 mcg/ml) in

5 % dextrose intravenous solution

dobuta

mine 500 mg/250 ml (2,000 mcg/ml) in

5 % dextrose iv

epinephrine hcl 8 mg/250 ml (32 mcg/ml) in

5 % dextrose intravenous

epinephrine hcl 8 mg/250 ml (32 mcg/ml) in

5 % dextrose intravenous

dopamine 400 mg/250 ml (1,600 mcg/ml) in

5 % dextrose intravenous solution

eptifibatide 0.75 mg/ml intravenous solution

etomidate 2 mg/ml intravenous solution

dopamine 800 mg/500 ml (1,600 mcg/ml) in

5 % dextrose intravenous solution

esmolol 2,500 mg/250 ml (10 mg/ml) in sodium

chloride (iso-osmotic) iv

famotidine (pf)

20 mg/2 ml intravenous solution

epinephrine hcl 8 mg/250 ml (32 mcg/ml) in

5 % dextrose intravenous

etomidate 2 mg/ml intravenous solution

famotidine (pf) 20 mg/50 ml in 0.9 % sodium

chloride (iso) intravenous piggyback

eptifibatide 0.75 mg/ml

intravenous solution

famotidine (pf) 20 mg/2 ml intravenous solution

famotidine 10 mg/ml inj solution (multi

vial

size)

esmolol 2,500 mg/250 ml (10 mg/ml) in sodium

chloride (iso-osmotic) iv

famotidine (pf) 20 mg/50 ml in 0.9 % sodium

chloride (iso) intravenous piggyback

fat emulsion 20 % intravenous

etomidate 2 mg/ml intravenous solution

fat emulsion 20 % intravenous

fentanyl (pf) 10 mcg/ml in 0.9 % sodium

chloride intravenous wrapper

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

famotidine (pf) 20 mg/2 ml intravenous solution

fentanyl (pf) 10 mcg/

ml in 0.9 % sodium

chloride intravenous wrapper

fentanyl (pf) 50 mcg/ml injection solution

famotidine (pf) 20 mg/50 ml in 0.9 % sodium

chloride (iso) intravenous piggyback

fentanyl (pf) 2,500 mcg/50 ml (50 mcg/ml)

intravenous pca syringe

fluconazole 200

mg/100 ml in sod. chloride

(iso) intravenous piggyback

famotidine 10 mg/ml inj solution (multi

vial

size)

fentanyl (pf) 50 mcg/ml injection solution

heparin (porcine) 1,000 unit/500 ml in 0.9%

sodium chloride iv (combined)

fat emulsion 20 % intravenous

entanyl (sublimaze) 100 mcg in ns 50ml (rex

or)

heparin (porcine) 1,000 unit/ml injection

solution

fentanyl (pf) 10 mcg/ml in 0.9 % sodium

chloride intravenous wrapper

fluconazole 400 mg/200 ml in sod. chloride(iso)

intravenous piggyback

heparin (porcine)

10,000 unit/1,000 ml in 0.9 %

sod. chloride iv solution

fentanyl (pf) 2,500 mcg/50 ml (50 mcg/ml)

intravenous pca syringe

heparin (porcine) 1,000 unit/ml injection

solution

heparin (porcine) 10,000 unit/ml injection

solution

fentanyl (pf) 50 mcg/ml inje

ction solution

heparin (porcine) 10,000 unit/ml injection

solution

heparin (porcine) 100 unit/ml bolus from

infusion

fluconazole 200 mg/100 ml in sod. chloride

(iso) intravenous piggyback

heparin (porcine) 100 unit/ml bolus from

infusion

heparin (porcine)

25,000 unit/250 ml in 0.45 %

sodium chloride iv solution

fluconazole 400 mg/200 ml in sod. chloride(iso)

intravenous piggyback

heparin (porcine) 25,000 unit/250 ml in 0.45 %

sodium chloride iv solution

heparin (porcine) for crrt 25,000 unit/250 ml in

0.45 % sodium chloride iv solution

heparin (porcine) 1,000 unit/ml injection

solution

heparin (porcine) for crrt 25,000 unit/250 ml in

0.45 % sodium chloride iv solution

heparin, porcine (pf) 10 unit/ml intravenous

syringe

heparin (porcine) 100 unit/ml bolu

s from

infusion

heparin 30,000 units (cell saver) in 1000 ml ns

heparin, porcine (pf) 100 unit/ml intravenous

syringe

heparin (porcine) 100 unit/ml load from

infusion

heparin, porcine (pf) 10 unit/ml intravenous

syringe

hydromorphone (pf) 1 mg/ml

injection solution

heparin (porcine) 25,000 unit/250 ml in 0.45 %

sodium chloride iv solution

heparin, porcine (pf) 100 unit/ml intravenous

syringe

hydromorphone 1 mg/ml in ns infusion wrapper

heparin (porcine) for crrt 25,000 unit/250 ml in

0.45 % sodium chloride iv solution

hydromorphone 1 mg/ml in ns infusion wrapper

hydromorphone 2 mg/ml injection syringe

heparin, porcine (pf) 10 unit/ml intravenous

syringe

hydromorphone 1 mg/ml injection syringe

hydromorphone 50 mg/50 ml (1 mg/ml) in

0.9 % sodium chloride iv pump resevoir

hydromorphone 1 mg/ml in ns infusion wrapper

hydromorphone 2 mg/ml injection syringe

lactated ringers intravenous solution

hydromorphone 1 mg/ml injection syringe

hydromorphone 50 mg/50 ml (1 mg/ml) in

0.9 % sodium chloride iv pump resevoir

lactated ringers iv bolus

hydromorphone 2 mg/ml injection syringe

insulin u

100 regular human 100 unit/ml

injection solution

levofloxacin 500 mg/100 ml in 5 % dextrose

intravenous piggyback

hydromorphone 50 mg/50 ml (1 mg/ml) in

0.9 % sodium chloride iv pump resevoir

lactated ringers intravenous solution

levofloxacin 750 mg/150 ml in 5 % dextrose

intravenous piggyback

lactated ringers intravenous solution

lactated ringers iv bo

lus

lidocaine (pf) 4 mg/ml (0.4 %) in 5 % dextrose

intravenous solution

lactated ringers irrigation solution

levofloxacin 500 mg/100 ml in 5 % dextrose

intravenous piggyback

linezolid in 5% dextrose in water 600 mg/300

ml intravenous piggyback

lactated

ringers iv bolus

levofloxacin 750 mg/150 ml in 5 % dextrose

intravenous piggyback

lorazepam 2 mg/ml injection syringe

levofloxacin 750 mg/150 ml in 5 % dextrose

intravenous piggyback

lidocaine (pf) 100 mg/5 ml (2 %) intravenous

syringe

lorazepam 2 mg/ml i

njection wrapper

lidocaine (pf) 100 mg/5 ml (2 %) intravenous

syringe

lidocaine (pf) 4 mg/ml (0.4 %) in 5 % dextrose

intravenous solution

mannitol 25 % intravenous solution

linezolid in 5% dextrose in water 600 mg/300

ml intravenous piggyback

linezolid i

n 5% dextrose in water 600 mg/300

ml intravenous piggyback

metronidazole 500 mg/100 ml

sodium

chloride(iso) intravenous piggyback

lorazepam 2 mg/ml injection syringe

midazolam (pf) 1 mg/ml in 0.9 % sodium

chloride intravenous solution

lorazepam 2 mg/ml injection wrapper

midazolam (pf) 1 mg/ml injection solution

mannitol 20 % intravenous solution

mannitol 25 % intravenous solution

midazolam 1 mg/ml in 0.9 % sodium chloride

intravenous

meperidine (pf) 25 mg/ml injection syringe

midazolam 1 mg/ml injection solution

metronidazole 500 mg/100 ml

sodium

chloride(iso) intravenous piggyback

metronidazole 500 mg/100 ml

sodium

chloride(iso) intravenous piggyback

midazolam 5 mg/ml (combined) injection

solution wrapper

midazolam (pf) 1 mg/ml in 0.9 % sodium

chloride intravenous solution

midazolam (pf) 1 mg/ml in 0.9 % sodium

chloride intravenous solution

milrinone 20 mg/100 ml(200 mcg/ml) in

5 %

dextrose intravenous piggyback

midazolam (pf) 1 mg/ml injection solution

midazolam 1 mg/ml injection solution

morphine 1 mg/ml in dextrose 5 % intravenous

solution

midazolam (pf) 5 mg/ml injection solution

morphine (pf) 1 mg/ml in 0.9% sodium chlorid

intravenous solution

morphine 10 mg/ml injection solution

midazolam 1 mg/ml in 0.9 % sodium chloride

intravenous

morphine 1 mg/ml in dextrose 5 % intravenous

solution

morphine 2 mg/ml intravenous cartridge

midazolam 1 mg/ml injection solution

morphine

10 mg/ml injection solution

morphine 4 mg/ml intravenous cartridge

midazolam 5 mg/ml (combined) injection

solution wrapper

morphine 2 mg/ml injection pf wrapper

norepinephrine bitartrate 8 mg/250 ml (32

mcg/ml) in 0.9 % sodium chloride iv

milrinone 20 mg/100 ml(200 mcg/ml) in 5 %

dextrose intravenous piggyback

morphine 2 mg/ml intravenous cartridge

octreotide acetate 100 mcg/ml injection solution

morphine 1 mg/ml in 0.9 % sodium chloride

injectable pump reservoir

morphine 4 mg/ml intraveno

us cartridge

pantoprazole 40 mg intravenous solution

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

morphine 10 mg/ml injection solution

nitroglycerin 100 mg/250 ml (400 mcg/ml) in

5 % dextrose intravenous

pentobarbital 2500mg/50 ml adult infusion

morphine 2 mg/ml injection pf wrapper

nitroglycerin

50 mg/250 ml (200 mcg/ml) in

5 % dextrose intravenous

phenylephrine 20 mg/250 ml (80 mcg/ml) in

0.9 % sodium chloride iv

morphine 2 mg/ml intravenous cartridge

norepinephrine bitartrate 8 mg/250 ml (32

mcg/ml) in 0.9 % sodium chloride iv

piperacillin

tazo

bactam 2.25 gram/50 ml in

dextrose(iso) iv piggyback

morphine 4 mg/ml intravenous cartridge

norepinephrine bitartrate 8 mg/250 ml (32

mcg/ml) in dextrose 5 % iv

piperacillin

tazobactam 3.375 gm/50ml

dextrose (extended duration)

nitroglycerin 100 mg/250 m

l (400 mcg/ml) in

5 % dextrose intravenous

pantoprazole 40 mg intravenous solution

piperacillin

tazobactam 3.375 gram/50 ml

dextrose(iso-osmotic) iv piggyback

nitroglycerin 50 mg/250 ml (200 mcg/ml) in

5 % dextrose intravenous

pentobarbital sodium 50

mg/ml injection

solution

piperacillin

tazobactam 4.5 gram/100 ml

dextrose(iso-osmotic) iv piggyback

norepinephrine bitartrate 8 mg/250 ml (32

mcg/ml) in 0.9 % sodium chloride iv

phenobarbital sodium 65 mg/ml injection

solution

propofol 10 mg/ml intravenou

s emulsion

norepinephrine bitartrate 8 mg/250 ml (32

mcg/ml) in dextrose 5 % iv

phenylephrine 20 mg/250 ml (80 mcg/ml) in

0.9 % sodium chloride iv

sodium chloride 0.45 % intravenous solution

octreotide acetate 100 mcg/ml injection solution

piperacillin

azobactam 3.375 gm/50ml

dextrose (extended duration)

sodium chloride 0.9 % intravenous solution

pantoprazole 40 mg intravenous solution

piperacillin

tazobactam 3.375 gram/50 ml

dextrose(iso-osmotic) iv piggyback

sodium chloride 3 % intravenous injection

solution

phenobarbital sodium 65 mg/ml injection

solution

piperacillin

tazobactam 4.5 gram/100 ml

dextrose(iso-osmotic) iv piggyback

sodium chloride 4 meq/ml intravenous solution

phenylephrine 20 mg/250 ml (80 mcg/ml) in

0.9 % sodium chloride iv

propofol

10 mg/ml intravenous emulsion

vancomycin 1 gram/200 ml in dextrose 5 %

intravenous piggyback

piperacillin

tazobactam 2.25 gram/50 ml in

dextrose(iso) iv piggyback

propofol infusion 10 mg/ml

vasopressin (pitressin) infusion 40 units/100 ml

piperacillin

zobactam 3.375 gm/50ml

dextrose (extended duration)

sodium chloride 0.45 % intravenous solution

vasopressin 40 units/50 ml (0.8 unit/ml) ssc

premade infusion

piperacillin

tazobactam 3.375 gram/50 ml

dextrose(iso-osmotic) iv piggyback

sodium chloride 0.9 %

intravenous solution

propofol infusion 10 mg/ml

sodium chloride 3 % intravenous bolus solution

rocuronium 10 mg/ml intravenous solution

sodium chloride 3 % intravenous injection

solution

sodium chloride 0.45 % intravenous solution

sodium chloride 4

meq/ml intravenous solution

sodium chloride 0.9 % intravenous solution

vancomycin 1 gram/200 ml in dextrose 5 %

intravenous piggyback

sodium chloride 3 % intravenous injection

solution

vancomycin 1.5 gram/500 ml in 0.9 % sodium

chloride intravenous solution

sodium chloride 4 meq/ml intravenous solution

vasopressin (pitressin) infusion 40 units/100 ml

succinylcholine chloride 20mg/ml syringe/vial

wrapper

vasopressin (pitressin) infusion 50 unit/50 ml

vancomycin 1 gram/200 ml in dextrose 5 %

intravenous piggyback

vecuronium bromide 10 mg intr avenous

solution

vancomycin 1.25 gram/250 ml in 0.9 % sodium

chloride intravenous

vancomycin 1.5 gram/500 ml in 0.9 % sodium

chloride intravenous solution

vasopressin (pitressin) infusion 40 units/

100 ml

vasopressin 40 units/50 ml (0.8 unit/ml) ssc

premade infusion

vecuronium bromide 20 mg intr avenous

solution

Table 8. Logistic Regressions for Prediction of Fluid Overload with/without Cluster 7 information

Model Logistic Regression for Fluid Overload

with APACHE II Score at 24 hours and

Diuretic Level

Logistic Regression for Fluid

Overload with APACHE II Score at

24 hours, Diuretic Level, and

Proportion of Medications Appearing

in Cluster 7

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

Estimated Value P-value Estimated Value P-value

(Intercept) -3.00 <0.0001 -3.61 <0.0001

APACHE Score at 24

hours 0.095 <0.0001 0.01 <0.0001

Diuretic level (0-5) -0.46 0.04 -0.42 0.06

Diuretic level (>5) -17.25 0.98 -17.18 0.98

Proportion of

Medications

Appearing in Cluster

5.65 0.0004

Diuretic level 0-5: the patient received

≤

5 doses of a diuretic medication within the first 72 hours of

ICU stay

Diuretic level >5: the patient received >5 doses of a diuretic medication within the first 71 hours of

ICU stay

Table 9. Logistic Regressions for Prediction of Fluid Overload Using Proportion of Medications

Appearing in Cluster 7 at Specified Time Periods

Model Logistic Regression for Fluid Overload

with APACHE II Score at 24 hours and

Diuretic Level

Estimated Value P-value

(Intercept) -3.34 <0.0001

APACHE Score at 24 hours 0.035 0.052

Diuretic level (0-5) -0.49 0.037

Diuretic level (>5) -16.75 0.98

Proportion of Medications Appearing in

Cluster 7 in Day 1 of ICU Admission 1.20 0.037

Proportion of Medications Appearing in

Cluster 7 in Day 2 of ICU Admission 0.40 0.52

Proportion of Medications Appearing in

Cluster 7 in Day 3 of ICU Admission 2.61 <0.0001

Diuretic level 0-5: the patient received

≤

5 doses of a diuretic medication within the first 72 hours of

ICU stay

Diuretic level >5: the patient received >5 doses of a diuretic medication within the first 71 hours of

ICU stay

Figure 1. Workflow for unsupervised analysis of medications for prediction of fluid overload

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

Figure 2. Venn diagrams of medication overlap within the 10 clusters by medication name & timing

Venn Diagrams Illustrating Medication Overlaps Between Clusters 1-5 and Clusters 6-

10, with Numerical

Values Indicating the Count of Shared Medication Administrations (Both medication name and time

period of administration)

Figure 3. Venn diagrams of medication overlap within the 10 clusters by medication name only

Venn Diagrams Illustrating Medication Overlaps Between Clusters 1-5 and Clusters 6-

10, with Numerical

Values Indicating the Count of Shared Medication Names

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

Figure 4. Cluster 7 medications organized by timing of medication administrations

Medication Record of Cluster 7 Distribution Over 72 Hours, with boxes indicating administration of

medication at specific time slot

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

Figure 5. Cluster 7 medications organized by frequency and timing of administration

Distribution of Medication Records for Cluster 7 Over 72 Hours. Horizontal Axis: Medication Names.

Vertical Axis: Frequency of Appearance in Time Slots

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

Figure 6. Cluster 7 medications organized by timing of administration and medication class

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

Figure 7. Cluster 7 medications organized by proportion of medications from each 3-hour time period

The Custer 7 medication administration is distributed over a span of 72 hours, divided into twenty-four

three-hour time slots. These slots are arranged clockwise, starting from the 0-

3 hour slot and ending at the

68-72 hour slot. The term "area" represents the quantity of medication detected within each respective

time slot.

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

Figure 8 Logistic regression model for Cluster 7

Logistic regression for incidence of fluid overload, including Cluster 7, APACHE II score, and diuretic

level

Specificity (%)

Sensitivity (%)

120 100 80 60 40 20 0 −20

0 20406080100

AUC: 74.1%

AUC: 71.9%

AUC: 65.4%

ROC

line 1 = LR w/ APACHE II

line 2 = LR w/ APACHE II and diuretic

line 3 = LR w/ APACHE II diuretic cluster 7

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

Figure 9. Visualization of significance of cluster 7 proportion and APACHE II score at 24 hours in

logistic regression model in predicting fluid overload.

Model1 Model2 Model3

010203001020300 102030

0.0

0.1

0.2

0.3

0.4

0.5

APACHE II Score at 24 hours

Proportion of Medications

Appearing in Cluster 7

2.5

5.0

7.5

10.0

12.5

0.2

0.4

0.6

0.8

Probability of

Fluid Overload

fluid

Fluid Overload

No Fluid Ove rload

Models In the Data Space

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

Figure 10. Distribution of patients in each group (non-fluid overload versus fluid overload) based on

proportion of individual medications that appeared within Cluster 7

0.0

0.1

0.2

0.3

0.4

0.5

−0.5 0.0 0.5 1.0 1.5

Fluid Overload Status

Proportion of Medications

Appearing in Cluster 7

fluid

Fluid Overload

No Fluid Ove rload

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

Figure 11. Marginal effect of cluster 7 proportion on fluid overload

Likelihood of an individual patient developing fluid overload, normalized to APACHE II score of 14 and

no receipt of diuretics.

25%

50%

75%

100%

0.0 0.2 0.4 0.6

Proportion of Medications

Appearing in Cluster 7

Probability of Fluid Overload

Marginal Effects Plot

Adjust for:APACHE_24h_score = 14.12 Diureticlevel = 0

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

References

1. Carr JR, Hawkins WA, Newsome AS, et al: Fluid stewardship of maintenance Intravenous

fluids. J Pharm Pract 2021:8971900211008261

2. Hawkins WA, Smith SE, Newsome AS, et al: Fluid stewardship during critical illness: a

call to action. J Pharm Pract 2020; 33(6):863-873

3. Bissell BD, Laine ME, Thompson Bastin ML, et al: Impact of protocolized diuresis for de-

resuscitation in the intensive care unit. Crit Care 2020; 24(1):70

4. Jones TW, Chase AM, Bruning R, et al: Early diuretics for de-resuscitation in septic

patients with left ventricular dysfunction. Clin Med Insights Cardiol 2022;

16:11795468221095875

5. Hawkins WA, Butler SA, Poirier N, et al: From theory to bedside: implementation of fluid

stewardship in a medical ICU pharmacy practice. Am J Health Syst Pharm 2022 Jun

7;79(12):984-992.

6. Bissell BD, Donaldson JC, Morris PE, et al: A narrative review of pharmacologic de-

resuscitation in the critically ill. J Crit Care 2020; 59:156-162

7. Messmer AS, Moser M, Zuercher P, et al: Fluid overload phenotypes in critical illness-a

machine learning approach. J Clin Med 2022; 11(2)

8. Zhang Z, Ho KM, Hong Y: Machine learning for the prediction of volume responsiveness

in patients with oliguric acute kidney injury in critical care. Crit Care 2019; 23(1):112

9. Olney WJ, Chase AM, Hannah SA, et al: Medication regimen complexity score as an

indicator of fluid balance in critically ill Patients. J Pharm Pract 2021:897190021999792

10. Sikora A, Ayyala D, Rech MA, et al: Impact of pharmacists to improve patient care in the

critically ill: a large multicenter analysis using meaningful metrics with the medication

regimen complexity-ICU (MRC-ICU) score. Crit Care Med 2022; 50(9):1318-1328

11. Newsome AS, Smith SE, Olney WJ, et al: Multicenter validation of a novel medication-

regimen complexity scoring tool. Am J Health Syst Pharm 2020; 77(6):474-478

12. Newsome AS, Anderson D, Gwynn ME, et al: Characterization of changes in medication

complexity using a modified scoring tool. Am J Health Syst Pharm 2019;

76(Supplement_4):S92-s95

13. Gwynn ME, Poisson MO, Waller JL, et al: Development and validation of a medication

regimen complexity scoring tool for critically ill patients. Am J Health Syst Pharm 2019;

76(Supplement_2):S34-s40

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

14. Al-Mamun MA, Brothers T, Newsome AS: Development of Machine Learning Models to

Validate a Medication Regimen Complexity Scoring Tool for Critically Ill Patients. Ann

Pharmacother 2021; 55(4):421-429

15. Smith SE, Shelley R, Sikora A: Medication regimen complexity vs patient acuity for

predicting critical care pharmacist interventions. Am J Health Syst Pharm 2022;

79(8):651-655

16. Webb AJ, Rowe S, Newsome AS: A descriptive report of the rapid implementation of

automated MRC-ICU calculations in the EMR of an academic medical center. Am J

Health Syst Pharm 2022; 79(12):979-983

17. Newsome AS, Smith SE, Olney WJ, et al: Medication regimen complexity is associated

with pharmacist interventions and drug-drug interactions: A use of the novel MRC-ICU

scoring tool. Journal of the American College of Clinical Pharmacy. 2020; 3(1):47-56

18. Sanchez P, Voisey JP, Xia T, et al: Causal machine learning for healthcare and precision

medicine. R Soc Open Sci 2022; 9(8):220638

19. Iwase S, Nakada TA, Shimada T, et al: Prediction algorithm for ICU mortality and length

of stay using machine learning. Sci Rep 2022; 12(1):12912

20. Beil M, Sviri S, Flaatten H, et al: On predictions in critical care: The individual

prognostication fallacy in elderly patients. J Crit Care 2021; 61:34-38

21. Lovejoy CA, Buch V, Maruthappu M: Artificial intelligence in the intensive care unit.

Crit Care 2019; 23(1):7

22. Gutierrez G: Artificial Intelligence in the Intensive Care Unit. Crit Care 2020; 24(1):101

23. Goh KH, Wang L, Yeow AYK, et al: Artificial intelligence in sepsis early prediction and

diagnosis using unstructured data in healthcare. Nat Commun 2021; 12(1):711

24. Hyland SL, Faltys M, Huser M, et al: Early prediction of circulatory failure in the

intensive care unit using machine learning. Nat Med 2020; 26(3):364-373

25. DeGrave AJ, Janizek JD, Lee SI: AI for radiographic COVID-19 detection selects

shortcuts over signal. medRxiv 2020

26. Nguyen D, Ngo B, vanSonnenberg E: AI in the Intensive Care Unit: Up-to-Date Review. J

Intensive Care Med 2021; 36(10):1115-1123

27. Yoon JH, Pinsky MR, Clermont G: Artificial Intelligence in Critical Care Medicine. Crit

Care 2022; 26(1):75

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

28. Farion KJ, Wilk S, Michalowski W, et al: Comparing predictions made by a prediction

model, clinical score, and physicians: pediatric asthma exacerbations in the emergency

department. Appl Clin Inform 2013; 4(3):376-391

29. Feng JZ, Wang Y, Peng J, et al: Comparison between logistic regression and machine

learning algorithms on survival prediction of traumatic brain injuries. J Crit Care 2019;

54:110-116

30. World Medical Association: World Medical Association Declaration of Helsinki: Ethical

principles for medical research involving human subjects. JAMA 2023: 312:2191-2194.

31. Von Elm E AD, Egger M, et al: STROBE Initiative: Strengthening the reporting of

observational studies in epidemiology (STROBE) statement: Guidelines for reporting

observational studies. BMJ 2007; 335:806-808.

32. Bouchard J, Soroko SB, Chertow GM, et al: Fluid accumulation, survival and recovery of

kidney function in critically ill patients with acute kidney injury. Kidney Int 2009;

76(4):422-427

33. Carr JR, Hawkins WA, Newsome AS, et al: Fluid Stewardship of Maintenance

Intravenous Fluids. J Pharm Pract 2022; 35(5):769-782

34. Malbrain M, Van Regenmortel N, Saugel B, et al: Principles of fluid management and

stewardship in septic shock: it is time to consider the four D's and the four phases of fluid

therapy. Ann Intensive Care 2018; 8(1):66

35. Claure-Del Granado R, Mehta RL: Fluid overload in the ICU: evaluation and management.

BMC Nephrol 2016; 17(1):109

36. O'Connor ME, Prowle JR: Fluid Overload. Crit Care Clin 2015; 31(4):803-821

37. Chen T, Guestrin C. XGBoost: A Scalable Tree Boosting System. In: Proceedings of the

22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

[Internet]. New York, NY, USA: ACM; 2016. p. 785–94. Available from:

http://doi.acm.org/10.1145/2939672.2939785

38. Cortes C, Vapnik V. Support-vector networks. Machine learning. 1995;20(3):273–97.

39. Ho TK. Random decision forests. In: Proceedings of 3rd international conference on

document analysis and recognition. 1995. p. 278–82.

40. Rubin DB: Multiple imputation for nonresponse in surveys. Hoboken, N.J. ;, Wiley-

Interscience, 2004

41. Topol EJ: Deep medicine : how artificial intelligence can make healthcare human again.

First edition. ed. New York, Basic Books,, 2019, p^pp 1 online resource

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

42. Kahneman D, Sibony O, Sunstein CR: Noise : a flaw in human judgment. First edition.

Edition. New York, Little, Brown Spark, 2021

43. D'Hondt E, Ashby TJ, Chakroun I, et al: Identifying and evaluating barriers for the

implementation of machine learning in the intensive care unit. Commun Med (Lond) 2022;

2(1):162

44. van de Sande D, van Genderen ME, Huiskens J, et al: Moving from bytes to bedside: a

systematic review on the use of artificial intelligence in the intensive care unit. Intensive

Care Med 2021; 47(7):750-760

45. Moss L, Corsar D, Shaw M, et al: Demystifying the Black Box: The Importance of

Interpretability of Predictive Models in Neurocritical Care. Neurocrit Care 2022;

37(Suppl 2):185-191

46. The Lancet Respiratory M: Opening the black box of machine learning. Lancet Respir

Med 2018; 6(11):801

47. Malbrain M, Martin G, Ostermann M: Everything you need to know about deresuscitation.

Intensive Care Med 2022; 48(12):1781-1786

48. Gelbart B, Serpa Neto A, Stephens D, et al: Fluid Accumulation in Mechanically

Ventilated, Critically Ill Children: Retrospective Cohort Study of Prevalence and Outcome.

Pediatr Crit Care Med 2022; 23(12):990-998

49. National Heart L, Blood Institute Acute Respiratory Distress Syndrome Clinical Trials N,

Wiedemann HP, et al: Comparison of two fluid-management strategies in acute lung

injury. N Engl J Med 2006; 354(24):2564-2575

50. Gamble KC, Smith SE, Bland CM, et al: Hidden Fluids in Plain Sight: Identifying

Intravenous Medication Classes as Contributors to Intensive Care Unit Fluid Intake. Hosp

Pharm 2022; 57(2):230-236

51. Branan T, Smith SE, Newsome AS, et al: Association of hidden fluid administration with

development of fluid overload reveals opportunities for targeted fluid minimization. SAGE

Open Med 2020; 8:2050312120979464

52. Mitchell KH, Carlbom D, Caldwell E, et al: Volume Overload: Prevalence, Risk Factors,

and Functional Outcome in Survivors of Septic Shock. Ann Am Thorac Soc 2015;

12(12):1837-1844

53. Ouchi A, Sakuramoto H, Hoshino H, et al: Association between fluid overload and

delirium/coma in mechanically ventilated patients. Acute Med Surg 2020; 7(1):e508

54. Murphy CV, Schramm GE, Doherty JA, et al: The importance of fluid management in

acute lung injury secondary to septic shock. Chest 2009; 136(1):102-109

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

55. Boyd JH, Forbes J, Nakada TA, et al: Fluid resuscitation in septic shock: a positive fluid

balance and elevated central venous pressure are associated with increased mortality. Crit

Care Med 2011; 39(2):259-265

56. Woodward CW, Lambert J, Ortiz-Soriano V, et al: Fluid Overload Associates With Major

Adverse Kidney Events in Critically Ill Patients With Acute Kidney Injury Requiring

Continuous Renal Replacement Therapy. Crit Care Med 2019; 47(9):e753-e760

57. Hawkins WA, Butler SA, Poirier N, et al: From theory to bedside: Implementation of fluid

stewardship in a medical ICU pharmacy practice. Am J Health Syst Pharm 2022;

79(12):984-992

58. Silversides JA, Perner A, Malbrain M: Liberal versus restrictive fluid therapy in critically

ill patients. Intensive Care Med 2019; 45(10):1440-1442

59. Goldstein S, Bagshaw S, Cecconi M, et al: Pharmacological management of fluid overload.

Br J Anaesth 2014; 113(5):756-763

60. Silversides JA, McAuley DF, Blackwood B, et al: Fluid management and deresuscitation

practices: A survey of critical care physicians. J Intensive Care Soc 2020; 21(2):111-118

61. Burkov A: The hundred-page machine learning book. Quebec City, Canada, Andriy

Burkov, 2019

62. Qin X, Zhang W, Hu X, et al: A deep learning model to identify the fluid overload status

in critically ill patients based on chest X-ray images. Pol Arch Intern Med 2023; 133(2)

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

Bibliography

1. Bouchard J, Soroko SB, Chertow GM, et al. Fluid accumulation, survival and recovery of

kidney function in critically ill patients with acute kidney injury. Kidney Int

2009;76(4):422-7. (In eng). DOI: 10.1038/ki.2009.159.

2. Carr JR, Hawkins WA, Newsome AS, et al. Fluid Stewardship of Maintenance

Intravenous Fluids. J Pharm Pract 2022;35(5):769-782. (In eng). DOI:

10.1177/08971900211008261.

3. Hawkins WA, Smith SE, Newsome AS, Carr JR, Bland CM, Branan TN. Fluid

Stewardship During Critical Illness: A Call to Action. J Pharm Pract 2020;33(6):863-873.

(In eng). DOI: 10.1177/0897190019853979.

4. Bissell BD, Donaldson JC, Morris PE, Neyra JA. A narrative review of pharmacologic

de-resuscitation in the critically ill. J Crit Care 2020;59:156-162. (In eng). DOI:

10.1016/j.jcrc.2020.07.004.

5. Bissell BD, Laine ME, Thompson Bastin ML, et al. Impact of protocolized diuresis for

de-resuscitation in the intensive care unit. Crit Care 2020;24(1):70. (In eng). DOI:

10.1186/s13054-020-2795-9.

6. Hawkins WA, Butler SA, Poirier N, Wilson CS, Long MK, Smith SE. From theory to

bedside: Implementation of fluid stewardship in a medical ICU pharmacy practice. Am J

Health Syst Pharm 2022;79(12):984-992. (In eng). DOI: 10.1093/ajhp/zxab453.

7. Jones TW, Chase AM, Bruning R, Nimmanonda N, Smith SE, Sikora A. Early Diuretics

for De-resuscitation in Septic Patients With Left Ventricular Dysfunction. Clin Med

Insights Cardiol 2022;16:11795468221095875. (In eng). DOI:

10.1177/11795468221095875.

8. Olney WJ, Chase AM, Hannah SA, Smith SE, Newsome AS. Medication Regimen

Complexity Score as an Indicator of Fluid Balance in Critically Ill Patients. J Pharm Pract

2022;35(4):573-579. (In eng). DOI: 10.1177/0897190021999792.

9. Rafiei A, Rad MG, Sikora A, Kamaleswaran R. Improving irregular temporal modeling

by integrating synthetic data to the electronic medical record using conditional GANs: a

case study of fluid overload prediction in the intensive care unit. medRxiv

2023:2023.06.20.23291680. DOI: 10.1101/2023.06.20.23291680.

10. Sikora A, Zhang T, Murphy DJ, et al. Machine learning vs. traditional regression analysis

for fluid overload prediction in the ICU. medRxiv 2023:2023.06.16.23291493. DOI:

10.1101/2023.06.16.23291493.

11. Messmer AS, Moser M, Zuercher P, Schefold JC, Müller M, Pfortmueller CA. Fluid

Overload Phenotypes in Critical Illness-A Machine Learning Approach. J Clin Med

2022;11(2) (In eng). DOI: 10.3390/jcm11020336.

12. Zhang Z, Ho KM, Hong Y. Machine learning for the prediction of volume responsiveness

in patients with oliguric acute kidney injury in critical care. Crit Care 2019;23(1):112. (In

eng). DOI: 10.1186/s13054-019-2411-z.

13. Sikora A, Devlin JW, Yu M, et al. Evaluation of medication regimen complexity as a

predictor for mortality. Sci Rep 2023;13(1):10784. DOI: 10.1038/s41598-023-37908-1.

14. Gwynn ME, Poisson MO, Waller JL, Newsome AS. Development and validation of a

medication regimen complexity scoring tool for critically ill patients. Am J Health Syst

Pharm 2019;76(Supplement_2):S34-s40. (In eng). DOI: 10.1093/ajhp/zxy054.

15. Murray B, Zhao B, Kong Y, Shen Y, Sikora A. 935: PREDICTING DURATION OF

MECHANICAL VENTILATION WITH MEDICATION REGIMEN COMPLEXITY

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

VARIABLES. Critical Care Medicine 2023;51(1):460. DOI:

10.1097/01.ccm.0000909468.03569.76.

16. Webb AJ, Rowe S, Sikora Newsome A. A descriptive report of the rapid implementation

of automated MRC-ICU calculations in the EMR of an academic medical center. Am J

Health Syst Pharm 2022. DOI: 10.1093/ajhp/zxac059.

17. Sikora A, Rafiei A, Rad MG, et al. Pharmacophenotype identification of intensive care

unit medications using unsupervised cluster analysis of the ICURx common data model.

Crit Care 2023;27(1):167. DOI: 10.1186/s13054-023-04437-2.

18. Chase A AH, Forehand C, Keats K, Taylor A, Wu S, Blotske K, Sikora A. An evaluation

of medication regimen complexity’s relationship to medication errors in critically ill

patients. Hospital Pharmacy 2023;Accepted.

19. Al-Mamun MA, Brothers T, Newsome AS. Development of Machine Learning Models to

Validate a Medication Regimen Complexity Scoring Tool for Critically Ill Patients. Ann

Pharmacother 2021;55(4):421-429. (In eng). DOI: 10.1177/1060028020959042.

20. Newsome AS, Anderson D, Gwynn ME, Waller JL. Characterization of changes in

medication complexity using a modified scoring tool. Am J Health Syst Pharm

2019;76(Supplement_4):S92-s95. (In eng). DOI: 10.1093/ajhp/zxz213.

21. Sikora A, Ayyala D, Rech MA, et al. Impact of Pharmacists to Improve Patient Care in

the Critically Ill: A Large Multicenter Analysis Using Meaningful Metrics With the

Medication Regimen Complexity-ICU (MRC-ICU) Score. Crit Care Med

2022;50(9):1318-1328. (In eng). DOI: 10.1097/ccm.0000000000005585.

22. Sikora A, Rafiei A, Rad MG, et al. Pharmacophenotype identification of intensive care

unit medications using unsupervised cluster analysis of the ICURx common data model.

Crit Care 2023;27(1):167. (In eng). DOI: 10.1186/s13054-023-04437-2.

23. Sikora A JH, Yu M, Chen X, Murray B, Kamaleswaran R. Cluster analysis driven by

unsupervised latent feature learning of

intensive care unit medications to identify novel pharmacophenotypes of critically ill patients.

Research Square 2022. DOI: https://doi.org/10.21203/rs.3.rs-1745568/v1.

24. World Medical Association Declaration of Helsinki: ethical principles for medical

research involving human subjects. Jama 2013;310(20):2191-4. (In eng). DOI:

10.1001/jama.2013.281053.

25. Elm Ev, Altman DG, Egger M, Pocock SJ, Gøtzsche PC, Vandenbroucke JP.

Strengthening the reporting of observational studies in epidemiology (STROBE)

statement: guidelines for reporting observational studies. BMJ 2007;335(7624):806-808.

DOI: 10.1136/bmj.39335.541782.AD.

26. Sikora A, Keats K, Murphy DJ, et al. A Common Data Model for the standardization of

intensive care unit (ICU) medication features in artificial intelligence (AI) applications.

medRxiv 2023:2023.09.18.23295727. DOI: 10.1101/2023.09.18.23295727.

27. Bro R, Smilde AK. Principal component analysis. Analytical Methods 2014;6(9):2812-

2831. (10.1039/C3AY41907J). DOI: 10.1039/C3AY41907J.

28. Wold S, Esbensen K, Geladi P. Principal component analysis. Chemometrics and

Intelligent Laboratory Systems 1987;2(1):37-52. DOI: https://doi.org/10.1016/0169-

7439(87)80084-9.

29. Hinton GE. A Practical Guide to Training Restricted Boltzmann Machines. In: Montavon

G, Orr GB, Müller K-R, eds. Neural Networks: Tricks of the Trade: Second Edition.

Berlin, Heidelberg: Springer Berlin Heidelberg; 2012:599-619.

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

30. Zhang N, Ding S, Zhang J, Xue Y. An overview on Restricted Boltzmann Machines.

Neurocomputing 2018;275:1186-1199. DOI:

https://doi.org/10.1016/j.neucom.2017.09.065.

31. Deng S. Syuand/unsupervisedfoprediction-: A time-dependent, unsupervised machine

learning (ML) analysis was conducted to determine patterns of IV medication use

associated with fo. GitHub. (https://github.com/SyuanD/UnsupervisedFOPrediction-.git).

32. Rafiei A, Rad MG, Sikora A, Kamaleswaran R. Improving irregular temporal modeling

by integrating synthetic data to the electronic medical record using conditional GANs: a

case study of fluid overload prediction in the intensive care unit. medRxiv 2023. DOI:

10.1101/2023.06.20.23291680.

33. Sikora A, Zhang T, Murphy DJ, et al. Machine learning vs. traditional regression analysis

for fluid overload prediction in the ICU. medRxiv 2023:2023.06.16.23291493. DOI:

10.1101/2023.06.16.23291493.

34. Olney WJ, Chase AM, Hannah SA, Smith SE, Newsome AS. Medication Regimen

Complexity Score as an Indicator of Fluid Balance in Critically Ill Patients. J Pharm Pract

2021:897190021999792. DOI: 10.1177/0897190021999792.

35. Sikora A, Zhao B, Kong Y, Murray B, Shen Y. Machine learning based prediction of

prolonged duration of mechanical ventilation incorporating medication data. medRxiv

2023. DOI: 10.1101/2023.09.18.23295724.

36. Sikora A, Keats K, Murphy DJ, et al. A Common Data Model for the standardization of

intensive care unit (ICU) medication features in artificial intelligence (AI) applications.

medRxiv 2023:2023.09.18.23295727. DOI: 10.1101/2023.09.18.23295727.

37. Goh KH, Wang L, Yeow AYK, et al. Artificial intelligence in sepsis early prediction and

diagnosis using unstructured data in healthcare. Nat Commun 2021;12(1):711. (In eng).

DOI: 10.1038/s41467-021-20910-4.

38. Gutierrez G. Artificial Intelligence in the Intensive Care Unit. Crit Care 2020;24(1):101.

(In eng). DOI: 10.1186/s13054-020-2785-y.

39. Hyland SL, Faltys M, Hüser M, et al. Early prediction of circulatory failure in the

intensive care unit using machine learning. Nat Med 2020;26(3):364-373. (In eng). DOI:

10.1038/s41591-020-0789-4.

40. Iwase S, Nakada TA, Shimada T, et al. Prediction algorithm for ICU mortality and length

of stay using machine learning. Sci Rep 2022;12(1):12912. (In eng). DOI:

10.1038/s41598-022-17091-5.

41. Beil M, Sviri S, Flaatten H, et al. On predictions in critical care: The individual

prognostication fallacy in elderly patients. J Crit Care 2021;61:34-38. (In eng). DOI:

10.1016/j.jcrc.2020.10.006.

42. Lovejoy CA, Buch V, Maruthappu M. Artificial intelligence in the intensive care unit.

Crit Care 2019;23(1):7. (In eng). DOI: 10.1186/s13054-018-2301-9.

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

Supplemental Digital Information

Table

Composition of ten medication clusters identified with Restricted Boltzmann

Machine

Cluster

(N=498)

(N=561)

(N=532)

(N=517)

(N=539)

(N=574)

(N=540)

(N=518)

(N=526)

(N=532)

famotidine

10 mg/ml

injection

solution

(multi-vial

size)

morphin

e 2

mg/ml

injection

wrapper

phenylephr

ine 20

mg/250 ml

(80

mcg/ml) in

0.9 %

sodium

chloride iv

dextrose

10 % in

water

(d10w)

intravenou

s solution

lactated

ringers

irrigation

solution

dopamine

400

mg/250 ml

(1,600

mcg/ml) in

5 %

dextrose

intravenou

s solution

dobutamin

e 250

mg/250 ml

(1 mg/ml)

in 5 %

dextrose

intravenou

insulin u

100 regular

human 100

unit/ml

injection

solution

piperacillin

tazobactam

2.25

gram/50

ml in

dextrose(is

o) iv

piggyback

dopamine

400

mg/250 ml

(1,600

mcg/ml) in

5 %

dextrose

intravenou

s solution

phenylephr

ine 20

mg/250 ml

(80

mcg/ml) in

0.9 %

sodium

chloride iv

metroni

dazole

500

mg/100

ml-

sodium

chloride

(iso)

intraven

ous

piggyba

heparin

(porcine)

10,000

unit/1,000

ml in

0.9 % sod.

chloride iv

solution

famotidine

10 mg/ml

injection

solution

(multi-vial

size)

dopamine

400

mg/250 ml

(1,600

mcg/ml) in

5 %

dextrose

intravenou

s solution

dobutamin

e 250

mg/250 ml

(1 mg/ml)

in 5 %

dextrose

intravenou

dexmedeto

midine 400

mcg/100

ml (4

mcg/ml) in

0.9 %

sodium

chloride iv

sodium

chloride

0.9 %

intravenou

s solution

hepar

(porcine)

10,000

unit/1,000

ml in

0.9 % sod.

chloride iv

solution

metronidaz

ole 500

mg/100

ml-sodium

chloride(is

intravenou

piggyback

heparin

(porcine)

10,000

unit/1,000

ml in

0.9 % sod.

chloride iv

solution

dobutam

ine 250

mg/250

ml (1

mg/ml)

in 5 %

dextrose

intraven

ous

fentan yl

(pf) 10

mcg/ml in

0.9 %

sodium

chloride

intravenou

s wrapper

heparin

(porcine)

100

unit/ml

load from

infusion

fentan yl

(pf) 10

mcg/ml in

0.9 %

sodium

chloride

intravenou

s wrapper

sodium

chloride

0.45 %

intravenou

s solution

heparin

(porcine)

1,000

unit/ml

injection

solution

fentan yl

(pf) 50

mcg/ml

injection

solution

levofloxaci

n 750

mg/150 ml

in 5 %

dextrose

intravenou

piggyback

famotidine

10 mg/ml

injection

solution

(multi-vial

size)

cefepime 2

gram/100

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

heparin

(porcine

) 10,000

unit/1,00

0 ml in

0.9 %

sod.

chloride

solution

sodium

chloride

0.9 %

intravenou

s solution

sodium

chloride

0.45 %

intravenou

s solution

morphine 1

mg/ml in

dextrose

5 %

intravenou

s solution

fentany

(pf) 10

mcg/ml in

0.9 %

sodium

chloride

intravenou

s wrapper

clevidipine

25 mg/50

intravenou

s emulsion

propofol

infusion 10

mg/ml

cefazolin 2

gram/100

ml in

dextrose(is

o-osmotic)

intravenou

piggyback

dexmedeto

midine 400

mcg/100

ml (4

mcg/ml) in

0.9 %

sodium

chloride iv

propofol

infusion 10

mg/ml

levoflox

acin 750

mg/150

ml in

5 %

dextrose

intraven

ous

piggyba

morphine 1

mg/ml in

dextrose

5 %

intravenou

s solution

piperacillin

tazobactam

2.25

gram/50

ml in

dextrose(is

o) iv

piggyback

hydromorp

hone 2

mg/ml

injection

syringe

levofloxaci

n 750

mg/150 ml

in 5 %

dextrose

intravenou

piggyback

hydromorp

hone 2

mg/ml

injection

syringe

amiodaron

e 450

mg/250 ml

(1.8

mg/ml) in

dextrose

5 %

intravenou

s solution

lorazepam

2 mg/ml

injection

syringe

piperacillin

tazobactam

2.25

gram/50

ml in

dextrose(is

o) iv

piggyback

midazolam

(pf) 1

mg/ml in

0.9 %

sodium

chloride

intravenou

s solution

hydrom

orphon e

2 mg/ml

injection

syringe

clevidipine

25 mg/50

intravenou

s emulsion

insulin u

100 regular

human 100

unit/ml

injection

solution

midazolam

(pf) 1

mg/ml in

0.9 %

sodium

chloride

intravenou

s solution

propofol

infusion 10

mg/ml

fentan yl

(pf) 10

mcg/ml in

0.9 %

sodium

chloride

intravenou

s wrapper

phenylephr

ine 20

mg/250 ml

(80

mcg/ml) in

0.9 %

sodium

chloride iv

cefaz

olin 2

gram/50

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

fentan yl

(pf) 10

mcg/ml in

0.9 %

sodium

chloride

intravenou

s wrapper

vancomyci

n 2

gram/500

ml in

0.9 %

sodium

chloride

vancom

ycin 2

gram/50

0 ml in

0.9 %

sodium

chloride

amiodaron

e 450

mg/250 ml

(1.8

mg/ml) in

dextrose

5 %

dextrose

5 % and

lactated

ringers

intravenou

s solution

clevidipine

25 mg/50

intravenou

s emulsion

clevidipine

25 mg/50

intravenou

s emulsion

lactated

ringers

intravenou

s solution

dobutamin

e 1,000

mg/250

ml(4,000

mcg/ml) in

5 %

dextrose iv

vasopressi

n 40

units/50 ml

(0.8

unit/ml) in

ns infusion

sodium

chloride

0.9 %

intravenou

s solution

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

intravenou

intrav

ous

intravenou

s solution

midazolam

(pf) 1

mg/ml

injection

solution

clevidipi

ne 25

mg/50

intraven

ous

emulsio

vancomyci

n 2

gram/500

ml in

0.9 %

sodium

chloride

intravenou

dobutamin

e 250

mg/250 ml

(1 mg/ml)

in 5 %

dextrose

intravenou

vasopressi

n 40

units/50 ml

(0.8

unit/ml) in

ns infusion

cefazolin 2

gram/100

ml in

dextrose(is

o-osmotic)

intravenou

piggyback

propofol

10 mg/ml

intravenou

s emulsion

clevidipine

25 mg/50

intravenou

s emulsion

fentan yl

(pf) 10

mcg/ml in

0.9 %

sodium

chloride

intravenou

s wrapper

hydromorp

hone 50

mg/50 ml

(1 mg/ml)

in 0.9 %

sod.chlorid

e iv pump

resevoir

sodium

chloride

0.9 %

intravenou

s solution

fentan yl

(pf) 10

mcg/ml

in 0.9 %

sodium

chloride

intraven

ous

wrapper

cefazolin 2

gram/50

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

heparin

(porcine)

1,000

unit/ml

injection

solution

fat

emulsion

20 %

intravenou

midazolam

(pf) 1

mg/ml in

0.9 %

sodium

chloride

intravenou

s solution

heparin

(porcine)

10,000

unit/1,000

ml in

0.9 % sod.

chloride iv

solution

clindamyci

n 600

mg/50 ml

in 5 %

dextrose

intravenou

piggyback

phenylephr

ine 20

mg/250 ml

(80

mcg/ml) in

0.9 %

sodium

chloride iv

heparin

(porcine)

1,000

unit/ml

injection

solution

morphine

1 mg/ml in

dextrose

5 %

intravenou

s solution

fat

emulsio

n 20 %

intraven

ous

morphine

10 mg/ml

injection

solution

fentan yl

(pf) 50

mcg/ml

injection

solution

lactated

ringers

intravenou

s solution

norepineph

rine

bitartrate 8

mg/250 ml

(32

mcg/ml) in

0.9 % nacl

phenobarbi

tal sodium

65 mg/ml

injection

solution

morphine 2

mg/ml

intravenou

s cartridge

propofol

10 mg/ml

intravenou

s emulsion

cefazolin 2

gram/100

ml in

dextrose(is

o-osmotic)

intravenou

piggyback

eptifibatide

0.75

mg/ml

intravenou

s solution

phenyle

phrine

mg/250

ml (80

mcg/ml)

in 0.9 %

sodium

chloride

fat

emulsion

20 %

intravenou

amiodaron

e 450

mg/250 ml

(1.8

mg/ml) in

dextrose

5 %

intravenou

s solution

heparin

(porcine)

10,000

unit/1,000

ml in

0.9 % sod.

chloride iv

solution

vasopressi

n 40

units/50 ml

(0.8

unit/ml) in

ns infusion

diazepam 5

mg/ml

injection

syringe

midazolam

(pf) 1

mg/ml

injection

solution

pantoprazo

le 40 mg

intravenou

s solution

hydromorp

hone 2

mg/ml

injection

syringe

morphine

2 mg/ml

intravenou

s cartridge

clindam

ycin 600

mg/50

ml in

5 %

dextrose

intraven

ous

piggyba

morphine 2

mg/ml

intravenou

s cartridge

midazolam

(pf) 1

mg/ml in

0.9 %

sodium

chloride

intravenou

s solution

morphine 4

mg/ml

intravenou

s cartridge

fat

emulsion

20 %

intravenou

morphine 4

mg/ml

intravenou

s cartridge

cefepime 1

gram

solution

for

injection

clindamyci

n 600

mg/50 ml

in 5 %

dextrose

intravenou

piggyback

midazolam

(pf) 1

mg/ml in

0.9 %

sodium

chloride

intravenou

s solution

propofol

10 mg/ml

intravenou

s emulsion

phenoba

rbital

sodium

mg/ml

injection

solution

pantoprazo

le 40 mg

intravenou

s solution

norepineph

rine

bitartrate 8

mg/250 ml

(32

mcg/ml) in

0.9 % nacl

fluconazol

e 200

mg/100 ml

in sod.

chloride

(iso)

intravenou

piggyback

dobutamin

e 1,000

mg/250

ml(4,000

mcg/ml) in

5 %

dextrose iv

levofloxaci

n 500

mg/100 ml

in 5 %

dextrose

intravenou

piggyback

propofol

10 mg/ml

intravenou

s emulsion

phenobarbi

tal sodium

65 mg/ml

injection

solution

vasopressi

n 40

units/50 ml

(0.8

unit/ml) in

ns infusion

morphine

1 mg/ml in

0.9 %

sodium

chloride

injectable

pump

reservoir

morphin

e 4

mg/ml

intraven

ous

cartridge

morphine 4

mg/ml

intravenou

s cartridge

clevidipine

25 mg/50

intravenou

s emulsion

hepar

(porcine)

10,000

unit/ml

injection

solution

pantoprazo

le 40 mg

intravenou

s solution

heparin

(porcine)

10,000

unit/ml

injection

solution

vasopressi

(pitressin)

infusion 50

unit/50 ml

midazolam

5 mg/ml

(combined

) injection

solution

wrapper

fat

emulsion

20 %

intravenou

heparin

(porcine)

10,000

unit/1,000

ml in ns

(unch

cupid)

midazol

am 5

mg/ml

(combin

ed)

injection

solution

wrapper

lactated

ringers

intravenou

s solution

propofol

10 mg/ml

intravenou

s emulsion

morphine 1

mg/ml in

0.9 %

sodium

chloride

injectable

pump

reservoir

morphine 4

mg/ml

intravenou

s cartridge

morphine 2

mg/ml

intravenou

s cartridge

morphine 4

mg/ml

intravenou

s cartridge

dopamine

400

mg/250 ml

(1,600

mcg/ml) in

5 %

dextrose

intravenou

s solution

clindamyci

n 600

mg/50 ml

in 5 %

dextrose

intravenou

piggyback

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

insulin u

100

regular

human 100

unit/ml

injection

solution

eptifibat

ide 0.75

mg/ml

intraven

ous

solution

phenobarbi

tal sodium

65 mg/ml

injection

solution

heparin

(porcine)

10,000

unit/1,000

ml in

0.9 % sod.

chloride iv

solution

midazolam

(pf) 1

mg/ml

injection

solution

fluconazol

e 200

mg/100 ml

in sod.

chloride

(iso)

intravenou

piggyback

midazolam

(pf) 1

mg/ml

injection

solution

dextrose

5 % and

0.45 %

sodium

chloride

intravenou

s solution

dobutamin

e 1,000

mg/250

ml(4,000

mcg/ml) in

5 %

dextrose iv

clevidipine

25 mg/50

intravenou

s emulsion

dextrose

5 % and

0.45 %

sodium

chloride

intravenou

s solution

morphin

e 2

mg/ml

intraven

ous

cartridge

midazolam

(pf) 1

mg/ml

injection

solution

morphine 4

mg/ml

intravenou

s cartridge

cefepime 1

gram

solution

for

injection

sodium

chloride

0.9 %

intravenou

s solution

dobutamin

e 1,000

mg/250

ml(4,000

mcg/ml) in

5 %

dextrose iv

linezolid in

dextrose in

water 600

mg/300 ml

intravenou

piggyback

morphine 4

mg/ml

intravenou

s cartridge

midaz

olam

(pf) 1

mg/ml

injection

solution

piperacillin

tazobactam

3.375

gm/50ml

dextrose

(extended

duration)

dexmed

etomidin

e 400

mcg/100

ml (4

mcg/ml)

in 0.9 %

sodium

chloride

dextrose

5 % and

0.45 %

nacl iv

bolus

midazolam

(pf) 1

mg/ml

injection

solution

propofol

10 mg/ml

intravenou

s emulsion

morphine 1

mg/ml in

dextrose

5 %

intravenou

s solution

morphine 1

mg/ml in

dextrose

5 %

intravenou

s solution

lidocaine

(pf) 4

mg/ml

(0.4 %) in

5 %

dextrose

intravenou

s solution

mannitol

20 %

intravenou

s solution

linezolid in

dextrose in

water 600

mg/300 ml

intravenou

piggyback

lidocaine

(pf) 4

mg/ml

(0.4 %) in

5 %

dextrose

intravenou

s solution

piperacil

lin-

tazobact

am 2.25

gram/50

ml in

dextrose

(iso) iv

piggyba

heparin

(porcine)

10,000

unit/ml

injection

solution

linezolid in

dextrose in

water 600

mg/300 ml

intravenou

piggyback

dobutamin

e 1,000

mg/250

ml(4,000

mcg/ml) in

5 %

dextrose iv

morphine 2

mg/ml

intravenou

s cartridge

norepineph

rine

bitartrate 8

mg/250 ml

(32

mcg/ml) in

0.9 % nacl

dopamine

800

mg/500 ml

(1,600

mcg/ml) in

5 %

dextrose

intravenou

s solution

insulin u

100 regular

human 100

unit/ml

injection

solution

morphine 4

mg/ml

intravenou

s cartridge

clindamyci

n 600

mg/50 ml

in 5 %

dextrose

intravenou

piggyback

morphin

e 1

mg/ml

dextrose

5 %

intraven

ous

solution

cefepime 1

gram

solution

for

injection

meperidine

(pf) 25

mg/ml

injection

syringe

norepineph

rine

bitartrate 8

mg/250 ml

(32

mcg/ml) in

0.9 % nacl

midazolam

(pf) 1

mg/ml

injection

solution

mannitol

20 %

intravenou

s solution

famotidine

(pf) 20

mg/2 ml

intravenou

s solution

dextrose

5 % and

0.45 %

sodium

chloride

intravenou

s solution

levofloxaci

n 500

mg/100 ml

in 5 %

dextrose

intravenou

piggyback

heparin

(porcine)

for crrt

25,000

unit/250

ml in

0.45 %

sodium

chloride iv

solution

heparin

(porcine

) 10,000

unit/1,00

0 ml in

ns (unch

cupid)

propofol

10 mg/ml

intravenou

s emulsion

vasopressi

(pitressin)

infusion 50

unit/50 ml

levofloxaci

n 500

mg/100 ml

in 5 %

dextrose

intravenou

piggyback

cefepime 1

gram

solution

for

injection

morphine

10 mg/ml

injection

solution

nitroglycer

in 100

mg/250 ml

(400

mcg/ml) in

5 %

dextrose

intravenou

piperacillin

tazobactam

4.5

gram/100

dextrose(is

o-osmotic)

piggyback

meperidine

(pf) 25

mg/ml

injection

syringe

vecuroniu

m bromide

10 mg

intravenou

s solution

morphin

e 10

mg/ml

injection

solution

dobutamin

e 1,000

mg/250

ml(4,000

mcg/ml) in

5 %

dextrose iv

dobutamin

e 1,000

mg/250

ml(4,000

mcg/ml) in

5 %

dextrose iv

piperacillin

tazobactam

3.375

gram/50

dextrose(is

o-os) iv

piggyback

meperidine

(pf) 25

mg/ml

injection

syringe

piperacillin

tazobactam

3.375

gm/50ml

dextrose

(extended

duration)

fluconazol

e 200

mg/100 ml

in sod.

chloride

(iso)

intravenou

piggyback

piperacillin

tazobactam

3.375

gm/50ml

dextrose

(extended

duration)

vasopressi

(pitressin)

infusion 50

unit/50 ml

lactated

ringers

intravenou

s solution

dextrose

5 % and

lactated

ringers

intraven

ous

solution

sodium

chloride

3 %

intravenou

s injection

solution

fat

emulsion

20 %

intravenou

linezolid in

dextrose in

water 600

mg/300 ml

intravenou

piggyback

propofol

10 mg/ml

intravenou

s emulsion

linezolid in

dextrose in

water 600

mg/300 ml

intravenou

piggyback

fat

emulsion

20 %

intravenou

piperacillin

tazobactam

3.375

gram/50

dextrose(is

o-os) iv

piggyback

dobutamin

e 1,000

mg/250

ml(4,000

mcg/ml) in

5 %

dextrose iv

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

amiodaron

e 150

mg/100 ml

(1.5

mg/ml) in

dextrose,

iso-

osmotic iv

lactated

ringers

iv bolus

dextrose

5 % in

water

(d5w)

intravenou

s solution

phenobarbi

tal sodium

65 mg/ml

injection

solution

esmolol

2,500

mg/250 ml

(10 mg/ml)

in sodium

chloride

(iso-

osmotic) iv

heparin,

porcine

(pf) 10

unit/ml

intravenou

s syringe

fat

emulsion

20 %

intravenou

dobutamin

e 250

mg/250 ml

(1 mg/ml)

in 5 %

dextrose

intravenou

dextrose

5 % and

lactated

ringers

intravenou

s solution

heparin,

porcine

(pf) 10

unit/ml

intravenou

s syringe

lorazepam

2 mg/ml

injection

syringe

nitrogly

cerin 50

mg/250

ml (200

mcg/ml)

in 5 %

dextrose

intraven

ous

insulin u

100 regular

human 100

unit/ml

injection

solution

heparin,

porcine

(pf) 10

unit/ml

intravenou

s syringe

clindamyci

n 600

mg/50 ml

in 5 %

dextrose

intravenou

piggyback

piperacillin

tazobactam

2.25

gram/50

ml in

dextrose(is

o) iv

piggyback

dextrose

5 % and

lactated

ringers

intravenou

s solution

fentan yl

(pf) 2,500

mcg/50 ml

(50

mcg/ml)

intravenou

s pca

syringe

dopamine

800

mg/500 ml

(1,600

mcg/ml) in

5 %

dextrose

intravenou

s solution

norepineph

rine

bitartrate 8

mg/250 ml

(32

mcg/ml) in

0.9 % nacl

morphine

4 mg/ml

intravenou

s cartridge

lactated

ringers

intraven

ous

solution

levofloxaci

n 500

mg/100 ml

in 5 %

dextrose

intravenou

piggyback

sodium

chloride

3 %

intravenou

s injection

solution

nitroglycer

in 50

mg/250 ml

(200

mcg/ml) in

5 %

dextrose

intravenou

heparin

(porcine)

10,000

unit/1,000

ml in ns

(unch

cupid)

midazolam

1 mg/ml

injection

solution

vecuroniu

m bromide

10 mg

intravenou

s solution

famotidine

(pf) 20

mg/2 ml

intravenou

s solution

rocuroniu

m 10

mg/ml

intravenou

s solution

vasopressi

n 40

units/50 ml

(0.8

unit/ml)

ssc

premade

infusion

hydrom

orphon e

mg/50

ml (1

mg/ml)

in 0.9 %

sod.chlo

ride iv

pump

resevoir

linezolid in

dextrose in

water 600

mg/300 ml

intravenou

piggyback

dextrose

5 % in

water

(d5w)

intravenou

s solution

sodium

chloride

3 %

intravenou

s injection

solution

mannitol

20 %

intravenou

s solution

meperidine

(pf) 25

mg/ml

injection

syringe

diazepam 5

mg/ml

injection

syringe

lactated

ringers iv

bolus

dextrose

5 % in

water

(d5w)

intravenou

s solution

midazolam

1 mg/ml

injection

solution

digoxin

250

mcg/ml

(0.25

mg/ml)

injection

solution

clindamyci

n 900

mg/50 ml

in 5 %

dextrose

intravenou

piggyback

piperacillin

tazobactam

3.375

gm/50ml

dextrose

(extended

duration)

hydromorp

hone 50

mg/50 ml

(1 mg/ml)

in 0.9 %

sod.chlorid

e iv pump

resevoir

lidocaine

(pf) 4

mg/ml

(0.4 %) in

5 %

dextrose

intravenou

s solution

albumin,

human 5 %

intravenou

s solution

nitroglycer

in 50

mg/250 ml

(200

mcg/ml) in

5 %

dextrose

intravenou

lactated

ringers

intravenou

s solution

morphine

10 mg/ml

injection

solution

diazepam

5 mg/ml

injection

syringe

heparin

(porcine

) for crrt

25,000

unit/250

ml in

0.45 %

sodium

chloride

solution

diazepam 5

mg/ml

injection

syringe

clindamyci

n 900

mg/50 ml

in 5 %

dextrose

intravenou

piggyback

meperidine

(pf) 25

mg/ml

injection

syringe

clindamyci

n 900

mg/50 ml

in 5 %

dextrose

intravenou

piggyback

heparin,

porcine

(pf) 10

unit/ml

intravenou

s syringe

heparin

(porcine)

for crrt

25,000

unit/250

ml in

0.45 %

sodium

chloride iv

solution

digoxin

250

mcg/ml

(0.25

mg/ml)

injection

solution

dextrose

5 % and

0.45 %

sodium

chloride

intravenou

s solution

fentan yl

(pf) 10

mcg/ml in

0.9 %

sodium

chloride

intravenou

s wrapper

insulin

u-100

regular

human

100

unit/ml

injection

solution

dextrose

5 % and

0.9 %

sodium

chloride

intravenou

s solution

dopamine

800

mg/500 ml

(1,600

mcg/ml) in

5 %

dextrose

intravenou

s solution

heparin,

porcine

(pf) 10

unit/ml

intravenou

s syringe

clindamyci

n 600

mg/50 ml

in 5 %

dextrose

intravenou

piggyback

cefazolin 1

gram/50

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

heparin

(porcine)

100

unit/ml

bolus from

infusion

heparin

(porcine)

for crrt

25,000

unit/250

ml in

0.45 %

sodium

chloride iv

solution

lidocaine

(pf) 4

mg/ml

(0.4 %) in

5 %

dextrose

intravenou

s solution

cefazolin 1

gram/50

ml in

dextrose

(iso-

osmotic)

intravenou

fentan yl

(pf)

2,500

mcg/50

ml (50

mcg/ml)

intraven

heparin

(porcine)

for crrt

25,000

unit/250

ml in

0.45 %

famotidine

(pf) 20

mg/2 ml

intravenou

s solution

lorazepam

2 mg/ml

injection

syringe

famotidine

(pf) 20

mg/2 ml

intravenou

s solution

heparin

(porcine)

for crrt

25,000

unit/250

ml in

0.45 %

morphine 1

mg/ml in

0.9 %

sodium

chloride

injectable

pump

amiodaron

e 150

mg/100 ml

(1.5

mg/ml) in

dextrose,

iso-

clindamyci

n 900

mg/50 ml

in 5 %

dextrose

intravenou

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

piggyback

ous pca

syringe

sodium

chloride iv

solution

sodium

chloride iv

solution

reservoir

osmotic

piggyback

nitroglycer

in 100

mg/250 ml

(400

mcg/ml) in

5 %

dextrose

intravenou

rocuroni

um 10

mg/ml

intraven

ous

solution

lactated

ringers iv

bolus

diazepam 5

mg/ml

injection

syringe

vancomyci

n 1.25

gram/250

ml in

0.9 %

sodium

chloride

intravenou

heparin

(porcine)

for crrt

25,000

unit/250

ml in

0.45 %

sodium

chloride iv

solution

fentan yl

(pf) 2,500

mcg/50 ml

(50

mcg/ml)

intravenou

s pca

syringe

piperacillin

tazobactam

3.375

gm/50ml

dextrose

(extended

duration)

vasopressi

n 40

units/50 ml

(0.8

unit/ml)

ssc

premade

infusion

heparin

(porcine)

10,000

unit/ml

injection

solution

heparin

(porcine)

1,000

unit/ml

injection

solution

midazol

am 1

mg/ml

in 0.9 %

sodium

chloride

intraven

ous

cefazolin 1

gram/50

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

heparin

(porcine)

for crrt

25,000

unit/250

ml in

0.45 %

sodium

chloride iv

solution

vasopressi

n 40

units/50 ml

(0.8

unit/ml)

ssc

premade

infusion

dextrose

5 % and

lactated

ringers

intravenou

s solution

lorazepam

2 mg/ml

injection

syringe

vancomyci

n 1.5

gram/500

ml in

0.9 %

sodium

chloride

intravenou

s solution

fentan yl

(pf) 2,500

mcg/50 ml

(50

mcg/ml)

intravenou

s pca

syringe

dopamine

800

mg/500 ml

(1,600

mcg/ml) in

5 %

dextrose

intravenou

s solution

dexmedeto

midine 200

mcg/50 ml

(4 mcg/ml)

in 0.9 %

sodium

chloride iv

vasopres

sin

(pitressi

infusion

unit/50

amiodaron

e 150

mg/100 ml

(1.5

mg/ml) in

dextrose,

iso-

osmotic iv

heparin

(porcine)

100

unit/ml

bolus from

infusion

pentobarbit

2500mg/50

ml adult

infusion

diazepam 5

mg/ml

injection

syringe

vancomyci

n 1

gram/200

ml in

dextrose

5 %

intravenou

piggyback

morphine 1

mg/ml in

dextrose

5 %

intravenou

s solution

diazepam 5

mg/ml

injection

syringe

famotidine

(pf) 20

mg/2 ml

intravenou

s solution

dextrose

5 % and

0.9 %

sodium

chloride

intravenou

s solution

albumin,

human

25 %

intraven

ous

solution

fentan yl

(pf) 2,500

mcg/50 ml

(50

mcg/ml)

intravenou

s pca

syringe

lactated

ringers iv

bolus

sodium

chloride

0.45 %

intravenou

s solution

dextrose

5 % and

0.9 %

sodium

chloride

intravenou

s solution

octreotide

acetate 100

mcg/ml

injection

solution

lorazepam

2 mg/ml

injection

syringe

vancomyci

n 1

gram/200

ml in

dextrose

5 %

intravenou

piggyback

lactated

ringers iv

bolus

dobutamin

e 250

mg/250 ml

(1 mg/ml)

in 5 %

dextrose

intravenou

vancom

ycin 1

gram/20

0 ml in

dextrose

5 %

intraven

ous

piggyba

lorazepam

2 mg/ml

injection

syringe

lorazepam

2 mg/ml

injection

syringe

heparin

(porcine)

1,000

unit/ml

injection

solution

midazol

1 mg/ml

injection

solution

sodium

chloride

0.9 %

intravenou

s solution

cefazolin 1

gram/50

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

pentobarbit

2500mg/50

ml adult

infusion

heparin

(porcine)

for crrt

25,000

unit/250

ml in

0.45 %

sodium

chloride iv

solution

sodium

chloride 4

mEq/ml

intravenou

s solution

cefepim

e 2

gram/10

0 ml in

dextrose

(iso-

osmotic)

intraven

ous

piggyba

vasopressi

n 40

units/50 ml

(0.8

unit/ml)

ssc

premade

infusion

fentan yl

(pf) 2,500

mcg/50 ml

(50

mcg/ml)

intravenou

s pca

syringe

phenylephr

ine 20

mg/250 ml

(80

mcg/ml) in

0.9 %

sodium

chloride iv

phenylephr

ine 20

mg/250 ml

(80

mcg/ml) in

0.9 %

sodium

chloride iv

dexmedeto

midine 200

mcg/50 ml

(4 mcg/ml)

in 0.9 %

sodium

chloride iv

vancomyci

n 1.25

gram/250

ml in

0.9 %

sodium

chloride

intravenou

sodium

chloride

0.45 %

intravenou

s solution

nitroglycer

in 50

mg/250 ml

(200

mcg/ml) in

5 %

dextrose

intravenou

heparin

30,000

units (cell

saver) in

1000 ml ns

norepine

phrine

bitartrat

e 8

mg/250

ml (32

mcg/ml)

in 0.9 %

nacl iv

heparin

(porcine)

1,000

unit/ml

injection

solution

midazolam

1 mg/ml

injection

solution

midazolam

1 mg/ml

injection

solution

heparin

(porcine)

100

unit/ml

bolus from

infusion

amiodaron

e 360

mg/200 ml

(1.8

mg/ml) in

dextrose,

iso-

osmotic iv

amiodaron

e 150

mg/100 ml

(1.5

mg/ml) in

dextrose,

iso-

osmotic iv

heparin

(porcine)

1,000

unit/ml

injection

solution

morphine 1

mg/ml in

0.9 %

sodium

chloride

injectable

pump

reservoir

norepineph

rine

bitartrate 8

lorazepa

m 2

mg/ml

amiodaron

e 360

mg/200 ml

midazolam

1 mg/ml in

0.9 %

morphine 2

mg/ml

injection pf

morphine 1

mg/ml in

0.9 %

mannitol

25 %

intravenou

midazolam

1 mg/ml in

0.9 %

vasopressi

(pitressin)

albumin,

human 5 %

intravenou

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

mg/250 ml

(32

mcg/ml) in

0.9 % nacl

injection

wrapper

(1.8

mg/ml) in

dextrose,

iso-

osmotic iv

sodium

chloride

intravenou

wrapper

sodium

chloride

injectable

pump

reservoir

s solution

sodium

chloride

intravenou

infusion 40

units/100

s solution

epinephrin

e hcl 8

mg/250 ml

(32

mcg/ml) in

5 %

dextrose

intravenou

propofol

infusion

mg/ml

sodium

chloride

0.45 %

intravenou

s solution

fentan yl

(pf) 10

mcg/ml in

0.9 %

sodium

chloride

intravenou

s wrapper

vasopressi

(pitressin)

infusion 50

unit/50 ml

actated

ringers

intravenou

s solution

hydromorp

hone 1

mg/ml in

ns infusion

wrapper

fentan yl

(pf) 10

mcg/ml in

0.9 %

sodium

chloride

intravenou

s wrapper

amiodaron

e 450

mg/250 ml

(1.8

mg/ml) in

dextrose

5 %

intravenou

s solution

heparin

(porcine)

100

unit/ml

bolus from

infusion

clevidipine

25 mg/50

intravenou

s emulsion

heparin

(porcine

) 1,000

unit/ml

injection

solution

lorazepam

2 mg/ml

injection

wrapper

cefazolin 1

gram/50

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

heparin

30,000

units (cell

saver) in

1000 ml ns

cefazolin 1

gram/50

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

propofol

infusion 10

mg/ml

vasopressi

n 40

units/50 ml

(0.8

unit/ml)

ssc

premade

infusion

vasopressi

(pitressin)

infusion 50

unit/50 ml

piperacillin

tazobactam

3.375

gm/50ml

dextrose

(extended

duration)

famotidine

(pf) 20

mg/2 ml

intravenou

s solution

dextrose

10 % iv

bolus

dextrose

5 % and

lactated

ringers

intravenou

s solution

octreotide

acetate 100

mcg/ml

injection

solution

dextrose

10 % iv

bolus

insulin u

100 regular

human 100

unit/ml

injection

solution

dextrose

5 % in

water

(d5w)

intravenou

s solution

vasopressi

(pitressin)

infusion 40

units/100

cefepime 2

gram/100

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

lactated

ringers

intravenou

s solution

sodium

chloride

0.45 %

intravenou

s solution

midazol

am (pf)

1 mg/ml

injection

solution

ceftriaxone

2 gram/50

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

epinephrin

e hcl 8

mg/250 ml

(32

mcg/ml) in

5 %

dextrose

intravenou

heparin

(porcine)

for crrt

25,000

unit/250

ml in

0.45 %

sodium

chloride iv

solution

dopamine

800

mg/500 ml

(1,600

mcg/ml) in

5 %

dextrose

intravenou

s solution

levofloxaci

n 750

mg/150 ml

in 5 %

dextrose

intravenou

piggyback

octreotide

acetate 100

mcg/ml

injection

solution

dextrose

5 % and

0.9 %

sodium

chloride

intravenou

s solution

lorazepam

2 mg/ml

injection

syringe

sodium

chloride

3 %

intravenou

s injection

solution

epinephr

ine hcl 8

mg/250

ml (32

mcg/ml)

in 5 %

dextrose

intraven

ous

fentan yl

(pf) 50

mcg/ml

injection

solution

pen

tobarbit

2500mg/50

ml adult

infusion

lorazepam

2 mg/ml

injection

wrapper

vancomyci

n 1

gram/200

ml in

dextrose

5 %

intravenou

piggyback

famotidine

(pf) 20

mg/50 ml

in 0.9 %

nacl (iso)

intravenou

piggyback

sodium

chloride

0.45 %

intravenou

s solution

dextrose

10 % iv

bolus

amiodaron

e 150

mg/100 ml

(1.5

mg/ml) in

dextrose,

iso-

osmotic iv

piperacillin

tazobactam

4.5

gram/100

dextrose(is

o-osmotic)

piggyback

vancom

ycin

1.25

gram/25

0 ml in

0.9 %

sodium

chloride

intraven

ous

famotidine

(pf) 20

mg/2 ml

intravenou

s solution

nitroglycer

in 50

mg/250 ml

(200

mcg/ml) in

5 %

dextrose

intravenou

nitroglycer

in 100

mg/250 ml

(400

mcg/ml) in

5 %

dextrose

intravenou

nitroglycer

in 100

mg/250 ml

(400

mcg/ml) in

5 %

dextrose

intravenou

piperacillin

tazobactam

3.375

gram/50

dextrose(is

o-os) iv

piggyback

pentobarbit

2500mg/50

ml adult

infusion

famotidine

(pf) 20

mg/50 ml

in 0.9 %

nacl (iso)

intravenou

piggyback

midazolam

1 mg/ml

injection

solution

lactated

ringers

irrigation

solution

piperacil

lin-

tazobact

3.375

gram/50

dextrose

(iso-os)

piggyba

vancomyci

n 1,000 mg

intravenou

s injection

dextrose

5 % and

0.9 %

sodium

chloride

intravenou

s solution

morphine

10 mg/ml

injection

solution

vasopressi

(pitressin)

infusion 40

units/100

cisatracuri

um 2

mg/ml

intravenou

s solution

piperacillin

tazobactam

3.375

gram/50

dextrose(is

o-os) iv

piggyback

epinephrin

e hcl 8

mg/250 ml

(32

mcg/ml) in

5 %

dextrose

intravenou

propofol

10 mg/ml

intravenou

s emulsion

vasopressi

fentan yl

heparin,

albumin,

hydromorp

lactated

dobutamin

cefepime 2

clevidipine

pentobarbit

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

(pitressin)

infusion 50

unit/50 ml

(pf) 50

mcg/ml

injection

solution

porcine

(pf) 100

unit/ml

intravenou

s syringe

human

25 %

intravenou

s solution

hone 1

mg/ml

injection

syringe

ringers iv

bolus

e 500

mg/250 ml

(2,000

mcg/ml) in

5 %

dextrose iv

gram/100

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

25 mg/50

intravenou

s emulsion

2500mg/50

ml adult

infusion

piperacillin

tazobactam

3.375

gram/50

dextrose(is

o-os) iv

piggyback

dobutam

ine 500

mg/250

(2,000

mcg/ml)

in 5 %

dextrose

hydromorp

hone 2

mg/ml

injection

syringe

cefepime 2

gram/100

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

piperacillin

tazobactam

4.5

gram/100

dextrose(is

o-osmotic)

piggyback

hydromorp

hone 1

mg/ml in

ns infusion

wrapper

famotidine

(pf) 20

mg/2 ml

intravenou

s solution

hydromorp

hone (pf) 1

mg/ml

injection

solution

hydromorp

hone 1

mg/ml

injection

syringe

nitroglycer

in 100

mg/250 ml

(400

mcg/ml) in

5 %

dextrose

intravenou

fluc

onazol

e 400

mg/200 ml

in sod.

chloride(is

intravenou

piggyback

famotidi

ne (pf)

20 mg/2

intraven

ous

solution

piperacillin

tazobactam

2.25

gram/50

ml in

dextrose(is

o) iv

piggyback

hydromorp

hone 1

mg/ml in

ns infusion

wrapper

dextrose

5 % and

lactated

ringers

intravenou

s solution

heparin

30,000

units (cell

saver) in

1000 ml ns

amiodaron

e 150

mg/100 ml

(1.5

mg/ml) in

dextrose,

iso-

osmotic iv

levofloxaci

n 500

mg/100 ml

in 5 %

dextrose

intravenou

piggyback

cisatracuri

um 2

mg/ml

intravenou

s solution

sodium

chloride

0.45 %

intravenou

s solution

dextrose

10 % in

water

(d10w)

intravenou

s solution

vancom

ycin

1,000

intraven

ous

injection

lactated

ringers

irrigation

solution

famotidine

(pf) 20

mg/50 ml

in 0.9 %

nacl (iso)

intravenou

piggyback

fentan yl

(pf) 2,500

mcg/50 ml

(50

mcg/ml)

intravenou

s pca

syringe

sodium

chloride

3 %

intravenou

s injection

solution

piperacillin

tazobactam

4.5

gram/100

dextrose(is

o-osmotic)

piggyback

norepineph

rine

bitartrate 8

mg/250 ml

(32

mcg/ml) in

0.9 % nacl

nitroglycer

in 50

mg/250 ml

(200

mcg/ml) in

5 %

dextrose

intravenou

vasopressi

(pitressin)

infusion 40

units/100

cefepime 1

gram

solution

for

injection

cefazoli

n 1

gram/50

ml in

dextrose

(iso-

osmotic)

intraven

ous

piggyba

fluconazol

e 400

mg/200 ml

in sod.

chloride(is

intravenou

piggyback

nitroglycer

in 100

mg/250 ml

(400

mcg/ml) in

5 %

dextrose

intravenou

cefazolin 1

gram/50

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

vasopressi

(pitressin)

infusion 50

unit/50 ml

dextrose

5 % and

0.45 %

sodium

chloride

intravenou

s solution

famotidine

(pf) 20

mg/50 ml

in 0.9 %

nacl (iso)

intravenou

piggyback

heparin

(porcine)

100

unit/ml

bolus from

infusion

epinephrin

e hcl 8

mg/250 ml

(32

mcg/ml) in

5 %

dextrose

intravenou

hydromorp

hone 50

mg/50 ml

(1 mg/ml)

in 0.9 %

sod.chlorid

e iv pump

resevoir

ceftriaxo

ne 1

gram/50

ml in

dextrose

(iso-

osmotic)

intraven

ous

piggyba

albumin,

human 5 %

intravenou

s solution

amiodaron

e 150

mg/100 ml

(1.5

mg/ml) in

dextrose,

iso-

osmotic iv

dex

trose

5 % and

0.45 %

sodium

chloride

intravenou

s solution

piperacillin

tazobactam

3.375

gram/50

dextrose(is

o-os) iv

piggyback

cefepime 2

gram/100

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

lorazepam

2 mg/ml

injection

wrapper

fentan yl

(pf) 50

mcg/ml

injection

solution

amiodaron

e 450

mg/250 ml

(1.8

mg/ml) in

dextrose

5 %

intravenou

s solution

ceftriaxone

1 gram

solution

for

injection

heparin

(porcine

) 100

unit/ml

bolus

from

infusion

dobutamin

e 500

mg/250 ml

(2,000

mcg/ml) in

5 %

dextrose iv

phenylephr

ine 20

mg/250 ml

(80

mcg/ml) in

0.9 %

sodium

chloride iv

heparin

(porcine)

100

unit/ml

bolus from

infusion

heparin

(porcine)

1,000

unit/ml

injection

solution

albumin,

human

25 %

intravenou

s solution

hydromorp

hone 2

mg/ml

injection

syringe

dexmede

midine 400

mcg/100

ml (4

mcg/ml) in

0.9 %

sodium

chloride iv

mannitol

25 %

intravenou

s solution

lactated

ringers iv

bolus

etomidat

e 2

mg/ml

intraven

ous

solution

famotidine

(pf) 20

mg/50 ml

in 0.9 %

nacl (iso)

intravenou

dexmedeto

midine 400

mcg/100

ml (4

mcg/ml) in

0.9 %

sodium

albumin,

human

25 %

intravenou

s solution

hydromorp

hone 1

mg/ml

injection

syringe

dextrose

10 % in

water

(d10w)

intravenou

s solution

albumin,

human

25 %

intravenou

s solution

linezolid in

dextrose in

water 600

mg/300 ml

intravenou

morphine 2

mg/ml

intravenou

s cartridge

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

piggyback

chloride iv

piggyback

hydromorp

hone 1

mg/ml

injection

syringe

sodium

chloride

0.45 %

intraven

ous

solution

heparin

(porcine)

10,000

unit/1,000

ml in ns

(unch

cupid)

dextrose

5 % and

0.45 %

sodium

chloride

intravenou

s solution

albumin,

human 5 %

intravenou

s solution

famotidine

(pf) 20

mg/50 ml

in 0.9 %

nacl (iso)

intravenou

piggyback

etomidate

2 mg/ml

intravenou

s solution

cefazolin 2

gram/100

ml in

dextrose(is

o-osmotic)

intravenou

piggyback

lactated

ringers

irrigation

solution

sodium

chloride 4

mEq/ml

intravenou

s solution

vancomyci

n 1

gram/200

ml in

dextrose

5 %

intravenou

piggyback

dextrose

5 % in

water

(d5w)

intraven

ous

solution

dobutamin

e 250

mg/250 ml

(1 mg/ml)

in 5 %

dextrose

intravenou

morphine 2

mg/ml

injection pf

wrapper

dextrose

10 % in

water

(d10w)

intravenou

s solution

nitroglycer

in 50

mg/250 ml

(200

mcg/ml) in

5 %

dextrose

intravenou

lidocaine

(pf) 100

mg/5 ml

(2 %)

intravenou

s syringe

lactated

ringers iv

bolus

cefazoli

n 1

gram/50

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

propofol

infusion 10

mg/ml

dobutamin

e 1,000

mg/250

ml(4,000

mcg/ml) in

5 %

dextrose iv

dopamin

e 400

mg/250

(1,600

mcg/ml)

in 5 %

dextrose

intraven

ous

solution

cefazolin 3

gram/100

ml in

0.9 %

sodium

chloride

intravenou

piggyback

fluconazol

e 400

mg/200 ml

in sod.

chloride(is

intravenou

piggyback

heparin

(porcine)

10,000

unit/1,000

ml in ns

(unch

cupid)

etomidate

2 mg/ml

intravenou

s solution

cefazolin 2

gram/100

ml in

dextrose(is

o-osmotic)

intravenou

piggyback

hydromorp

hone 1

mg/ml in

ns infusion

wrapper

ceftriaxone

1 gram/50

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

dextrose

5 % and

lactated

ringers

intravenou

s solution

hydromorp

hone (pf) 1

mg/ml

injection

solution

clindam

ycin 900

mg/50

ml in

5 %

dextrose

intraven

ous

piggyba

cefazolin 2

gram/100

ml in

dextrose(is

o-osmotic)

intravenou

piggyback

morphine 1

mg/ml in

0.9 %

sodium

chloride

injectable

pump

reservoir

propofol

infusion 10

mg/ml

fentan yl

(pf) 50

mcg/ml

injection

solution

ceftriaxone

1 gram

solution

for

injection

dextrose

5 % and

0.9 %

sodium

chloride

intravenou

s solution

dexmedeto

midine 200

mcg/50 ml

(4 mcg/ml)

in 0.9 %

sodium

chloride iv

lorazepam

2 mg/ml

injection

wrapper

midazolam

5 mg/ml

(combined

) injection

solution

wrapper

dextrose

5 % and

0.9 %

sodium

chloride

intraven

ous

solution

albumin,

human

25 %

intravenou

s solution

lidocaine

(pf) 100

mg/5 ml

(2 %)

intravenou

s syringe

dextrose

5 % and

0.9 %

sodium

chloride

intravenou

s solution

linezolid in

dextrose in

water 600

mg/300 ml

intravenou

piggyback

amiodaron

e 450

mg/250 ml

(1.8

mg/ml) in

dextrose

5 %

intravenou

s solution

esmolol

2,500

mg/250 ml

(10 mg/ml)

in sodium

chloride

(iso-

osmotic) iv

morphine 2

mg/ml

intravenou

s cartridge

cisatracuri

um 2

mg/ml

intravenou

s solution

meperidine

(pf) 25

mg/ml

injection

syringe

amiodar

one 450

mg/250

ml (1.8

mg/ml)

dextrose

5 %

intraven

ous

solution

dopamine

400

mg/250 ml

(1,600

mcg/ml) in

5 %

dextrose

intravenou

s solution

sodium

chloride

0.9 %

intravenou

s solution

cefazolin 2

gram/100

ml in

dextrose(is

o-osmotic)

intravenou

piggyback

vancomyci

n 1,000 mg

intravenou

s injection

fluconazol

e 400

mg/200 ml

in sod.

chloride(is

intravenou

piggyback

vasopressi

n 40

units/50 ml

(0.8

unit/ml) in

ns infusion

lidocaine

(pf) 100

mg/5 ml

(2 %)

intravenou

s syringe

phenylephr

ine 20

mg/250 ml

(80

mcg/ml) in

0.9 %

sodium

chloride iv

clindamyci

n 900

mg/50 ml

in 5 %

dextrose

intravenou

piggyback

dobutam

ine

1,000

mg/250

ml(4,00

mcg/ml)

in 5 %

dextrose

norepinep

rine

bitartrate 8

mg/250 ml

(32

mcg/ml) in

dextrose

5 % iv

cefepime 1

gram

solution

for

injection

lactated

ringers iv

bolus

lactated

ringers

irrigation

solution

norepineph

rine

bitartrate 8

mg/250 ml

(32

mcg/ml) in

dextrose

5 % iv

sodium

chloride

3 %

intravenou

s injection

solution

sodium

chloride

0.9 %

intravenou

s solution

lactated

ringers

irrigation

solution

heparin,

porcine

(pf) 100

unit/ml

intravenou

fluconaz

ole 400

mg/200

ml in

sod.

vasopressi

n 40

units/50 ml

(0.8

unit/ml) in

morphine 1

mg/ml in

dextrose

5 %

intravenou

dextrose

5 % in

water

(d5w)

intravenou

cefepime 2

gram/100

ml in

dextrose

(iso-

morphine 1

mg/ml in

0.9 %

sodium

chloride

lactated

ringers

irrigation

solution

morphine 1

mg/ml in

dextrose

5 %

intravenou

piperacillin

tazobactam

3.375

gram/50

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

s syringe

chloride

(iso)

intraven

ous

piggyba

ns infusion

s solution

osmotic

)

intravenou

piggyback

injectable

pump

reservoir

s solution

dextrose(is

o-os) iv

piggyback

linezolid in

dextrose in

water 600

mg/300 ml

intravenou

piggyback

morphin

e 1

mg/ml

in 0.9 %

sodium

chloride

injectabl

e pump

reservoir

fluconazol

e 200

mg/100 ml

in sod.

chloride

(iso)

intravenou

piggyback

cefazolin 2

gram/100

ml in

dextrose(is

o-osmotic)

intravenou

piggyback

clindamyci

n 900

mg/50 ml

in 5 %

dextrose

intravenou

piggyback

morphine 2

mg/ml

injection pf

wrapper

cefazolin 2

gram/50

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

milrinone

20 mg/100

ml(200

mcg/ml) in

5 %

dextrose

intravenou

piggyback

eparin

(porcine)

10,000

unit/1,000

ml in ns

(unch

cupid)

morphine 2

mg/ml

injection pf

wrapper

lorazepam

2 mg/ml

injection

wrapper

fluconaz

ole 200

mg/100

ml in

sod.

chloride

(iso)

intraven

ous

piggyba

norepineph

rine

bitartrate 8

mg/250 ml

(32

mcg/ml) in

0.9 % nacl

hydromorp

hone 50

mg/50 ml

(1 mg/ml)

in 0.9 %

sod.chlorid

e iv pump

resevoir

fluconazol

e 400

mg/200 ml

in sod.

chloride(is

intravenou

piggyback

midazolam

1 mg/ml in

0.9 %

sodium

chloride

intravenou

milrinone

20 mg/100

ml(200

mcg/ml) in

5 %

dextrose

intravenou

piggyback

meperidine

(pf) 25

mg/ml

injection

syringe

lorazepam

2 mg/ml

injection

wrapper

heparin

(porcine)

10,000

unit/1,000

ml in ns

(unch

cupid)

pantoprazo

le 40 mg

intravenou

s solution

dextrose

10 % in

water

(d10w)

intraven

ous

solution

nitroglycer

in 50

mg/250 ml

(200

mcg/ml) in

5 %

dextrose

intravenou

heparin

(porcine)

10,000

unit/1,000

ml in ns

(unch

cupid)

dobutamin

e 250

mg/250 ml

(1 mg/ml)

in 5 %

dextrose

intravenou

albumin,

human

25 %

intravenou

s solution

clindamyci

n 900

mg/50 ml

in 5 %

dextrose

intravenou

piggyback

digoxin

250

mcg/ml

(0.25

mg/ml)

injection

solution

hydromorp

hone 1

mg/ml in

ns infusion

wrapper

dobutamin

e 500

mg/250 ml

(2,000

mcg/ml) in

5 %

dextrose iv

ceftriaxone

1 gram/50

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

cefazoli

n 2

gram/50

ml in

dextrose

(iso-

osmotic)

intraven

ous

piggyba

piperacillin

tazobactam

3.375

gram/50

dextrose(is

o-os) iv

piggyback

vasopressi

n 40

units/50 ml

(0.8

unit/ml)

ssc

premade

infusion

lidocai

(pf) 4

mg/ml

(0.4 %) in

5 %

dextrose

intravenou

s solution

ceftriaxone

1 gram

solution

for

injection

dopamine

800

mg/500 ml

(1,600

mcg/ml) in

5 %

dextrose

intravenou

s solution

eptifibatide

0.75

mg/ml

intravenou

s solution

heparin

(porcine)

25,000

unit/250

ml in

0.45 %

sodium

chloride iv

solution

etomidate

2 mg/ml

intravenou

s solution

dopamine

800

mg/500 ml

(1,600

mcg/ml) in

5 %

dextrose

intravenou

s solution

linezolid

in 5%

dextrose

in water

600

mg/300

intraven

ous

piggyba

hydromorp

hone 1

mg/ml

injection

syringe

vasopressi

(pitressin)

infusion 40

units/100

mannitol

25 %

intravenou

s solution

heparin

(porcine)

25,000

unit/250

ml in

0.45 %

sodium

chloride iv

solution

vasopressi

(pitressin)

infusion 40

units/100

hydromorp

hone 50

mg/50 ml

(1 mg/ml)

in 0.9 %

sod.chlorid

e iv pump

resevoir

esmolol

2,500

mg/250 ml

(10 mg/ml)

in sodium

chloride

(iso-

osmotic) iv

dextrose

5 % and

0.9 %

sodium

chloride

intravenou

s solution

morphine

2 mg/ml

injection

pf wrapper

milrinon

e 20

mg/100

ml(200

mcg/ml)

in 5 %

dextrose

intraven

ous

piggyba

digoxin

250

mcg/ml

(0.25

mg/ml)

injection

solution

clindamyci

n 600

mg/50 ml

in 5 %

dextrose

intravenou

piggyback

fentan yl

(sublimaze

) 100 mcg

in ns 50ml

(rex or)

eptifibatide

0.75

mg/ml

intravenou

s solution

heparin

(porcine)

100

unit/ml

bolus from

infusion

midazolam

1 mg/ml

injection

solution

eptifibatide

0.75

mg/ml

intravenou

s solution

dobutamin

e 250

mg/250 ml

(1 mg/ml)

in 5 %

dextrose

intravenou

norepineph

rine

bitartrate 8

mg/250 ml

(32

mcg/ml) in

hydrom

orphon e

1 mg/ml

injection

syringe

heparin

(porcine)

100

unit/ml

bolus from

infusion

midazolam

5 mg/ml

(combined

) injection

solution

wrapper

hydromorp

hone 1

mg/ml in

ns infusion

wrapper

fluconazol

e 400

mg/200 ml

in sod.

chloride(is

pantoprazo

le 40 mg

intravenou

s solution

dextrose

5 % in

water

(d5w)

intravenou

s solution

hydromorp

hone 2

mg/ml

injection

syringe

vasopressi

n 40

units/50 ml

(0.8

unit/ml)

ssc

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

dextrose

5 % iv

intravenou

piggyback

premade

infusion

fluconazol

e 200

mg/100 ml

in sod.

chloride

(iso)

intravenou

piggyback

meperidi

ne (pf)

mg/ml

injection

syringe

heparin

(porcine)

25,000

unit/250

ml in

0.45 %

sodium

chloride iv

solution

norepineph

rine

bitartrate 8

mg/250 ml

(32

mcg/ml) in

dextrose

5 % iv

famotidine

(pf) 20

mg/50 ml

in 0.9 %

nacl (iso)

intravenou

piggyback

cefazolin 2

gram/50

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

lorazepam

2 mg/ml

injection

wrapper

fentan yl

(sublimaze

) 100 mcg

in ns 50ml

(rex or)

dobutamin

e 250

mg/250 ml

(1 mg/ml)

in 5 %

dextrose

intravenou

cefepime 2

gram/100

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

succinylch

oline

chloride

20mg/ml

syringe/via

l wrapper

midazol

am 1

mg/ml

injection

solution

hydromorp

hone 1

mg/ml in

ns infusion

wrapper

digoxin

250

mcg/ml

(0.25

mg/ml)

injection

solution

amiodaron

e 150

mg/100 ml

(1.5

mg/ml) in

dextrose,

iso-

osmotic iv

piperacillin

tazobactam

3.375

gm/50ml

dextrose

(extended

duration)

alteplase

0.81 mg/kg

stroke

infusion

dexmedeto

midine 200

mcg/50 ml

(4 mcg/ml)

in 0.9 %

sodium

chloride iv

morphine 1

mg/ml in

0.9 %

sodium

chloride

injectable

pump

reservoir

heparin

(porcine)

25,000

unit/250

ml in

0.45 %

sodium

chloride iv

solution

vancomyci

n 1.5

gram/500

ml in

0.9 %

sodium

chloride

intravenou

s solution

vasopres

sin

(pitressi

infusion

units/10

0 ml

epinephrin

e hcl 8

mg/250 ml

(32

mcg/ml) in

5 %

dextrose

intravenou

eptifibatide

0.75

mg/ml

intravenou

s solution

dexmedeto

midine 200

mcg/50 ml

(4 mcg/ml)

in 0.9 %

sodium

chloride iv

dextrose

5 % in

water

(d5w)

intravenou

s solution

eptifibatide

0.75

mg/ml

intravenou

s solution

dextrose

10 % in

water

(d10w)

intravenou

s solution

midazolam

1 mg/ml in

0.9 %

sodium

chloride

intravenou

esmolol

2,500

mg/250 ml

(10 mg/ml)

in sodium

chloride

(iso-

osmotic) iv

famotidine

(pf) 20

mg/50 ml

in 0.9 %

nacl (iso)

intravenou

piggyback

pantopra

zole 40

intraven

ous

solution

mannitol

20 %

intravenou

s solution

dopamine

400

mg/250 ml

(1,600

mcg/ml) in

5 %

dextrose

intravenou

s solution

ceftriaxone

1 gram/50

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

vanc

omyci

n 1.5

gram/500

ml in

0.9 %

sodium

chloride

intravenou

s solution

morphine 2

mg/ml

injection pf

wrapper

norepineph

rine

bitartrate 8

mg/250 ml

(32

mcg/ml) in

dextrose

5 % iv

dextrose

10 % in

water

(d10w)

intravenou

s solution

digoxin

250

mcg/ml

(0.25

mg/ml)

injection

solution

metronidaz

ole 500

mg/100

ml-sodium

chloride(is

intravenou

piggyback

heparin

(porcine

) 25,000

unit/250

ml in

0.45 %

sodium

chloride

solution

dextrose

5 % and

0.45 %

sodium

chloride

intravenou

s solution

vancomyci

n 1.75

gram/500

ml in

0.9 %

sodium

chloride

intravenou

diazepam 5

mg/ml

injection

syringe

dexmedeto

midine 200

mcg/50 ml

(4 mcg/ml)

in 0.9 %

sodium

chloride iv

clindamyci

n 600

mg/50 ml

in 5 %

dextrose

intravenou

piggyback

dexmedeto

midine 400

mcg/100

ml (4

mcg/ml) in

0.9 %

sodium

chloride iv

succinylch

oline

chloride

20mg/ml

syringe/via

l wrapper

phenobarbi

tal sodium

65 mg/ml

injection

solution

hydromorp

hone 1

mg/ml in

ns infusion

wrapper

amiodar

one 360

mg/200

ml (1.8

mg/ml)

dextrose

, iso-

osmotic

dextrose

10 % in

water

(d10w)

intravenou

s solution

ceftriaxone

1 gram/50

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

piperacillin

tazobactam

3.375

gm/50ml

dextrose

(extended

duration)

alteplase

0.81 mg/kg

stroke

infusion

cyclospori

ne 1 mg/ml

ns aviva iv

heparin

(porcine)

10,000

unit/1,000

ml in

0.9 % sod.

chloride iv

solution

meperidine

(pf) 25

mg/ml

injection

syringe

hydromorp

hone 1

mg/ml

injection

syringe

cefazolin 2

gram/100

ml in

dextrose(is

o-osmotic)

intravenou

piggyback

midazol

am (pf)

5 mg/ml

injection

solution

midazolam

1 mg/ml in

0.9 %

sodium

chloride

intravenou

propofol

infusion 10

mg/ml

vancomyci

n 1

gram/200

ml in

dextrose

5 %

intravenou

piggyback

dextrose

10 % in

water

(d10w)

intravenou

s solution

cefepime 1

gram

solution

for

injection

metronidaz

ole 500

mg/100

ml-sodium

chloride(is

intravenou

piggyback

midazolam

1 mg/ml

injection

solution

heparin,

porcine

(pf) 100

unit/ml

intravenou

s syringe

albumin,

human

25 %

intravenou

s solution

albumin,

human

5 %

intraven

ous

solution

hydromorp

hone 50

mg/50 ml

(1 mg/ml)

in 0.9 %

sod.chlorid

heparin,

porcine

(pf) 100

unit/ml

intravenou

s syringe

dobutamin

e 500

mg/250 ml

(2,000

mcg/ml) in

5 %

norepineph

rine

bitartrate 8

mg/250 ml

(32

mcg/ml) in

nitrogly

cer

in 100

mg/250 ml

(400

mcg/ml) in

5 %

famotidine

10 mg/ml

injection

solution

(multi-vial

size)

fentan yl

(sublimaze

) 100 mcg

in ns 50ml

(rex or)

fentan yl

(pf) 50

mcg/ml

injection

solution

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

e iv pump

resevoir

dextrose iv

dextrose

5 % iv

dextrose

intravenou

amiodaron

e 360

mg/200 ml

(1.8

mg/ml) in

dextrose,

iso-

osmotic iv

alteplase

0.81

mg/kg

stroke

infusion

midazolam

1 mg/ml

injection

solution

lactated

ringers

intravenou

s solution

heparin,

porcine

(pf) 100

unit/ml

intravenou

s syringe

dexmedeto

midine 400

mcg/100

ml (4

mcg/ml) in

0.9 %

sodium

chloride iv

lidocaine

(pf) 4

mg/ml

(0.4 %) in

5 %

dextrose

intravenou

s solution

vancomyci

n 1

gram/200

ml in

dextrose

5 %

intravenou

piggyback

midazolam

(pf) 5

mg/ml

injection

solution

vancomyci

n 1.75

gram/500

ml in

0.9 %

sodium

chloride

intravenou

piperacillin

tazobactam

2.25

gram/50

ml in

dextrose(is

o) iv

piggyback

lorazepa

m 2

mg/ml

injection

syringe

cyclospori

ne 1 mg/ml

ns aviva iv

vancomyci

n 1.5

gram/500

ml in

0.9 %

sodium

chloride

intravenou

s solution

famotidine

(pf) 20

mg/2 ml

intravenou

s solution

amiodaron

e 150

mg/100 ml

(1.5

mg/ml) in

dextrose,

iso-

osmotic iv

heparin,

porcine

(pf) 100

unit/ml

intravenou

s syringe

vancomyci

n 2

gram/500

ml in

0.9 %

sodium

chloride

intravenou

propofol

infusion 10

mg/ml

morphine 1

mg/ml in

dextrose

5 %

intravenou

s solution

dextrose

10 % iv

bolus

heparin,

porcine

(pf) 100

unit/ml

intraven

ous

syringe

fentan yl

(sublimaze

) 100 mcg

in ns 50ml

(rex or)

vancomyci

n 1

gram/200

ml in

dextrose

5 %

intravenou

piggyback

sodium

chloride 4

mEq/ml

intravenou

s solution

heparin

(porcine)

10,000

unit/1,000

ml in

0.9 % sod.

chloride iv

solution

fentan yl

(sublimaze

) 100 mcg

in ns 50ml

(rex or)

dobutamin

e 500

mg/250 ml

(2,000

mcg/ml) in

5 %

dextrose iv

alteplase

0.81 mg/kg

stroke

infusion

heparin

(porcine)

10,000

unit/1,000

ml in

0.9 % sod.

chloride iv

solution

heparin,

porcine

(pf) 10

unit/ml

intravenou

s syringe

dextrose

5 % and

0.45 %

sodium

chloride

intraven

ous

solution

vasopressi

(pitressin)

infusion 40

units/100

metronidaz

ole 500

mg/100

ml-sodium

chloride(is

intravenou

piggyback

levofloxaci

n 750

mg/150 ml

in 5 %

dextrose

intravenou

piggyback

metronidaz

ole 500

mg/100

ml-sodium

chloride(is

intravenou

piggyback

sodium

chloride 4

mEq/ml

intravenou

s solution

cefazolin 2

gram/50

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

dextrose

5 % in

water

(d5w)

intravenou

s solution

midazolam

(pf) 5

mg/ml

injection

solution

cisatracuri

um 2

mg/ml

intravenou

s solution

amiodar

one 150

mg/100

ml (1.5

mg/ml)

dextrose

, iso-

osmotic

vancomyci

n 1

gram/200

ml in

dextrose

5 %

intravenou

piggyback

ceftriaxone

1 gram

solution

for

injection

cefepime 2

gram/100

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

amiodaron

e 450

mg/250 ml

(1.8

mg/ml) in

dextrose

5 %

intravenou

s solution

aztreo

nam

1 gram

solution

for iv push

aztreonam

1 gram

solution

for iv push

heparin,

porcine

(pf) 100

unit/ml

intravenou

s syringe

hydromorp

hone 1

mg/ml in

ns infusion

wrapper

pentobarbit

2500mg/50

ml adult

infusion

sodium

chloride

0.9 %

intraven

ous

solution

vancomyci

n 1.75

gram/500

ml in

0.9 %

sodium

chloride

intravenou

heparin

30,000

units (cell

saver) in

1000 ml ns

amiodaron

e 360

mg/200 ml

(1.8

mg/ml) in

dextrose,

iso-

osmotic iv

cyclospori

ne 1 mg/ml

ns aviva iv

sodium

chloride

0.45 %

intravenou

s solution

dextrose

5 % and

lactated

ringers

intravenou

s solution

clindamyci

n 900

mg/50 ml

in 5 %

dextrose

intravenou

piggyback

dextrose

10 % in

water

(d10w)

intravenou

s solution

dopamine

400

mg/250 ml

(1,600

mcg/ml) in

5 %

dextrose

intravenou

s solution

diazepa

m 5

mg/ml

injection

syringe

dopamine

800

mg/500 ml

(1,600

mcg/ml) in

5 %

dextrose

intravenou

s solution

fentan yl

(sublimaze

) 100 mcg

in ns 50ml

(rex or)

mannitol

20 %

intravenou

s solution

phenobarbi

tal sodium

65 mg/ml

injection

solution

vasopressi

(pitressin)

infusion 50

unit/50 ml

mannitol

20 %

intravenou

s solution

metronidaz

ole 500

mg/100

ml-sodium

chloride(is

intravenou

piggyback

norepineph

rine

bitartrate 8

mg/250 ml

(32

mcg/ml) in

dextrose

5 % iv

levofloxaci

n 750

mg/150 ml

in 5 %

dextrose

intravenou

nitrogly

cerin

100

mg/250

ml (400

mcg/ml)

in 5 %

pentobarbit

al sodium

50 mg/ml

injection

solution

sodium

chloride 4

mEq/ml

intravenou

s solution

vancomyci

n 1.75

gram/500

ml in

0.9 %

sodium

chloride

dobutamin

e 500

mg/250 ml

(2,000

mcg/ml) in

5 %

dextrose iv

midazolam

5 mg/ml

(combined

) injection

solution

wrapper

amiodaron

e 360

mg/200 ml

(1.8

mg/ml) in

dextrose,

iso-

amiodaron

e 360

mg/200 ml

(1.8

mg/ml) in

dextrose,

iso-

cyclospori

ne 1 mg/ml

ns aviva iv

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

piggyback

dextrose

intraven

ous

intravenou

osmotic

midazolam

1 mg/ml in

0.9 %

sodium

chloride

intravenou

piperacil

lin-

tazobact

3.375

gm/50m

dextrose

(extende

duration

)

cisatracuri

um 2

mg/ml

intravenou

s solution

vancomyci

n 2

gram/500

ml in

0.9 %

sodium

chloride

intravenou

dopamine

800

mg/500 ml

(1,600

mcg/ml) in

5 %

dextrose

intravenou

s solution

lorazepam

2 mg/ml

injection

syringe

pentobarbit

al sodium

50 mg/ml

injection

solution

midazolam

(pf) 1

mg/ml in

0.9 %

sodium

chloride

intravenou

s solution

famotidine

10 mg/ml

injection

solution

(multi-vial

size)

vancomyci

n 1

gram/200

ml in

dextrose

5 %

intravenou

piggyback

dexmedeto

midine 400

mcg/100

ml (4

mcg/ml) in

0.9 %

sodium

chloride iv

cefazoli

n 2

gram/10

0 ml in

dextrose

(iso-

osmotic)

intraven

ous

piggyba

metronidaz

ole 500

mg/100

ml-sodium

chloride(is

intravenou

piggyback

lactated

ringers

irrigation

solution

midazolam

5 mg/ml

(combined

) injection

solution

wrapper

heparin

(porcine)

10,000

unit/ml

injection

solution

nitroglycer

in 50

mg/250 ml

(200

mcg/ml) in

5 %

dextrose

intravenou

heparin,

porcine

(pf) 100

unit/ml

intravenou

s syringe

cefepime 1

gram

solution

for

injection

vancomyci

n 2

gram/500

ml in

0.9 %

sodium

chloride

intravenou

nitroglycer

in 50

mg/250 ml

(200

mcg/ml) in

5 %

dextrose

intravenou

lactated

ringers

irrigatio

solution

levofloxaci

n 750

mg/150 ml

in 5 %

dextrose

intravenou

piggyback

levofloxaci

n 750

mg/150 ml

in 5 %

dextrose

intravenou

piggyback

insulin u

100 regular

human 100

unit/ml

injection

solution

vancomyci

n 1.25

gram/250

ml in

0.9 %

sodium

chloride

intravenou

hydromorp

hone 1

mg/ml

injection

syringe

levofloxaci

n 750

mg/150 ml

in 5 %

dextrose

intravenou

piggyback

heparin

30,000

units (cell

saver) in

1000 ml ns

levofloxaci

n 750

mg/150 ml

in 5 %

dextrose

intravenou

piggyback

fat

emulsion

20 %

intravenou

famotidi

ne (pf)

mg/50

ml in

0.9 %

nacl

(iso)

intraven

ous

piggyba

clindamyci

n 600

mg/50 ml

in 5 %

dextrose

intravenou

piggyback

milrinone

20 mg/100

ml(200

mcg/ml) in

5 %

dextrose

intravenou

piggyback

pentobarbit

al sodium

50 mg/ml

injection

solution

hydromorp

hone 50

mg/50 ml

(1 mg/ml)

in 0.9 %

sod.chlorid

e iv pump

resevoir

pentobarbit

2500mg/50

ml adult

infusion

heparin

(porcine)

1,000

unit/ml

injection

solution

vancomyci

n 2

gram/500

ml in

0.9 %

sodium

chloride

intravenou

cefazolin 2

gram/50

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

dextrose

5 % and

lactated

ringers

intravenou

s solution

dopamin

e 800

mg/500

(1,600

mcg/ml)

in 5 %

dextrose

intraven

ous

solution

dexmedeto

midine 200

mcg/50 ml

(4 mcg/ml)

in 0.9 %

sodium

chloride iv

vasopressi

n 40

units/50 ml

(0.8

unit/ml) in

ns infusion

cisatracuri

um 2

mg/ml

intravenou

s solution

hydromorp

hone 4

mg/ml

injection

syringe

dextrose

5 % and

0.9 %

sodium

chloride

intravenou

s solution

piperacillin

tazobactam

2.25

gram/50

ml in

dextrose(is

o) iv

piggyback

lidocaine

(pf) 4

mg/ml

(0.4 %) in

5 %

dextrose

intravenou

s solution

octreotide

acetate 100

mcg/ml

injection

solution

heparin

(porcine)

100

unit/ml

bolus from

infusion

dexmed

etomidin

e 200

mcg/50

ml (4

mcg/ml)

in 0.9 %

sodium

chloride

octreotide

acetate 100

mcg/ml

injection

solution

hydromorp

hone 4

mg/ml

injection

syringe

aztreonam

2 gram

solution

for iv push

amiodaron

e 360

mg/200 ml

(1.8

mg/ml) in

dextrose,

iso-

osmotic iv

hydromorp

hone 50

mg/50 ml

(1 mg/ml)

in 0.9 %

sod.chlorid

e iv pump

resevoir

heparin

30,000

units (cell

saver) in

1000 ml ns

vancomyci

n 1.75

gram/500

ml in

0.9 %

sodium

chloride

intravenou

amiodaron

e 360

mg/200 ml

(1.8

mg/ml) in

dextrose,

iso-

osmotic iv

morphine

10 mg/ml

injection

solution

pentoba

bital

sodium

mg/ml

injection

lidocaine

(pf) 4

mg/ml

(0.4 %) in

5 %

dextrose

cefazolin 2

gram/50

ml in

dextrose

(iso-

osmotic)

midazolam

1 mg/ml in

0.9 %

sodium

chloride

intravenou

famotidine

10 mg/ml

injection

solution

(multi-vial

size)

midazolam

1 mg/ml in

0.9 %

sodium

chloride

intravenou

morphine 2

mg/ml

injection pf

wrapper

octreotide

acetate 100

mcg/ml

injection

solution

fluconazol

e 200

mg/100 ml

in sod.

chloride

(iso)

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

solution

intravenou

s solution

intravenou

piggyback

intravenou

piggyback

milrinone

20 mg/100

ml(200

mcg/ml) in

5 %

dextrose

intravenou

piggyback

cisatracu

rium 2

mg/ml

intraven

ous

solution

milrinone

20 mg/100

ml(200

mcg/ml) in

5 %

dextrose

intravenou

piggyback

hydromorp

hone 1

mg/ml

injection

syringe

cefazolin 3

gram/100

ml in

0.9 %

sodium

chloride

intravenou

piggyback

morphine

10 mg/ml

injection

solution

midazolam

(pf) 1

mg/ml in

0.9 %

sodium

chloride

intravenou

s solution

morphine

10 mg/ml

injection

solution

fluconazol

e 200

mg/100 ml

in sod.

chloride

(iso)

intravenou

piggyback

pantoprazo

le 40 mg

intravenou

s solution

heparin

(porcine)

25,000

unit/250

ml in

0.45 %

sodium

chloride iv

solution

sodium

chloride

3 %

intraven

ous

bolus

solution

vancomyci

n 1.25

gram/250

ml in

0.9 %

sodium

chloride

intravenou

hydromorp

hone (pf) 1

mg/ml

injection

solution

sodium

chloride

3 %

intravenou

s bolus

solution

milrinone

20 mg/100

ml(200

mcg/ml) in

5 %

dextrose

intravenou

piggyback

dextrose

10 % iv

bolus

lactated

ringers

intravenou

s solution

vecuroniu

m bromide

10 mg

intravenou

s solution

pentobarbit

al sodium

50 mg/ml

injection

solution

dobutamin

e 500

mg/250 ml

(2,000

mcg/ml) in

5 %

dextrose iv

sodium

chloride

3 %

intraven

ous

injection

solution

hydromorp

hone 4

mg/ml

injection

syringe

lorazepam

2 mg/ml

injection

wrapper

eptifibatide

0.75

mg/ml

intravenou

s solution

midazolam

5 mg/ml

(combined

) injection

solution

wrapper

heparin

30,000

units (cell

saver) in

1000 ml ns

cisatracuri

um 2

mg/ml

intravenou

s solution

heparin,

porcine

(pf) 10

unit/ml

intravenou

s syringe

midazolam

5 mg/ml

(combined

) injection

solution

wrapper

albumin,

human 5 %

intravenou

s solution

lidocain

e (pf) 4

mg/ml

(0.4 %)

in 5 %

dextrose

intraven

ous

solution

piperacillin

tazobactam

3.375

gm/50ml

dextrose

(extended

duration)

piperacillin

tazobactam

4.5

gram/100

dextrose(is

o-osmotic)

piggyback

hydromorp

hone 4

mg/ml

injection

syringe

cisatracuri

um 2

mg/ml

intravenou

s solution

famotidine

10 mg/ml

injection

solution

(multi-vial

size)

piperacillin

tazobactam

4.5

gram/100

dextrose(is

o-osmotic)

piggyback

albumin,

human

25 %

intravenou

s solution

midazolam

1 mg/ml in

0.9 %

sodium

chloride

intravenou

cefazolin 2

gram/50

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

vasopres

sin 40

units/50

ml (0.8

unit/ml)

in ns

infusion

morphine 2

mg/ml

injection pf

wrapper

pipera

cillin

tazobactam

3.375

gram/50

dextrose(is

o-os) iv

piggyback

famotidine

10 mg/ml

injection

solution

(multi-vial

size)

mannitol

25 %

intravenou

s solution

vancomyci

n 1.5

gram/500

ml in

0.9 %

sodium

chloride

intravenou

s solution

epinephrin

e hcl 8

mg/250 ml

(32

mcg/ml) in

5 %

dextrose

intravenou

fat

emulsion

20 %

intravenou

dexmedeto

midine 200

mcg/50 ml

(4 mcg/ml)

in 0.9 %

sodium

chloride iv

vasopressi

(pitressin)

infusion 40

units/100

hydrom

orphon e

4 mg/ml

injection

syringe

sodium

chloride

3 %

intravenou

s bolus

solution

amiodaron

e 360

mg/200 ml

(1.8

mg/ml) in

dextrose,

iso-

osmotic iv

vasopressi

(pitressin)

infusion 40

units/100

dextrose

5 % and

0.45 %

sodium

chloride

intravenou

s solution

fentan yl

(pf) 50

mcg/ml

injection

solution

heparin

(porcine)

100

unit/ml

load from

infusion

milrinone

20 mg/100

ml(200

mcg/ml) in

5 %

dextrose

intravenou

piggyback

sodium

chloride

3 %

intravenou

s bolus

solution

heparin

(porcine)

100

unit/ml

load from

infusion

famotidi

ne 10

mg/ml

injection

solution

(multi-

vial

size)

heparin

(porcine)

100

unit/ml

load from

infusion

pentobarbit

al sodium

50 mg/ml

injection

solution

heparin

(porcine)

25,000

unit/250

ml in

0.45 %

sodium

chloride iv

solution

hydromorp

hone 2

mg/ml

injection

syringe

heparin

(porcine)

25,000

unit/250

ml in

0.45 %

sodium

chloride iv

solution

dextrose

10 % iv

bolus

vancomyci

n 1,000 mg

intravenou

s injection

cefepime 1

gram

solution

for

injection

100

vecuroniu

m bromide

20 mg

intravenou

s solution

hydrom

orphon e

1 mg/ml

in ns

infusion

wrapper

alteplase

0.81 mg/kg

stroke

infusion

vecuroniu

m bromide

20 mg

intravenou

s solution

cefazolin 2

gram/50

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

sodium

chloride

3 %

intravenou

s bolus

solution

insulin u

100 regular

human 100

unit/ml

injection

solution

heparin,

porcine

(pf) 10

unit/ml

intravenou

s syringe

morphine

(pf) 1

mg/ml in

0.9%

sodium

chloride

intravenou

s solution

dextrose

10 % iv

bolus

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

101

digoxin

250

mcg/ml

(0.25

mg/ml)

injection

solution

vancom

ycin 1.5

gram/50

0 ml in

0.9 %

sodium

chloride

intraven

ous

solution

meperidine

(pf) 25

mg/ml

injection

syringe

sodium

chloride

0.9 % iv

bolus (cath

lab)

vancomyci

n 1,000 mg

intravenou

s injection

dextrose

10 % iv

bolus

heparin

(porcine)

100

unit/ml

load from

infusion

morphine

10 mg/ml

injection

syringe

morphine 2

mg/ml

injection pf

wrapper

albumin,

human

25 %

intravenou

s solution

102

fentan yl

(pf) 50

mcg/ml

injection

solution

vecuroni

bromide

10 mg

intraven

ous

solution

morphine

10 mg/ml

injection

syringe

pantoprazo

le 40 mg

intravenou

s solution

amiodaron

e 450

mg/250 ml

(1.8

mg/ml) in

dextrose

5 %

intravenou

s solution

heparin,

porcine

(pf) 100

unit/ml

intravenou

s syringe

sodium

chloride

3 %

intravenou

s bolus

solution

vecuroniu

m bromide

20 mg

intravenou

s solution

nitroglycer

in 100

mg/250 ml

(400

mcg/ml) in

5 %

dextrose

intravenou

diazepam 5

mg/ml

injection

syringe

103

phenobarbi

tal sodium

65 mg/ml

injection

solution

mannitol

25 %

intraven

ous

solution

vancomyci

n 1.5

gram/500

ml in

0.9 %

sodium

chloride

intravenou

s solution

dextrose

10 % iv

bolus

lidocaine

(pf) 100

mg/5 ml

(2 %)

intravenou

s syringe

morphine

10 mg/ml

injection

syringe

fluconazol

e 200

mg/100 ml

in sod.

chloride

(iso)

intravenou

piggyback

heparin

(porcine)

25,000

unit/250

ml in

0.45 %

sodium

chloride iv

solution

norepineph

rine

bitartrate 8

mg/250 ml

(32

mcg/ml) in

0.9 % nacl

hydromorp

hone 4

mg/ml

injection

syringe

104

amiodaron

e 450

mg/250 ml

(1.8

mg/ml) in

dextrose

5 %

intravenou

s solution

esmolol

2,500

mg/250

ml (10

mg/ml)

sodium

chloride

(iso-

osmotic)

dexmedeto

midine 400

mcg/100

ml (4

mcg/ml) in

0.9 %

sodium

chloride iv

morphine

10 mg/ml

injection

solution

morphine 2

mg/ml

intravenou

s cartridge

lorazepam

2 mg/ml

injection

wrapper

vecuroniu

m bromide

20 mg

intravenou

s solution

sodium

chloride

0.9 % iv

bolus (cath

lab)

sodium

chloride

3 %

intravenou

s injection

solution

piperacillin

tazobactam

4.5

gram/100

dextrose(is

o-osmotic)

piggyback

105

pentobarbit

al sodium

50 mg/ml

injection

solution

lidocain

e (pf)

100

mg/5 ml

(2 %)

intraven

ous

syringe

nitroglycer

in 100

mg/250 ml

(400

mcg/ml) in

5 %

dextrose

intravenou

heparin

(porcine)

25,000

unit/250

ml in

0.45 %

sodium

chloride iv

solution

heparin

(porcine)

100

unit/ml

load from

infusion

piperacillin

tazobactam

4.5

gram/100

dextrose(is

o-osmotic)

piggyback

dopamine

400

mg/250 ml

(1,600

mcg/ml) in

5 %

dextrose

intravenou

s solution

sodium

chloride

3 %

intravenou

s bolus

solution

hydromorp

hone (pf) 1

mg/ml

injection

solution

vecuroniu

m bromide

10 mg

intravenou

s solution

106

mannitol

20 %

intravenou

s solution

mannitol

20 %

intraven

ous

solution

aztreonam

2 gram

solution

for iv push

albumin,

human 5 %

intravenou

s solution

metronidaz

ole 500

mg/100

ml-sodium

chloride(is

intravenou

piggyback

vancomyci

n 2

gram/500

ml in

0.9 %

sodium

chloride

intravenou

sodium

chloride

3 %

intravenou

s injection

solution

dopamine

400

mg/250 ml

(1,600

mcg/ml) in

5 %

dextrose

intravenou

s solution

vancomyci

n 1.5

gram/500

ml in

0.9 %

sodium

chloride

intravenou

s solution

lidocaine

(pf) 100

mg/5 ml

(2 %)

intravenou

s syringe

107

midazolam

(pf) 5

mg/ml

injection

solution

morphin

e 10

mg/ml

injection

syringe

dextrose

10 % iv

bolus

mannitol

20 %

intravenou

s solution

morphine

10 mg/ml

injection

syringe

aztreonam

2 gram

solution

for iv push

digoxin

250

mcg/ml

(0.25

mg/ml)

injection

solution

pantoprazo

le 40 mg

intravenou

s solution

vancomyci

n 1.25

gram/250

ml in

0.9 %

sodium

chloride

intravenou

vecuroniu

m bromide

20 mg

intravenou

s solution

108

hydromorp

hone 2

mg/ml

injection

syringe

midazol

am (pf)

1 mg/ml

in 0.9 %

sodium

chloride

intraven

morphine 1

mg/ml in

0.9 %

sodium

chloride

injectable

pump

morphine 2

mg/ml

intravenou

s cartridge

sodium

chloride

0.9 % iv

bolus (cath

lab)

midazolam

(pf) 5

mg/ml

injection

solution

phenylephr

ine 20

mg/250 ml

(80

mcg/ml) in

0.9 %

sodium

clindamyci

n 900

mg/50 ml

in 5 %

dextrose

intravenou

sodium

chloride 4

mEq/ml

intravenou

s solution

famotidine

(pf) 20

mg/50 ml

in 0.9 %

nacl (iso)

intravenou

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

ous

solution

reservoir

chloride iv

piggyback

109

octreotide

acetate 100

mcg/ml

injection

solution

cyclospo

rine 1

mg/ml

ns aviva

pentobarbit

2500mg/50

ml adult

infusion

dobutamin

e 500

mg/250 ml

(2,000

mcg/ml) in

5 %

dextrose iv

digoxin

250

mcg/ml

(0.25

mg/ml)

injection

solution

albumin,

human 5 %

intravenou

s solution

aztreonam

2 gram

solution

for iv push

albumin,

human 5 %

intravenou

s solution

morphine

10 mg/ml

injection

solution

vancomyci

n 1.25

gram/250

ml in

0.9 %

sodium

chloride

intravenou

110

dextrose

5 % in

water

(d5w)

intravenou

s solution

pentobar

bital

2500mg/

50 ml

adult

infusion

etomidate

2 mg/ml

intravenou

s solution

lidocaine

(pf) 4

mg/ml

(0.4 %) in

5 %

dextrose

intravenou

s solution

midazolam

(pf) 5

mg/ml

injection

solution

ceftriaxone

1 gram/50

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

vancomyci

n 1.25

gram/250

ml in

0.9 %

sodium

chloride

intravenou

fluconazol

e 400

mg/200 ml

in sod.

chloride(is

intravenou

piggyback

aztreonam

2 gram

solution

for iv push

sodium

chloride

3 %

intravenou

s injection

solution

111

vancomyci

n 1.25

gram/250

ml in

0.9 %

sodium

chloride

intravenou

hydrom

orphon e

(pf) 1

mg/ml

injection

solution

ceftriaxone

1 gram/50

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

dexmedeto

midine 200

mcg/50 ml

(4 mcg/ml)

in 0.9 %

sodium

chloride iv

octreotide

acetate 100

mcg/ml

injection

solution

vancomyci

n 1.75

gram/500

ml in

0.9 %

sodium

chloride

intravenou

metronidaz

ole 500

mg/100

ml-sodium

chloride(is

intravenou

piggyback

vancomyci

n 1,000 mg

intravenou

s injection

midazolam

(pf) 1

mg/ml in

0.9 %

sodium

chloride

intravenou

s solution

cefazolin 1

gram/50

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

112

vancomyci

n 1.75

gram/500

ml in

0.9 %

sodium

chloride

intravenou

cefepim

e 1 gram

solution

for

injection

esmolol

2,500

mg/250 ml

(10 mg/ml)

in sodium

chloride

(iso-

osmotic) iv

levofloxaci

n 500

mg/100 ml

in 5 %

dextrose

intravenou

piggyback

phenobarbi

tal sodium

65 mg/ml

injection

solution

epinephrin

e hcl 8

mg/250 ml

(32

mcg/ml) in

5 %

dextrose

intravenou

hydromorp

hone (pf) 1

mg/ml

injection

solution

ceftriaxone

1 gram/50

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

albumin,

human 5 %

intravenou

s solution

milrinone

20 mg/100

ml(200

mcg/ml) in

5 %

dextrose

intravenou

piggyback

113

levofloxaci

n 500

mg/100 ml

in 5 %

dextrose

intravenou

piggyback

vasopres

sin 40

units/50

ml (0.8

unit/ml)

ssc

premade

infusion

hydromorp

hone (pf) 1

mg/ml

injection

solution

cefazolin 3

gram/100

ml in

0.9 %

sodium

chloride

intravenou

piggyback

hydromorp

hone (pf) 1

mg/ml

injection

solution

digoxin

250

mcg/ml

(0.25

mg/ml)

injection

solution

cefazolin 3

gram/100

ml in

0.9 %

sodium

chloride

intravenou

piggyback

phenobarbi

tal sodium

65 mg/ml

injection

solution

midazolam

(pf) 1

mg/ml

injection

solution

ceftriaxone

1 gram

solution

for

injection

114

fentan yl

(pf) 2,500

mcg/50 ml

(50

mcg/ml)

intravenou

s pca

syringe

levoflox

acin 500

mg/100

ml in

5 %

dextrose

intraven

ous

piggyba

vasopressi

(pitressin)

infusion 50

unit/50 ml

sugammad

ex 100

mg/ml

intravenou

s solution

pantoprazo

le 40 mg

intravenou

s solution

cefazolin 3

gram/100

ml in

0.9 %

sodium

chloride

intravenou

piggyback

epinephrin

e hcl 8

mg/250 ml

(32

mcg/ml) in

5 %

dextrose

intravenou

cefazolin 3

gram/100

ml in

0.9 %

sodium

chloride

intravenou

piggyback

dobutamin

e 500

mg/250 ml

(2,000

mcg/ml) in

5 %

dextrose iv

insulin u

100 regular

human 100

unit/ml

injection

solution

115

cefazolin 3

gram/100

ml in

0.9 %

sodium

chloride

intravenou

piggyback

heparin,

porcine

(pf) 10

unit/ml

intraven

ous

syringe

sodium

chloride 4

mEq/ml

intravenou

s solution

fluconazol

e 200

mg/100 ml

in sod.

chloride

(iso)

intravenou

piggyback

ceftriaxone

1 gram

solution

for

injection

fentan yl

(pf) 2,500

mcg/50 ml

(50

mcg/ml)

intravenou

s pca

syringe

piperacillin

tazobactam

2.25

gram/50

ml in

dextrose(is

o) iv

piggyback

etomida

2 mg/ml

intravenou

s solution

cefazolin 3

gram/100

ml in

0.9 %

sodium

chloride

intravenou

piggyback

fentan yl

(pf) 2,500

mcg/50 ml

(50

mcg/ml)

intravenou

s pca

syringe

116

sodium

chloride

3 %

intravenou

s bolus

solution

norepine

phrine

bitartrat

e 8

mg/250

ml (32

mcg/ml)

propofol

infusion 10

mg/ml

succinylch

oline

chloride

20mg/ml

syringe/via

l wrapper

epinephrin

e hcl 8

mg/250 ml

(32

mcg/ml) in

5 %

dextrose

intravenou

succinylch

oline

chloride

20mg/ml

syringe/via

l wrapper

vasopressi

n 40

units/50 ml

(0.8

unit/ml)

ssc

premade

infusion

heparin

(porcine)

10,000

unit/ml

injection

solution

etomidate

2 mg/ml

intravenou

s solution

heparin

(porcine)

100

unit/ml

load from

infusion

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

dextrose

5 % iv

117

vancomyci

n 1,000 mg

intravenou

s injection

sodium

chloride

mEq/ml

intraven

ous

solution

morphine

(pf) 1

mg/ml in

0.9%

sodium

chloride

intravenou

s solution

vancomyci

n 1.25

gram/250

ml in

0.9 %

sodium

chloride

intravenou

fentan yl

(pf) 50

mcg/ml

injection

solution

vasopressi

n 40

units/50 ml

(0.8

unit/ml)

ssc

premade

infusion

lactated

ringers

irrigation

solution

morphine

(pf) 1

mg/ml in

0.9%

sodium

chloride

intravenou

s solution

hydromorp

hone 4

mg/ml

injection

syringe

sugammad

ex 100

mg/ml

intravenou

s solution

118

aztreonam

1 gram

solution

for iv push

sugamm

adex

100

mg/ml

intraven

ous

solution

succinylch

oline

chloride

20mg/ml

syringe/via

l wrapper

hydromorp

hone 2

mg/ml

injection

syringe

sodium

chloride

0.9 %

intravenou

s solution

morphine

(pf) 1

mg/ml in

0.9%

sodium

chloride

intravenou

s solution

esmolol

2,500

mg/250 ml

(10 mg/ml)

in sodium

chloride

(iso-

osmotic) iv

succinylch

oline

chloride

20mg/ml

syringe/via

l wrapper

norepineph

rine

bitartrate 8

mg/250 ml

(32

mcg/ml) in

dextrose

5 % iv

succinylch

oline

chloride

20mg/ml

syringe/via

l wrapper

119

heparin

(porcine)

1,000

unit/500

ml in 0.9%

sodium

chloride iv

(combined

)

propofol

mg/ml

intraven

ous

emulsio

piperacillin

tazobactam

4.5

gram/100

dextrose(is

o-osmotic)

piggyback

cisatracuri

um 2

mg/ml

intravenou

s solution

sugammad

ex 100

mg/ml

intravenou

s solution

octreotide

acetate 100

mcg/ml

injection

solution

morphine

(pf) 1

mg/ml in

0.9%

sodium

chloride

intravenou

s solution

midazolam

(pf) 5

mg/ml

injection

solution

hydromorp

hone 50

mg/50 ml

(1 mg/ml)

in 0.9 %

sod.chlorid

e iv pump

resevoir

morphine

(pf) 1

mg/ml in

0.9%

sodium

chloride

intravenou

s solution

120

esmolol

2,500

mg/250 ml

(10 mg/ml)

in sodium

chloride

(iso-

osmotic) iv

heparin

30,000

units

(cell

saver) in

1000 ml

midazolam

(pf) 1

mg/ml in

0.9 %

sodium

chloride

intravenou

s solution

sodium

chloride

3 %

intravenou

s bolus

solution

etomidate

2 mg/ml

intravenou

s solution

esmolol

2,500

mg/250 ml

(10 mg/ml)

in sodium

chloride

(iso-

osmotic) iv

lactated

ringers iv

bolus

hydromorp

hone 1

mg/ml

injection

syringe

heparin

(porcine)

10,000

unit/ml

injection

solution

vancomyci

n 1.5

gram/500

ml in

0.9 %

sodium

chloride

intravenou

s solution

121

ketamine

10 mg/ml

injection

solution

octreotid

e acetate

100

mcg/ml

injection

solution

eptifibatide

0.75

mg/ml

intravenou

s solution

vancomyci

n 1,000 mg

intravenou

s injection

vancomyci

n 1.5

gram/500

ml in

0.9 %

sodium

chloride

intravenou

s solution

levofloxaci

n 500

mg/100 ml

in 5 %

dextrose

intravenou

piggyback

succinylch

oline

chloride

20mg/ml

syringe/via

l wrapper

ceftriaxone

2 gram/50

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

levofloxaci

n 500

mg/100 ml

in 5 %

dextrose

intravenou

piggyback

aztreonam

1 gram

solution

for iv push

122

piperacil

lin-

tazobact

am 4.5

gram/10

0 ml

dextrose

(iso-

osmotic)

piggyba

aztreonam

1 gram

solution

for iv push

heparin

(porcine)

10,000

unit/ml

injection

solution

piperacillin

tazobactam

2.25

gram/50

ml in

dextrose(is

o) iv

piggyback

cefepime 2

gram

solution

for iv push'

midazolam

(pf) 5

mg/ml

injection

solution

vancomyci

n 1.75

gram/500

ml in

0.9 %

sodium

chloride

intravenou

heparin

(porcine)

1,000

unit/500

ml in 0.9%

sodium

chloride iv

(combined

)

fluconazol

e 400

mg/200 ml

in sod.

chloride(is

intravenou

piggyback

123

cefazoli

n 3

gram/10

0 ml in

0.9 %

sodium

chloride

intraven

ous

piggyba

heparin,

porcine

(pf) 10

unit/ml

intravenou

s syringe

esmolol

2,500

mg/250 ml

(10 mg/ml)

in sodium

chloride

(iso-

osmotic) iv

vecuroniu

m bromide

10 mg

intravenou

s solution

heparin

(porcine)

1,000

unit/500

ml in 0.9%

sodium

chloride iv

(combined

)

vecuroniu

m bromide

10 mg

intravenou

s solution

idazolam

5 mg/ml

(combined

) injection

solution

wrapper

cyclospori

ne 1 mg/ml

ns aviva iv

eptifibatide

0.75

mg/ml

intravenou

s solution

124

ceftriaxo

ne 2

gram/50

ml in

ceftriaxone

1 gram

solution

for

midazolam

(pf) 5

mg/ml

injection

cyclospori

ne 1 mg/ml

ns aviva iv

hydromorp

hone (pf) 1

mg/ml

injection

heparin

(porcine)

1,000

unit/500

pentobarbit

al sodium

50 mg/ml

injection

hydromorp

hone (pf) 1

mg/ml

injection

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

dextrose

(iso-

osmotic)

intraven

ous

piggyba

injection

solution

ml in 0.9%

sodium

chloride iv

(combined

)

solution

125

vancom

ycin

1.75

gram/50

0 ml in

0.9 %

sodium

chloride

intraven

ous

heparin

(porcine)

1,000

unit/500

ml in 0.9%

sodium

chloride iv

(combined

)

cefepime 2

gram

solution

for iv push'

ketamine

10 mg/ml

injection

solution

sodium

chloride 4

mEq/ml

intravenou

s solution

ceftriaxone

2 gram/50

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

cefepime 2

gram

solution

for iv push'

fentan yl

(sublimaze

) 100 mcg

in ns 50ml

(rex or)

126

heparin

(porcine

) 100

unit/ml

load

from

infusion

vecuroniu

m bromide

10 mg

intravenou

s solution

milrinone

20 mg/100

ml(200

mcg/ml) in

5 %

dextrose

intravenou

piggyback

heparin

(porcine)

100

unit/ml

load from

infusion

rocuroniu

m 10

mg/ml

intravenou

s solution

127

succinyl

choline

chloride

20mg/m

syringe/

vial

wrapper

cefepime 2

gram/100

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

rocuroniu

m 10

mg/ml

intravenou

s solution

ceftriaxone

1 gram/50

ml in

dextrose

(iso-

osmotic)

intravenou

piggyback

128

heparin

(porcine

) 1,000

unit/500

ml in

0.9%

sodium

chloride

(combin

ed)

midazolam

(pf) 5

mg/ml

injection

solution

129

famotidine

10 mg/ml

injection

solution

(multi-vial

size)

130

cefepime 2

gram

solution

for iv push'

N represents the number of individual medication administrations

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

Table

Distribution of medication classes within each medication cluster by total medication

administrations

Cluste

Medication Class

(N=498) 2

(N=561)

(N=532)

(N=517)

(N=539)

(N=574)

(N=540) 8

(N=518)

(N=526)

(N=532)

Analgesic

(N=7348) 15.46

14.62

16.73

15.28

15.21

13.76

15.00

15.25

14.45

13.35

Antiarrhythmic

(N=511) 3.61

5.35

6.02

4.64

5.38

3.83

4.81

5.02

5.70

5.26

Antibiotic

(N=2992)

21.89

18.72

19.74

18.18

20.73

19.0

18.15

19.96

20.11

Anticoagulant

(N=2915)

6.43

6.24

6.7

7.54

8.35

6.45

5.74

7.14

7.60

7.71

Anticonvulsants

(N=55)

3.21

1.96

1.50

1.74

1.86

1.05

1.85

1.74

1.52

1.13

Antifungal Agent

(N=29)

0.40

0.89

0.94

0.7

0.93

0.8

0.74

1.16

0.76

0.94

Antihypertensive

(N=1195)

2.61

2.32

2.82

2.51

2.41

4.18

3.33

2.70

2.85

3.57

Antiplatelet

(N=46)

1.00

0.71

0.38

0.39

0.74

0.52

0.74

0.39

0.95

0.38

Antifungal

(N=14)

1.00

0.71

0.75

1.35

0.3

0.35

0.56

0.19

0.00

0.38

Diabetic Agents

(N=16)

1.00

1.25

1.13

1.55

0.56

1.39

0.74

1.16

0.95

0.38

Diuretic

(N=)

0.20

0.36

0.19

0.56

0.52

0.93

0.19

0.38

Fluids

(N=10364)

10.44

14.80

12.59

15.09

14.29

12.37

12.41

11.78

13.88

11.65

Gastric Agent

(N=1494)

5.02

4.99

3.57

3.09

3.34

3.83

5.37

4.05

4.94

3.38

Hypertonic Saline

(N=230)

1.20

1.60

1.13

1.16

1.30

2.09

0.93

1.74

0.76

1.13

Inotropic Agent

(N=687)

3.21

3.92

3.38

4.06

2.04

3.66

3.70

2.90

2.28

3.01

Neuromuscular

blocking agents

(N=62)

1.41

1.25

1.13

0.9

0.74

0.8

0.93

1.16

1.52

1.88

Sedative

(N=8700)

13.25

11.94

11.28

10.64

11.69

11.85

13.15

13.90

11.79

14.10

Somatostatic

Agents

(N=11)

0.40

0.18

0.38

0.58

0.74

0.35

0.74

0.7

0.5

0.56

Total parenteral

nutrition

(N=59)

0.80

0.53

0.75

1.16

1.11

0.52

1.11

1.35

0.5

1.13

Vasopresso

(N= 8270)

7.43

7.31

8.27

9.09

10.02

10.45

7.22

9.27

8.3

9.21

Antidotes/Rescue

Therapy

0.00

0.18

0.19

0.00

0.1

0.3

0.00

0.19

0.00

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

(N=4)

Immunosuppressan

(N=4)

0.00

0.18

0.38

0.00

0.19

0.1

0.56

0.00

0.19

0.38

N represents the number of medication administrations, with each column summing up to 100%.

Table 3 Logistic Regressions for Incidence of Fluid Overload with Varying Proportions of

Medication Administrations Matching Cluster 7

Model

Logistic Regression for Fluid Overload with

APACHE II Score at 24 hours and Diuretic

Level

Estimated Value

P-value

Greater than 10% of Medication Administrations

Matching Cluster 7 0.68

0.00183

Greater than 15% of Medication Administrations

Matching Cluster 7 0.63

0.00481

Greater than 20% of Medication Administrations

Matching Cluster 7 -0.29

0.601

Greater than 30% of Medication Administrations

Matching Cluster 7 -16.2

0.9941

Table 4. Logistic Regressions for Prediction of Fluid Overload with/without Cluster 5

information

Model Logistic Regression for Fluid

Overload with APACHE II Score at

24 hours and Diuretic Level

Logistic Regression for Fluid Overload

with APACHE II Score at 24 hours,

Diuretic Level, and Proportion of

Medications Appearing in Cluster 5

Estimated

Value P-value Estimated Value P-value

(Intercept) -3.00 <0.0001 -3.42 <0.0001

APACHE Score at 24

hours 0.095 <0.0001 0.09343 <0.0001

Diuretic level (0-5) -0.46 0.04 -0.486 0.03

Diuretic level (>5) -17.25 0.98 -17.26 0.98

Proportion of

Medications Appearing

in Cluster 5

5.406 0.0007

Diuretic level 0-5: the patient received

≤

5 doses of a diuretic medication within the first 72 hours of

ICU stay

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

Diuretic level >5: the patient received >5 doses of a diuretic medication within the first 71 hours of

ICU stay

Figure 1. Consort Diagram of the Data Process Procedures

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

Figure 2. Cluster 7 medication administrations organized by timing of administration and

medication class

Black boxes indicate medication administration at specific time slots, while the width of column

indicates amount of medications appearing within that class within the cluster

Alternative version of Figure 6 from the main text

Figure 3. Cluster 7 medication administrations organized by timing of administration and

medication class with classes in alphabetical order

Black boxes indicate medication administration at specific time slots, while the width of column

indicates amount of medications appearing within that class within the cluster

Alternative version of Figure 6 from the main text

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

Figure 4. Logistic regression model for Cluster 5

Logistic regression for incidence of fluid overload, including Cluster 5, APACHE II score, and

diuretic level

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

Specificity (%)

Sensitivity (%)

120 100 80 60 40 20 0 −20

0 20406080100

AUC: 73.8%

AUC: 71.9%

AUC: 65.4%

ROC

line 1 = LR w/ APACHE II

line 2 = LR w/ APACHE II and diuretic

line 3 = LR w/ APACHE II diuretic cluster 5

. CC-BY-NC-ND 4.0 International licenseIt is made available under a

Does artificial intelligence close gaps in clinical pharmacology in the ICU?

Article

Dec 2024
INTENS CARE MED

Evaluation of medication regimen complexity as a predictor for mortality

Article

Full-text available

Jul 2023

While medication regimen complexity, as measured by a novel medication regimen complexity-intensive care unit (MRC-ICU) score, correlates with baseline severity of illness and mortality, whether the MRC-ICU improves hospital mortality prediction is not known. After characterizing the association between MRC-ICU, severity of illness and hospital mortality we sought to evaluate the incremental benefit of adding MRC-ICU to illness severity-based hospital mortality prediction models. This was a single-center, observational cohort study of adult intensive care units (ICUs). A random sample of 991 adults admitted ≥ 24 h to the ICU from 10/2015 to 10/2020 were included. The logistic regression models for the primary outcome of mortality were assessed via area under the receiver operating characteristic (AUROC). Medication regimen complexity was evaluated daily using the MRC-ICU. This previously validated index is a weighted summation of medications prescribed in the first 24 h of ICU stay [e.g., a patient prescribed insulin (1 point) and vancomycin (3 points) has a MRC-ICU = 4 points]. Baseline demographic features (e.g., age, sex, ICU type) were collected and severity of illness (based on worst values within the first 24 h of ICU admission) was characterized using both the Acute Physiology and Chronic Health Evaluation (APACHE II) and the Sequential Organ Failure Assessment (SOFA) score. Univariate analysis of 991 patients revealed every one-point increase in the average 24-h MRC-ICU score was associated with a 5% increase in hospital mortality [Odds Ratio (OR) 1.05, 95% confidence interval 1.02–1.08, p = 0.002]. The model including MRC-ICU, APACHE II and SOFA had a AUROC for mortality of 0.81 whereas the model including only APACHE-II and SOFA had a AUROC for mortality of 0.76. Medication regimen complexity is associated with increased hospital mortality. A prediction model including medication regimen complexity only modestly improves hospital mortality prediction.

Improving irregular temporal modeling by integrating synthetic data to the electronic medical record using conditional GANs: a case study of fluid overload prediction in the intensive care unit

Preprint

Full-text available

Jun 2023

Objective: The challenge of irregular temporal data, which is particularly prominent for medication use in the critically ill, limits the performance of predictive models. The purpose of this evaluation was to pilot test integrating synthetic data within an existing dataset of complex medication data to improve machine learning model prediction of fluid overload. Materials and Methods: This retrospective cohort study evaluated patients admitted to an ICU ≥ 72 hours. Four machine learning algorithms to predict fluid overload after 48-72 hours of ICU admission were developed using the original dataset. Then, two distinct synthetic data generation methodologies (synthetic minority over-sampling technique (SMOTE) and conditional tabular generative adversarial network (CTGAN)) were used to create synthetic data. Finally, a stacking ensemble technique designed to train a meta-learner was established. Models underwent training in three scenarios of varying qualities and quantities of datasets. Results: Training machine learning algorithms on the combined synthetic and original dataset overall increased the performance of the predictive models compared to training on the original dataset. The highest performing model was the meta-model trained on the combined dataset with 0.83 AUROC while it managed to significantly enhance the sensitivity across different training scenarios. Discussion: The integration of synthetically generated data is the first time such methods have been applied to ICU medication data and offers a promising solution to enhance the performance of machine learning models for fluid overload, which may be translated to other ICU outcomes. A meta-learner was able to make a trade-off between different performance metrics and improve the ability to identify the minority class.

Everything you need to know about deresuscitation

Article

Full-text available

Aug 2022

Early Diuretics for De-resuscitation in Septic Patients With Left Ventricular Dysfunction

Article

Full-text available

May 2022

Introduction De-resuscitation practices in septic patients with heart failure (HF) are not well characterized. This study aimed to determine if diuretic initiation within 48 hours of intensive care unit (ICU) admission was associated with a positive fluid balance and patient outcomes. Methods This single-center, retrospective cohort study included adult patients with an established diagnosis of HF admitted to the ICU with sepsis or septic shock. The primary outcome was the incidence of positive fluid balance in patients receiving early (<48 hours) versus late (>48 hours) initiation of diuresis. Secondary outcomes included hospital mortality, ventilator-free days, and hospital and ICU length of stay. Continuous variables were assessed using independent t-test or Mann-Whitney U, while categorical variables were evaluated using the Pearson Chi-squared test. Results A total of 101 patients were included. Positive fluid balance was significantly reduced at 72 hours (−139 mL vs 4370 mL, P < .001). The duration of mechanical ventilation (4 vs 5 days, P = .129), ventilator-free days (22 vs 18.5 days, P = .129), and in-hospital mortality (28 (38%) vs 12 (43%), P = .821) were similar between groups. In a subgroup analysis excluding patients not receiving renal replacement therap (RRT) (n = 76), early diuretics was associated with lower incidence of mechanical ventilation (41 [73.2%] vs 20 (100%), P = .01) and reduced duration of mechanical ventilation (4 vs 8 days, P = .018). Conclusions Diuretic use within 48 hours of ICU admission in septic patients with HF resulted in less incidence of positive fluid balance. Early diuresis in this unique patient population warrants further investigation.

Fluid Overload Phenotypes in Critical Illness—A Machine Learning Approach

Article

Full-text available

Jan 2022

Background: The detrimental impact of fluid overload (FO) on intensive care unit (ICU) morbidity and mortality is well known. However, research to identify subgroups of patients particularly prone to fluid overload is scarce. The aim of this cohort study was to derive "FO phenotypes" in the critically ill by using machine learning techniques. Methods: Retrospective single center study including adult intensive care patients with a length of stay of ≥3 days and sufficient data to compute FO. Data was analyzed by multivariable logistic regression, fast and frugal trees (FFT), classification decision trees (DT), and a random forest (RF) model. Results: Out of 1772 included patients, 387 (21.8%) met the FO definition. The random forest model had the highest area under the curve (AUC) (0.84, 95% CI 0.79-0.86), followed by multivariable logistic regression (0.81, 95% CI 0.77-0.86), FFT (0.75, 95% CI 0.69-0.79) and DT (0.73, 95% CI 0.68-0.78) to predict FO. The most important predictors identified in all models were lactate and bicarbonate at admission and postsurgical ICU admission. Sepsis/septic shock was identified as a risk factor in the MV and RF analysis. Conclusion: The FO phenotypes consist of patients admitted after surgery or with sepsis/septic shock with high lactate and low bicarbonate.

Machine learning vs. traditional regression analysis for fluid overload prediction in the ICU

Preprint

Jun 2023

Background Fluid overload, while common in the ICU and associated with serious sequelae, is hard to predict and may be influenced by ICU medication use. Machine learning (ML) approaches may offer advantages over traditional regression techniques to predict it. We compared the ability of traditional regression techniques and different ML-based modeling approaches to identify clinically meaningful fluid overload predictors. Methods This was a retrospective, observational cohort study of adult patients admitted to an ICU ≥ 72 hours between 10/1/2015 and 10/31/2020 with available fluid balance data. Models to predict fluid overload (a positive fluid balance ≥10% of the admission body weight) in the 48-72 hours after ICU admission were created. Potential patient and medication fluid overload predictor variables (n=28) were collected at either baseline or 24 hours after ICU admission. The optimal traditional logistic regression model was created using backward selection. Supervised, classification-based ML models were trained and optimized, including a meta-modeling approach. Area under the receiver operating characteristic (AUROC), positive predictive value (PPV), and negative predictive value (NPV) were compared between the traditional and ML fluid prediction models. Results A total of 49 of the 391 (12.5%) patients developed fluid overload. Among the ML models, the XGBoost model had the highest performance (AUROC 0.78, PPV 0.27, NPV 0.94) for fluid overload prediction. The XGBoost model performed similarly to the final traditional logistic regression model (AUROC 0.70; PPV 0.20, NPV 0.94). Feature importance analysis revealed severity of illness scores and medication-related data were the most important predictors of fluid overload. Conclusion In the context of our study, ML and traditional models appear to perform similarly to predict fluid overload in the ICU. Baseline severity of illness and ICU medication regimen complexity are important predictors of fluid overload.

From theory to bedside: Implementation of fluid stewardship in a medical ICU pharmacy practice

Article

Nov 2021

Purpose Intravenous fluids are the most commonly prescribed medication in the intensive care unit (ICU) and can have a negative impact on patient outcomes if not utilized properly. Fluid stewardship aims to heighten awareness and improve practice in fluid therapy. This report describes a practical construct for implementation of fluid stewardship services and characterizes the pharmacist’s role in fluid stewardship practice. Summary Fluid stewardship services were integrated into an adult medical ICU at a large community hospital. Data characterizing these services over a 2-year span are reported and categorized based on the 4 rights (right patient, right drug, right route, right dose) and the ROSE (rescue, optimization, stabilization, evacuation) model of fluid administration. The review encompassed 305 patients totaling 905 patient days for whom 2,597 pharmacist recommendations were made, 19% of which were related to fluid stewardship. This corresponded to an average of 1.52 fluid stewardship recommendations per patient. Within the construct of the 4 rights, 39% of recommendations were related to the right patient, 33% were related to the right route, 17% were related to the right drug, and 11% were related to the right dose. By the ROSE model, 1% of recommendations were related to the rescue phase, 3% were related to optimization, 79% were related to stabilization, and 17% were related to evacuation. Conclusion Implementation of fluid stewardship pharmacy services in a community hospital medical ICU is feasible. Integration of this practice contributed to 19% of pharmacy recommendations. The most common recommendations involved evaluation of the patient for the appropriateness of fluid therapy during the stabilization phase. The impact of fluid stewardship on patient outcomes needs to be explored.

Fluid Stewardship of Maintenance Intravenous Fluids

Article

Apr 2021

Despite the frequent use of maintenance intravenous fluids (mIVF) in critically ill patients, limited guidance is available. Notably, fluid overload secondary to mIVF mismanagement is associated with significant adverse patient outcomes. The Four Rights (right drug, right dose, right duration, right patient) construct of fluid stewardship has been proposed for the safe evaluation and use of fluids. The purpose of this evidence-based review is to offer practical insights for the clinician regarding mIVF selection, dosing, and duration in line with the Four Rights of Fluid Stewardship.

Medication Regimen Complexity Score as an Indicator of Fluid Balance in Critically Ill Patients

Article

Mar 2021

Background Critically ill patients are at increased risk for fluid overload, but objective prediction tools to guide clinical decision-making are lacking. The MRC-ICU scoring tool is an objective tool for measuring medication regimen complexity. Objective To evaluate the relationship between MRC-ICU score and fluid overload in critically ill patients. Methods In this multi-center, retrospective, observational study, the relationship between MRC-ICU and the risk of fluid overload was examined. Patient demographics, fluid balance at day 3 of ICU admission, MRC-ICU score at 24 hours, and clinical outcomes were collected from the medical record. The primary outcome was relationship between MRC-ICU and fluid overload. To analyze this, MRC-ICU scores were divided into tertiles (low, moderate, high), and binary logistic regression was performed. Linear regression was performed to determine variables associated with positive fluid balance. Results A total of 125 patients were included. The median MRC-ICU score at 24 hours of ICU admission for low, moderate, and high tertiles were 9, 15, and 21, respectively. For each point increase in MRC-ICU, a 13% increase in the likelihood of fluid overload was observed (OR 1.128, 95% CI 1.028-1.238, p = 0.011). The MRC-ICU score was positively associated with fluid balance at day 3 (β-coefficient 218.455, 95% CI 94.693-342.217, p = 0.001) when controlling for age, gender, and SOFA score. Conclusions Medication regimen complexity demonstrated a weakly positive correlation with fluid overload in critically ill patients. Future studies are necessary to establish the MRC-ICU as a predictor to identify patients at risk of fluid overload.

A narrative review of pharmacologic de-resuscitation in the critically ill

Article

Jul 2020
J CRIT CARE

Despite evidence highlighting harms of fluid overload, minimal guidance exists on counteraction via utilization of diuretics in the de-resuscitation phase. While diuretics have been shown to decrease net volume and improve clinical outcomes in the critically ill, a lack of standardization surrounding selection of diuretic regimen or monitoring of de-resuscitation exists. Current monitoring parameters of de-resuscitation often rely on clinical signs of fluid overload, end organ recovery and other biochemical surrogate markers which are often deemed unreliable. The majority of evidence suggests that achieving a net-negative fluid balance within 72 h after shock resolution may be of benefit; however, approaches to such goal are uncertain. Loop diuretics are a widely available type of diuretic for removal of volume in patients with sufficient kidney function, with the potential for adjunct diuretics in special circumstances. At present, administration of diuretics within the broad critically ill population fails to find uniformity and often efficacy. Given the lack of randomized controlled trials in this susceptible population, we aim to provide a thorough therapeutic understanding of diuretic pharmacotherapy which is necessary in order to achieve desired goal of fluid balance and improve overall outcomes.

Unsupervised machine learning analysis to identify patterns of ICU medication use for fluid overload prediction

Abstract

Recommended publications

Unsupervised machine learning analysis to identify patterns of ICU medication use for fluid overload...

Improving irregular temporal modeling by integrating synthetic data to the electronic medical record...

Machine learning vs. traditional regression analysis for fluid overload prediction in the ICU

Improving mixed-integer temporal modeling by generating synthetic data using conditional generative...