No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
A common data model for the standardization of intensive care unit medication features
Abstract
Objective
Common data models provide a standard means of describing data for artificial intelligence (AI) applications, but this process has never been undertaken for medications used in the intensive care unit (ICU). We sought to develop a common data model (CDM) for ICU medications to standardize the medication features needed to support future ICU AI efforts.
Materials and Methods
A 9-member, multi-professional team of ICU clinicians and AI experts conducted a 5-round modified Delphi process employing conference calls, web-based communication, and electronic surveys to define the most important medication features for AI efforts. Candidate ICU medication features were generated through group discussion and then independently scored by each team member based on relevance to ICU clinical decision-making and feasibility for collection and coding. A key consideration was to ensure the final ontology both distinguished unique medications and met Findable, Accessible, Interoperable, and Reusable (FAIR) guiding principles.
Results
Using a list of 889 ICU medications, the team initially generated 106 different medication features, and 71 were ranked as being core features for the CDM. Through this process, 106 medication features were assigned to 2 key feature domains: drug product-related (n = 43) and clinical practice-related (n = 63). Each feature included a standardized definition and suggested response values housed in the electronic data library. This CDM for ICU medications is available online.
Conclusion
The CDM for ICU medications represents an important first step for the research community focused on exploring how AI can improve patient outcomes and will require ongoing engagement and refinement.
... Established open-source common data models (CDMs), such as the Observational Medical Outcomes Partnership (OMOP) [12], address this data harmonization and standardization challenge for the entire EHR. While OMOP is capable of representing critical care data elements such as ventilator settings, infusion titrations, and mechanical circulatory support, these concepts are captured inconsistently-and often without granularity-across OMOP implementations, making multi-center critical care studies with OMOP extremely challenging [13][14][15][16]. ...
Critical illness threatens millions of lives annually. Electronic health record (EHR) data are a source of granular information that could generate crucial insights into the nature and optimal treatment of critical illness.
Overcome the data management, security, and standardization barriers to large-scale critical illness EHR studies.
We developed a Common Longitudinal Intensive Care Unit (ICU) data Format (CLIF), an open-source database format to harmonize EHR data necessary to study critical illness. We conducted proof-of-concept studies with a federated research architecture: (1) an external validation of an in-hospital mortality prediction model for critically ill patients and (2) an assessment of 72-h temperature trajectories and their association with mechanical ventilation and in-hospital mortality using group-based trajectory models.
We converted longitudinal data from 111,440 critically ill patient admissions from 2020 to 2021 (mean age 60.7 years [standard deviation 17.1], 31% Black, 6% Hispanic, 44% female) across 9 health systems and 38 hospitals into CLIF databases. The in-hospital mortality prediction model had varying performance across CLIF consortium sites (AUCs: 0.73–0.81, Brier scores: 0.06–0.10) with degradation in performance relative to the derivation site. Temperature trajectories were similar across health systems. Hypothermic and hyperthermic-slow-resolver patients consistently had the highest mortality.
CLIF enables transparent, efficient, and reproducible critical care research across diverse health systems. Our federated case studies showcase CLIF’s potential for disease sub-phenotyping and clinical decision-support evaluation. Future applications include pragmatic EHR-based trials, target trial emulations, foundational artificial intelligence (AI) models of critical illness, and real-time critical care quality dashboards.
... The Observational Medical Outcomes Partnership (OMOP) has previously created a common data model (CDM) that would allow for incorporation of medication information into AI models; however, this model is fairly limited in scope (including mostly basic information such as drug name and formulation) [62]. However, recently the ICURx CDM has been developed and contains many more drug features including efficacy and safety that can now be used in AI models [63]. While the application of the ICURx CDM is limited at this time due to its recent development, this poses a great opportunity for advancement of sleep medicine as now medications can be more thoroughly described within the AI model and patterns related to their use, adverse reactions, and efficacy and safety may be developed. ...
Purpose of Review
Sleep medicine focuses on diagnosing and managing disorders like obstructive sleep apnea (OSA), which affects nearly one billion people worldwide, yet remains underdiagnosed in many cases. This review explores how artificial intelligence (AI) and machine learning (ML) can address these gaps by improving diagnostic tools, enhancing treatment strategies, and advancing patient outcomes. We also examine key challenges, including data privacy concerns, algorithmic bias, and the lack of standardized methods for integrating AI into clinical practice, while highlighting recent advancements and the evolving role of AI in sleep healthcare.
Recent Findings
Recent advancements in AI for sleep medicine include the use of deep learning models for automated sleep stage classification, wearable devices for real-time sleep monitoring, and AI-powered tools that increase the accuracy of home testing for disorders like OSA. ML algorithms enhance diagnostic accuracy by analyzing large datasets to identify patterns that traditional methods might miss. These advancements also enable more precise endotyping, allowing tailored treatment based on specific physiological drivers of sleep disorders, such as airway collapsibility or ventilatory control abnormalities. In the realm of pharmacology, AI is also helping predict drug efficacy, repurpose existing medications for sleep-related disorders, and explore how genetic variations influence individual responses to treatment. These innovations offer new opportunities for personalized medicine in sleep healthcare.
Summary
AI holds immense promise in revolutionizing sleep medicine by refining diagnostic tools, optimizing management protocols, and reducing healthcare costs. Recent advancements, such as deep learning models for sleep stage classification, wearable devices for real-time monitoring, and AI-driven pharmacological insights, highlight its potential to transform patient care. Addressing the challenges of data standardization, ethical implementation, and clinician education will be critical to unlocking its full potential. With continued advancements, AI can provide more personalized and efficient care, improving outcomes for patients with sleep-related disorders.
Objectives
This study aimed to establish a set of guiding principles for data sharing and harmonization in critical care, focusing on the use of real-world data (RWD) and real-world evidence (RWE) to improve patient outcomes and research efficacy. The principles were developed through a systematic literature review and a modified Delphi process, with the goal of enhancing data accessibility, standardization, and interoperability across critical care settings.
Data Sources
Data sources included a comprehensive search of peer-reviewed literature, specifically studies related to the use of RWD and RWE in healthcare, guidelines, best practices, and recommendations on data sharing and harmonization. A total of 8150 articles were initially identified through databases such as MEDLINE and Web of Science, with 257 studies meeting inclusion criteria.
Study Selection
Inclusion criteria focused on publications discussing health-related informatics, recommendations for RWD/RWE usage, data sharing, and harmonization principles. Exclusion criteria ruled out non-human studies, case studies, conference abstracts, and articles published before 2013, as well as those not available in English.
Data Extraction
From the 257 selected studies, 322 statements were extracted. After removing irrelevant definitions and off-topic content, 232 statements underwent content validation and thematic analysis. These statements were then consolidated into 24 candidate guiding principles after rigorous review and consensus-building among the expert panel.
Data Synthesis
A three-phase modified Delphi process was employed, involving a conceptualization group, a review group, and a Delphi group. In phase 1, experts identified key themes and search terms for the systematic review. Phase 2 involved validating and refining the prospective guiding principles, while phase 3 employed a Delphi panel to rate principles on acceptability, importance, and feasibility. This process resulted in 24 guiding principles, with high consensus achieved in rounds 2 and 3 on their relevance and applicability.
Conclusions
The systematic review and Delphi process resulted in 24 guiding principles to improve data sharing and harmonization in critical care. These principles address challenges across the data lifecycle, including generation, storage, access, and usage of RWD and RWE. This framework is designed to promote more effective and equitable data practices, with relevance for the development of artificial intelligence-based decision support tools and clinical research. The principles are intended to guide the responsible use of data science in critical care, with emphasis on ethics and equity, while acknowledging the variability of resources across settings.
Background
Fluid overload (FO) in the intensive care unit (ICU) is common, serious, and may be preventable. Intravenous medications (including administered volume) are a primary cause for FO but are challenging to evaluate as a FO predictor given the high frequency and time‐dependency of their use and other factors affecting FO. We sought to employ unsupervised machine learning methods to uncover medication administration patterns correlating with FO.
Methods
This retrospective cohort study included 927 adults admitted to an ICU for ≥72 h. FO was defined as a positive fluid balance ≥7% of admission body weight. After reviewing medication administration record data in 3‐h periods, 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 their temporal association with FO.
Results
FO occurred in 127 (13.7%) of 927 included patients. Patients received a median (interquartile range) of 31(13–65) discrete intravenous medication administrations over the 72‐h period. Across all 47,803 intravenous medication administrations, 10 unique medication clusters, containing 121 to 130 medications per cluster, were identified. The mean number of Cluster 7 medications administered was significantly greater in the FO cohort compared with patients without FO (25.6 vs.10.9, p < 0.0001). A total of 51 (40.2%) of 127 unique Cluster 7 medications were administered in more than five different 3‐h periods during the 72‐h study window. The most common Cluster 7 medications included continuous infusions, antibiotics, and sedatives/analgesics. Addition of Cluster 7 medications to an FO prediction model including the Acute Physiologic and Chronic Health Evaluation (APACHE) II score and receipt of diuretics improved model predictiveness from an Area Under the Receiver Operation Characteristic (AUROC) curve of 0.719 to 0.741 ( p = 0.027).
Conclusions
Using machine learning approaches, a unique medication cluster was strongly associated with FO. Incorporation of this cluster improved the ability to predict FO compared to traditional prediction models. Integration of this approach into real‐time clinical applications may improve early detection of FO to facilitate timely intervention.
Objectives
To provide guidance on the reporting of norepinephrine formulation labeling, reporting in publications, and use in clinical practice.
Design
Review and task force position statements with necessary guidance.
Setting
A series of group conference calls were conducted from August 2023 to October 2023, along with a review of the available evidence and scope of the problem.
Subjects
A task force of multinational and multidisciplinary critical care experts assembled by the Society of Critical Care Medicine and the European Society of Intensive Care Medicine.
Interventions
The implications of a variation in norepinephrine labeled as conjugated salt (i.e., bitartrate or tartrate) or base drug in terms of effective concentration of norepinephrine were examined, and guidance was provided.
Measurements and Main Results
There were significant implications for clinical care, dose calculations for enrollment in clinical trials, and results of datasets reporting maximal norepinephrine equivalents. These differences were especially important in the setting of collaborative efforts across countries with reported differences.
Conclusions
A joint task force position statement was created outlining the scope of norepinephrine-dose formulation variations, and implications for research, patient safety, and clinical care. The task force advocated for a uniform norepinephrine-base formulation for global use, and offered advice aimed at appropriate stakeholders.
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. This was a retrospective, observational cohort study of adult patients admitted to an ICU ≥ 72 h 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 h after ICU admission were created. Potential patient and medication fluid overload predictor variables (n = 28) were collected at either baseline or 24 h 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. 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. 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.
Rationale
Duration of mechanical ventilation is associated with adverse outcomes in critically ill patients and increased use of resources. The increasing complexity of medication regimens has been associated with increased mortality, length of stay, and fluid overload but has never been studied specifically in the setting of mechanical ventilation.
Objective
The purpose of this analysis was to develop prediction models for mechanical ventilation duration to test the hypothesis that incorporating medication data may improve model performance.
Methods
This was a retrospective cohort study of adults admitted to the ICU and undergoing mechanical ventilation for longer than 24 hours from October 2015 to October 2020. Patients were excluded if it was not their index ICU admission or if the patient was placed on comfort care in the first 24 hours of admission. Relevant patient characteristics including age, sex, body mass index, admission diagnosis, morbidities, vital signs measurements, severity of illness, medication regimen complexity as measured by the MRC-ICU, and medical treatments before intubation were collected. The primary outcome was area under the receiver operating characteristic (AUROC) of prediction models for prolonged mechanical ventilation (defined as greater than 5 days). Both logistic regression and supervised learning techniques including XGBoost, Random Forest, and Support Vector Machine were used to develop prediction models.
Results
The 318 patients [age 59.9 (SD 16.9), female 39.3%, medical 28.6%] had mean 24-hour MRC-ICU score of 21.3 (10.5), mean APACHE II score of 21.0 (5.4), mean SOFA score of 9.9 (3.3), and ICU mortality rate of 22.6% (n=72). The strongest performing logistic model was the base model with MRC-ICU added, with AUROC of 0.72, positive predictive value (PPV) of 0.83, and negative prediction value (NPV) of 0.92. The strongest overall model was Random Forest with an AUROC of 0.78, a PPV of 0.53, and NPV of 0.90. Feature importance analysis using support vector machine and Random Forest revealed severity of illness scores and medication related data were the most important predictors.
Conclusions
Medication regimen complexity is significantly associated with prolonged duration of mechanical ventilation in critically ill patients, and prediction models incorporating medication information showed modest improvement in this prediction.
Unsupervised clustering of intensive care unit (ICU) medications may identify unique medication clusters (i.e., pharmacophenotypes) in critically ill adults. We performed an unsupervised analysis with Restricted Boltzmann Machine of 991 medications profiles of patients managed in the ICU to explore pharmacophenotypes that correlated with ICU complications (e.g., mechanical ventilation) and patient-centered outcomes (e.g., length of stay, mortality). Six unique pharmacophenotypes were observed, with unique medication profiles and clinically relevant differences in ICU complications and patient-centered outcomes. While pharmacophenotypes 2 and 4 had no statistically significant difference in ICU length of stay, duration of mechanical ventilation, or duration of vasopressor use, their mortality differed significantly (9.0% vs. 21.9%, p < 0.0001). Pharmacophenotype 4 had a mortality rate of 21.9%, compared with the rest of the pharmacophenotypes ranging from 2.5 to 9%. Phenotyping approaches have shown promise in classifying the heterogenous syndromes of critical illness to predict treatment response and guide clinical decision support systems but have never included comprehensive medication information. This first-ever machine learning approach revealed differences among empirically-derived subgroups of ICU patients that are not typically revealed by traditional classifiers. Identification of pharmacophenotypes may enable enhanced decision making to optimize treatment decisions.
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.
Background
Identifying patterns within ICU medication regimens may help artificial intelligence algorithms to better predict patient outcomes; however, machine learning methods incorporating medications require further development, including standardized terminology. The Common Data Model for Intensive Care Unit (ICU) Medications (CDM-ICURx) may provide important infrastructure to clinicians and researchers to support artificial intelligence analysis of medication-related outcomes and healthcare costs. Using an unsupervised cluster analysis approach in combination with this common data model, the objective of this evaluation was to identify novel patterns of medication clusters (termed ‘pharmacophenotypes’) correlated with ICU adverse events (e.g., fluid overload) and patient-centered outcomes (e.g., mortality).
Methods
This was a retrospective, observational cohort study of 991 critically ill adults. To identify pharmacophenotypes, unsupervised machine learning analysis with automated feature learning using restricted Boltzmann machine and hierarchical clustering was performed on the medication administration records of each patient during the first 24 h of their ICU stay. Hierarchical agglomerative clustering was applied to identify unique patient clusters. Distributions of medications across pharmacophenotypes were described, and differences among patient clusters were compared using signed rank tests and Fisher's exact tests, as appropriate.
Results
A total of 30,550 medication orders for the 991 patients were analyzed; five unique patient clusters and six unique pharmacophenotypes were identified. For patient outcomes, compared to patients in Clusters 1 and 3, patients in Cluster 5 had a significantly shorter duration of mechanical ventilation and ICU length of stay ( p < 0.05); for medications, Cluster 5 had a higher distribution of Pharmacophenotype 1 and a smaller distribution of Pharmacophenotype 2, compared to Clusters 1 and 3. For outcomes, patients in Cluster 2, despite having the highest severity of illness and greatest medication regimen complexity, had the lowest overall mortality; for medications, Cluster 2 also had a comparably higher distribution of Pharmacophenotype 6.
Conclusion
The results of this evaluation suggest that patterns among patient clusters and medication regimens may be observed using empiric methods of unsupervised machine learning in combination with a common data model. These results have potential because while phenotyping approaches have been used to classify heterogenous syndromes in critical illness to better define treatment response, the entire medication administration record has not been incorporated in those analyses. Applying knowledge of these patterns at the bedside requires further algorithm development and clinical application but may have the future potential to be leveraged in guiding medication-related decision making to improve treatment outcomes.
Background:
Medication Regimen Complexity (MRC) refers to the combination of medication classes, dosages, and frequencies. The objective of this study was to examine the relationship between the scores of different MRC tools and the clinical outcomes.
Methods:
We conducted a retrospective cohort study at Roger William Medical Center, Providence, Rhode Island, which included 317 adult patients admitted to the intensive care unit (ICU) between 1 February 2020 and 30 August 2020. MRC was assessed using the MRC Index (MRCI) and MRC for the Intensive Care Unit (MRC-ICU). A multivariable logistic regression model was used to identify associations among MRC scores, clinical outcomes, and a logistic classifier to predict clinical outcomes.
Results:
Higher MRC scores were associated with increased mortality, a longer ICU length of stay (LOS), and the need for mechanical ventilation (MV). MRC-ICU scores at 24 h were significantly (p < 0.001) associated with increased ICU mortality, LOS, and MV, with ORs of 1.12 (95% CI: 1.06-1.19), 1.17 (1.1-1.24), and 1.21 (1.14-1.29), respectively. Mortality prediction was similar using both scoring tools (AUC: 0.88 [0.75-0.97] vs. 0.88 [0.76-0.97]. The model with 15 medication classes outperformed others in predicting the ICU LOS and the need for MV with AUCs of 0.82 (0.71-0.93) and 0.87 (0.77-0.96), respectively.
Conclusion:
Our results demonstrated that both MRC scores were associated with poorer clinical outcomes. The incorporation of MRC scores in real-time therapeutic decision making can aid clinicians to prescribe safer alternatives.
This article is one of ten reviews selected from the Annual Update in Intensive Care and Emergency Medicine 2022. Other selected articles can be found online at https://www.biomedcentral.com/collections/annualupdate2022. Further information about the Annual Update in Intensive Care and Emergency Medicine is available from https://link.springer.com/bookseries/8901.
IMPORTANCE:. Altered heart rate variability has been associated with autonomic dysfunction in a number of disease profiles, in this work we elucidate differences in the biomarker among patients with all-cause sepsis and coronavirus disease 2019.
OBJECTIVES:. To measure heart rate variability metrics in critically ill coronavirus disease 2019 patients with comparison to all-cause critically ill sepsis patients.
DESIGN, SETTING, AND PARTICIPANTS:. Retrospective analysis of coronavirus disease 2019 patients admitted to an ICU for at least 24 hours at any of Emory Healthcare ICUs between March 2020 and April 2020 up to 5 days of ICU stay. The comparison group was a cohort of all-cause sepsis patients prior to coronavirus disease 2019 pandemic.
MAIN OUTCOMES AND MEASURES:. Continuous waveforms were captured from the patient monitor. The electrocardiogram was then analyzed for each patient over a 300 seconds observational window that was shifted by 30 seconds in each iteration from admission till discharge. A total of 23 heart rate variability metrics were extracted in each iteration. We use the Kruskal-Wallis and Steel-Dwass tests (p < 0.05) for statistical analysis and interpretations of heart rate variability multiple measures.
RESULTS:. A total of 141 critically ill coronavirus disease 2019 patients met inclusion criteria, who were compared with 208 patients with all-cause sepsis. Three nonlinear markers, including the ratio of standard deviation derived from the Poincaré plot, sample entropy, and approximate entropy and four linear features, including mode of beat-to-beat interval, acceleration capacity, deceleration capacity, and the proportion of consecutive RR intervals that differ by more than 50 ms, were all statistically significant (p < 0.05) between the coronavirus disease 2019 and all-cause sepsis cohorts. The three nonlinear features and acceleration capacity, deceleration capacity, and beat-to-beat interval (mode) were statistically significant (p < 0.05) when comparing pairwise analysis among the combinations of survivors and nonsurvivors between the coronavirus disease 2019 and sepsis cohorts. Temporal analysis of the main markers showed low variability across the 5 days of analysis compared with sepsis patients.
CONCLUSIONS AND RELEVANCE:. In this descriptive statistical study, heart rate variability measures were found to be statistically different across critically ill patients infected with severe acute respiratory syndrome coronavirus 2 and distinct from bacterial sepsis.
Hierarchal clustering of amino acid metabolites may identify a metabolic signature in children with pediatric acute hypoxemic respiratory failure. Seventy-four immunocompetent children, 41 (55.4%) with pediatric acute respiratory distress syndrome (PARDS), who were between 2 days to 18 years of age and within 72 h of intubation for acute hypoxemic respiratory failure, were enrolled. We used hierarchal clustering and partial least squares-discriminant analysis to profile the tracheal aspirate airway fluid using quantitative LC–MS/MS to explore clusters of metabolites that correlated with acute hypoxemia severity and ventilator-free days. Three clusters of children that differed by severity of hypoxemia and ventilator-free days were identified. Quantitative pathway enrichment analysis showed that cysteine and methionine metabolism, selenocompound metabolism, glycine, serine and threonine metabolism, arginine biosynthesis, and valine, leucine, and isoleucine biosynthesis were the top five enriched, impactful pathways. We identified three clusters of amino acid metabolites found in the airway fluid of intubated children important to acute hypoxemia severity that correlated with ventilator-free days < 21 days. Further studies are needed to validate our findings and to test our models.
We present an interpretable machine learning algorithm called ‘eARDS’ for predicting ARDS in an ICU population comprising COVID-19 patients, up to 12-hours before satisfying the Berlin clinical criteria. The analysis was conducted on data collected from the Intensive care units (ICU) at Emory Healthcare, Atlanta, GA and University of Tennessee Health Science Center, Memphis, TN and the Cerner® Health Facts Deidentified Database, a multi-site COVID-19 EMR database. The participants in the analysis consisted of adults over 18 years of age. Clinical data from 35,804 patients who developed ARDS and controls were used to generate predictive models that identify risk for ARDS onset up to 12-hours before satisfying the Berlin criteria. We identified salient features from the electronic medical record that predicted respiratory failure among this population. The machine learning algorithm which provided the best performance exhibited AUROC of 0.89 (95% CI = 0.88–0.90), sensitivity of 0.77 (95% CI = 0.75–0.78), specificity 0.85 (95% CI = 085–0.86). Validation performance across two separate health systems (comprising 899 COVID-19 patients) exhibited AUROC of 0.82 (0.81–0.83) and 0.89 (0.87, 0.90). Important features for prediction of ARDS included minimum oxygen saturation (SpO2), standard deviation of the systolic blood pressure (SBP), O2 flow, and maximum respiratory rate over an observational window of 16-hours. Analyzing the performance of the model across various cohorts indicates that the model performed best among a younger age group (18–40) (AUROC = 0.93 [0.92–0.94]), compared to an older age group (80+) (AUROC = 0.81 [0.81–0.82]). The model performance was comparable on both male and female groups, but performed significantly better on the severe ARDS group compared to the mild and moderate groups. The eARDS system demonstrated robust performance for predicting COVID19 patients who developed ARDS at least 12-hours before the Berlin clinical criteria, across two independent health systems.
Objective:
Specific factors affecting generalizability of clinical prediction models are poorly understood. Our main objective was to investigate how measurement indicator variables affect external validity in clinical prediction models for predicting onset of vasopressor therapy.
Design:
We fit logistic regressions on retrospective cohorts to predict vasopressor onset using two classes of variables: seemingly objective clinical variables (vital signs and laboratory measurements) and more subjective variables denoting recency of measurements.
Setting:
Three cohorts from two tertiary-care academic hospitals in geographically distinct regions, spanning general inpatient and critical care settings.
Patients:
Each cohort consisted of adult patients (age greater than or equal to 18 yr at time of hospitalization), with lengths of stay between 6 and 600 hours, and who did not receive vasopressors in the first 6 hours of hospitalization or ICU admission. Models were developed on each of the three derivation cohorts and validated internally on the derivation cohort and externally on the other two cohorts.
Interventions:
None.
Measurements and main results:
The prevalence of vasopressors was 0.9% in the general inpatient cohort and 12.4% and 11.5% in the two critical care cohorts. Models utilizing both classes of variables performed the best in-sample, with C-statistics for predicting vasopressor onset in 4 hours of 0.862 (95% CI, 0.844-0.879), 0.822 (95% CI, 0.793-0.852), and 0.889 (95% CI, 0.880-0.898). Models solely using the subjective variables denoting measurement recency had poor external validity. However, these practice-driven variables helped adjust for differences between the two hospitals and led to more generalizable models using clinical variables.
Conclusions:
We developed and externally validated models for predicting the onset of vasopressors. We found that practice-specific features denoting measurement recency improved local performance and also led to more generalizable models if they are adjusted for during model development but discarded at validation. The role of practice-specific features such as measurement indicators in clinical prediction modeling should be carefully considered if the goal is to develop generalizable models.
Background
Standardized collection of predictors of pediatric sepsis has enormous potential to increase data compatibility across research studies. The Pediatric Sepsis Predictor Standardization Working Group collaborated to define common data elements for pediatric sepsis predictors at the point of triage to serve as a standardized framework for data collection in resource-limited settings.
Methods
A preliminary list of pediatric sepsis predictor variables was compiled through a systematic literature review and examination of global guideline documents. A 5-round modified Delphi that involved independent voting and active group discussions was conducted to select, standardize, and prioritize predictors. Considerations included the perceived predictive value of the candidate predictor at the point of triage, intra- and inter-rater measurement reliability, and the amount of time and material resources required to reliably collect the predictor in resource-limited settings.
Results
We generated 116 common data elements for implementation in future studies. Each common data element includes a standardized prompt, suggested response values, and prioritization as tier 1 (essential), tier 2 (important), or tier 3 (exploratory). Branching logic was added to the predictors list to facilitate the design of efficient data collection methods, such as low-cost electronic case report forms on a mobile application. The set of common data elements are freely available on the Pediatric Sepsis CoLab Dataverse and a web-based feedback survey is available through the Pediatric Sepsis CoLab. Updated iterations will continuously be released based on feedback from the pediatric sepsis research community and emergence of new information.
Conclusion
Routine use of the common data elements in future studies can allow data sharing between studies and contribute to development of powerful risk prediction algorithms. These algorithms may then be used to support clinical decision making at triage in resource-limited settings. Continued collaboration, engagement, and feedback from the pediatric sepsis research community will be important to ensure the common data elements remain applicable across a broad range of geographical and sociocultural settings.
Background:
Sepsis is a life-threatening condition with high mortality rates. Early detection and treatment are critical to improving outcomes. Our primary objective was to develop artificial intelligence capable of predicting sepsis earlier using a minimal set of streaming physiological data in real-time.
Methods and findings:
A total of 29,552 adult patients were admitted to the intensive care unit across five regional hospitals in Memphis, TN over 18 months from January 2017 to July 2018. From these, 5,958 patients were selected after filtering for continuous (minute-by-minute) physiological data availability. A total of 617 (10.4%) patients were identified as sepsis cases, using the Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3) criteria. Physiomarkers, a set of signal processing features, were derived from five physiological data streams including heart rate, respiratory rate, and blood pressure (systolic, diastolic, and mean), captured every minute from the bedside monitors. A support vector machine (SVM) classifier was used for classification. The model accurately predicted sepsis up to a mean and 95% confidence interval of 17.4 ± 0.22 hours before sepsis onset, with an average test accuracy of 83.0% (average sensitivity, specificity, and area under the receiver operating characteristics curve of 0.757, 0.902, and 0.781, respectively).
Conclusions:
This study demonstrates that salient physiomarkers derived from continuous bedside monitoring are temporally and differentially expressed in septic patients. Using this information, minimalistic artificial intelligence models can be developed to predict sepsis earlier in critically ill patients.
AI is the latest technologic trend that likely will have a huge impact in medicine. AI’s potential lies in its ability to process large volumes of data and perform complex pattern analyses. The ICU is an area of medicine that is particularly conducive to AI applications. Much AI ICU research currently is focused on improving high volumes of data on high-risk patients and making clinical workflow more efficient. Emerging topics of AI medicine in the ICU include AI sensors, sepsis prediction, AI in the NICU or SICU, and the legal role of AI in medicine. This review will cover the current applications of AI medicine in the ICU, potential pitfalls, and other AI medicine-related topics relevant for the ICU.
Sepsis is not a monolithic disease, but a loose collection of symptoms with diverse outcomes. Thus, stratification and subtyping of sepsis patients is of great importance. We examine the temporal evolution of patient state using our previously-published method for computing risk of transition from sepsis into septic shock. Risk trajectories diverge into four clusters following early prediction of septic shock, stratifying by outcome: the highest-risk and lowest-risk groups have a 76.5% and 10.4% prevalence of septic shock, and 43% and 18% mortality, respectively. These clusters differ also in treatments received and median time to shock onset. Analyses reveal the existence of a rapid (30-60 min) transition in risk at the time of threshold crossing. We hypothesize that this transition occurs as a result of the failure of compensatory biological systems to cope with infection, resulting in a bifurcation of low to high risk. Such a collapse, we believe, represents the true onset of septic shock. Thus, this rapid elevation in risk represents a potential new data-driven definition of septic shock.
Intensive-care clinicians are presented with large quantities of measurements from multiple monitoring systems. The limited ability of humans to process complex information hinders early recognition of patient deterioration, and high numbers of monitoring alarms lead to alarm fatigue. We used machine learning to develop an early-warning system that integrates measurements from multiple organ systems using a high-resolution database with 240 patient-years of data. It predicts 90% of circulatory-failure events in the test set, with 82% identified more than 2 h in advance, resulting in an area under the receiver operating characteristic curve of 0.94 and an area under the precision-recall curve of 0.63. On average, the system raises 0.05 alarms per patient and hour. The model was externally validated in an independent patient cohort. Our model provides early identification of patients at risk for circulatory failure with a much lower false-alarm rate than conventional threshold-based systems. A machine-learning algorithm based on an array of demographic, physiological and clinical information is able to predict, hours in advance, circulatory failure of patients in the intensive-care unit.
Background:
Patients presenting to the healthcare system with rotator cuff pathology do not always receive high quality care. High quality care occurs when a patient receives care that is accessible, appropriate, acceptable, effective, efficient, and safe. The aim of this study was twofold: 1) to develop a clinical pathway algorithm that sets forth a stepwise process for making decisions about the diagnosis and treatment of rotator cuff pathology presenting to primary, secondary, and tertiary healthcare settings; and 2) to establish clinical practice guidelines for the diagnosis and treatment of rotator cuff pathology to inform decision-making processes within the algorithm.
Methods:
A three-step modified Delphi method was used to establish consensus. Fourteen experts representing athletic therapy, physiotherapy, sport medicine, and orthopaedic surgery were invited to participate as the expert panel. In round 1, 123 best practice statements were distributed to the panel. Panel members were asked to mark "agree" or "disagree" beside each statement, and provide comments. The same voting method was again used for round 2. Round 3 consisted of a final face-to-face meeting.
Results:
In round 1, statements were grouped and reduced to 44 statements that met consensus. In round 2, five statements reached consensus. In round 3, ten statements reached consensus. Consensus was reached for 59 statements representing five domains: screening, diagnosis, physical examination, investigations, and treatment. The final face-to-face meeting was also used to develop clinical pathway algorithms (i.e., clinical care pathways) for three types of rotator cuff pathology: acute, chronic, and acute-on-chronic.
Conclusion:
This consensus guideline will help to standardize care, provide guidance on the diagnosis and treatment of rotator cuff pathology, and assist in clinical decision-making for all healthcare professionals.
There is an urgent need to improve the infrastructure supporting the reuse of scholarly data. A diverse set of stakeholders—representing academia, industry, funding agencies, and scholarly publishers—have come together to design and jointly endorse a concise and measureable set of principles that we refer to as the FAIR Data Principles. The intent is that these may act as a guideline for those wishing to enhance the reusability of their data holdings. Distinct from peer initiatives that focus on the human scholar, the FAIR Principles put specific emphasis on enhancing the ability of machines to automatically find and use the data, in addition to supporting its reuse by individuals. This Comment is the first formal publication of the FAIR Principles, and includes the rationale behind them, and some exemplar implementations in the community.
PHAR-QA, funded by the European Commission, is producing a framework of competences for pharmacy practice. The framework is in line with the EU directive on sectoral professions and takes into account the diversity of the pharmacy profession and the on-going changes in healthcare systems (with an increasingly important role for pharmacists), and in the pharmaceutical industry. PHAR-QA is asking academia, students and practicing pharmacists to rank competences required for practice. The results show that competences in the areas of “drug interactions”, “need for drug treatment” and “provision of information and service” were ranked highest whereas those in the areas of “ability to design and conduct research” and “development and production of medicines” were ranked lower. For the latter two categories, industrial pharmacists ranked them higher than did the other five groups.
Abstract
Introduction: Due to the importance of prolonged mechanical ventilation (PMV) as a postoperative complication, predicting “high-risk” patients by identifying predisposing risk factors is of important issue. The present study was aimed to identify perioperative variables associated with PMV in patients undergoing open heart surgery.Methods: A total of 743 consecutive patients, American Society of Anesthesiologists (ASA)physical status class III, who were scheduled to undergo open heart surgery using cardiopulmonary bypass were included in this observational study. Perioperative variables were compared between the patients with and without PMV, as defined by an extubation time of >48 h.Results: PMV occurred in 45 (6.1%) patients. On univariate analysis, pre-operative variables;including gender, history of chronic obstructive pulmonary disease (COPD); chronic kidney disease and endocarditis, intra-operative variables; including type of surgery, operation time,pump time, transfusion in operating room and postoperative variables; including bleeding andinotrope-dependency were significantly different between patients with and without PMV (all P<0.001, except for COPD and transfusion in operating room; P=0.004 and P=0.017, respectively).Conclusion: Our findings reinforce that risk stratification for predicting delayed extubation should be an important aspect of preoperative clinical evaluation in all anesthesiology settings.
Key performance indicators (KPIs) are quantifiable measures of quality. There are no published, systematically derived clinical pharmacy KPIs (cpKPIs).
A group of hospital pharmacists aimed to develop national cpKPIs to advance clinical pharmacy practice and improve patient care.
A cpKPI working group established a cpKPI definition, 8 evidence-derived cpKPI critical activity areas, 26 candidate cpKPIs, and 11 cpKPI ideal attributes in addition to 1 overall consensus criterion. Twenty-six clinical pharmacists and hospital pharmacy leaders participated in an internet-based 3-round modified Delphi survey. Panelists rated 26 candidate cpKPIs using 11 cpKPI ideal attributes and 1 overall consensus criterion on a 9-point Likert scale. A meeting was facilitated between rounds 2 and 3 to debate the merits and wording of candidate cpKPIs. Consensus was reached if 75% or more of panelists assigned a score of 7 to 9 on the consensus criterion during the third Delphi round.
All panelists completed the 3 Delphi rounds, and 25/26 (96%) attended the meeting. Eight candidate cpKPIs met the consensus definition: (1) performing admission medication reconciliation (including best-possible medication history), (2) participating in interprofessional patient care rounds, (3) completing pharmaceutical care plans, (4) resolving drug therapy problems, (5) providing in-person disease and medication education to patients, (6) providing discharge patient medication education, (7) performing discharge medication reconciliation, and (8) providing bundled, proactive direct patient care activities.
A Delphi panel of hospital pharmacists was successful in determining 8 consensus cpKPIs. Measurement and assessment of these cpKPIs will serve to advance clinical pharmacy practice and improve patient care.
© The Author(s) 2015.
Pharmacists' access to user-friendly electronic drug information databases that can quickly provide accurate, up-to-date information has become increasingly important. Unfortunately, decisions about purchasing subscriptions to such services are not always made objectively. Previously published studies have compared drug information databases, but there are no recent analyses from the perspective of Canadian hospital pharmacists.
To determine overall preferences among the most commonly used online drug information databases, based on an appraisal of the quality, performance, and usability of the databases and users' preferences.
Qualitative and quantitative analyses with descriptive and inferential statistics were used to compare the Clinical Pharmacology, Lexi-Comp Online, and Micromedex databases. Quality scores were determined from investigators' consensus ratings across 5 categories of quality indicators. Performance scores were determined according to the ability of a database to answer 15 clinical drug information questions. Usability scores were determined from user ratings in 7 domains. Users' preferences were assessed through rankings of the databases by 26 practising pharmacists.
The highest quality and performance scores were awarded to Lexi-Comp Online, whereas Micromedex received the lowest overall usability score, attributable to poor scores for layout, navigation, and speed. Lack of Canadian content was identified as a major disadvantage of the Clinical Pharmacology database. Users ranked Micromedex significantly lower than the other databases, whereas the majority of users ranked Lexi-Comp Online as the most preferred database.
Lexi-Comp Online appeared to be the most preferred database, whereas Micromedex was clearly the least preferred database. These findings should be considered in future decisions about purchasing database subscriptions.
Critical care pharmacy has evolved rapidly over the last 50 years to keep pace with the rapid technological and knowledge advances that have characterized critical care medicine. The modern-day critical care pharmacist is a highly trained individual well suited for the interprofessional team-based care that critical illness necessitates. Critical care pharmacists improve patient-centered outcomes and reduce health care costs through three domains: direct patient care, indirect patient care, and professional service. Optimizing workload of critical care pharmacists, similar to the professions of medicine and nursing, is a key next step for using evidence-based medicine to improve patient-centered outcomes.
Objectives:
Despite the established role of the critical care pharmacist on the ICU multiprofessional team, critical care pharmacist workloads are likely not optimized in the ICU. Medication regimen complexity (as measured by the Medication Regimen Complexity-ICU [MRC-ICU] scoring tool) has been proposed as a potential metric to optimize critical care pharmacist workload but has lacked robust external validation. The purpose of this study was to test the hypothesis that MRC-ICU is related to both patient outcomes and pharmacist interventions in a diverse ICU population.
Design:
This was a multicenter, observational cohort study.
Setting:
Twenty-eight ICUs in the United States.
Patients:
Adult ICU patients.
Interventions:
Critical care pharmacist interventions (quantity and type) on the medication regimens of critically ill patients over a 4-week period were prospectively captured. MRC-ICU and patient outcomes (i.e., mortality and length of stay [LOS]) were recorded retrospectively.
Measurements and main results:
A total of 3,908 patients at 28 centers were included. Following analysis of variance, MRC-ICU was significantly associated with mortality (odds ratio, 1.09; 95% CI, 1.08-1.11; p < 0.01), ICU LOS (β coefficient, 0.41; 95% CI, 00.37-0.45; p < 0.01), total pharmacist interventions (β coefficient, 0.07; 95% CI, 0.04-0.09; p < 0.01), and a composite intensity score of pharmacist interventions (β coefficient, 0.19; 95% CI, 0.11-0.28; p < 0.01). In multivariable regression analysis, increased patient: pharmacist ratio (indicating more patients per clinician) was significantly associated with increased ICU LOS (β coefficient, 0.02; 0.00-0.04; p = 0.02) and reduced quantity (β coefficient, -0.03; 95% CI, -0.04 to -0.02; p < 0.01) and intensity of interventions (β coefficient, -0.05; 95% CI, -0.09 to -0.01).
Conclusions:
Increased medication regimen complexity, defined by the MRC-ICU, is associated with increased mortality, LOS, intervention quantity, and intervention intensity. Further, these results suggest that increased pharmacist workload is associated with decreased care provided and worsened patient outcomes, which warrants further exploration into staffing models and patient outcomes.
Disclaimer
In an effort to expedite the publication of articles, AJHP is posting manuscripts online as soon as possible after acceptance. Accepted manuscripts have been peer-reviewed and copyedited, but are posted online before technical formatting and author proofing. These manuscripts are not the final version of record and will be replaced with the final article (formatted per AJHP style and proofed by the authors) at a later time.
Purpose
Numerous clinical scoring tools exist for a variety of patient populations and disease states, but few tools provide information specifically designed for use by critical care pharmacists. The medication regimen complexity intensive care unit (MRC-ICU) score was designed to provide high-level information about the complexity of critically ill patient’s medication regimens for use by critical care pharmacists. To date, implementation of this score in the electronic medical record (EMR) has not been reported.
Summary
Using an agile project management framework, the MRC-ICU score was rapidly implemented into an academic medical center’s EMR. The score automatically calculates on all critically ill patients and is available for critical care pharmacists to triage patient review in their individual workflow. Reporting capabilities of the score also allow for granular complexity trending over time and between units, supplementing other objective measures of pharmacist workload.
Conclusion
The MRC-ICU score can be quickly implemented into the EMR for pharmacist use in real time. Future investigations into how pharmacists utilize this information and how to harness reporting capabilities for pharmacist workload assessment are warranted.
Objectives:
To train a model to predict vasopressor use in ICU patients with sepsis and optimize external performance across hospital systems using domain adaptation, a transfer learning approach.
Design:
Observational cohort study.
Setting:
Two academic medical centers from January 2014 to June 2017.
Patients:
Data were analyzed from 14,512 patients (9,423 at the development site and 5,089 at the validation site) who were admitted to an ICU and met Center for Medicare and Medicaid Services definition of severe sepsis either before or during the ICU stay. Patients were excluded if they never developed sepsis, if the ICU length of stay was less than 8 hours or more than 20 days or if they developed shock up to the first 4 hours of ICU admission.
Measurements and main results:
Forty retrospectively collected features from the electronic medical records of adult ICU patients at the development site (four hospitals) were used as inputs for a neural network Weibull-Cox survival model to derive a prediction tool for future need of vasopressors. Domain adaptation updated parameters to optimize model performance in the validation site (two hospitals), a different healthcare system over 2,000 miles away. The cohorts at both sites were randomly split into training and testing sets (80% and 20%, respectively). When applied to the test set in the development site, the model predicted vasopressor use 4-24 hours in advance with an area under the receiver operator characteristic curve, specificity, and positive predictive value ranging from 0.80 to 0.81, 56.2% to 61.8%, and 5.6% to 12.1%, respectively. Domain adaptation improved performance of the model to predict vasopressor use within 4 hours at the validation site (area under the receiver operator characteristic curve 0.81 [CI, 0.80-0.81] from 0.77 [CI, 0.76-0.77], p < 0.01; specificity 59.7% [CI, 58.9-62.5%] from 49.9% [CI, 49.5-50.7%], p < 0.01; positive predictive value 8.9% [CI, 8.5-9.4%] from 7.3 [7.1-7.4%], p < 0.01).
Conclusions:
Domain adaptation improved performance of a model predicting sepsis-associated vasopressor use during external validation.
What gets measured, gets improved. —Robert Sharma
Every critically ill patient requires care by a critical care pharmacist (CCP) for best possible outcomes. Indeed, these highly trained professionals generate benefit through direct patient care (eg, pharmacist-driven protocols, medication monitoring, etc), participation on the intensive care unit (ICU) interprofessional team (eg, pharmacotherapy recommendations, team education, etc), and leadership in the development and implementation of quality improvement initiatives.¹ However, clinical CCP services are not provided for all ICU patients, and CCP staffing models often vary substantially across ICUs in a given hospital and among ICUs in the United States.²⁻⁴ In this narrative review, we use a gap analysis approach to define current levels of clinical CCP services, identify barriers to reaching an optimal level of these services, and propose strategies focused on expanding clinical CCP services and justifying those that currently exist.
Current critical care pharmacy clinical services
The broad scope of beneficial activities performed by the CCP has been extensively reviewed and supported by a position statement from the American Society of Health-System Pharmacists (ASHP), the American College of Clinical Pharmacy (ACCP), and the Society of Critical Care Medicine (SCCM): the CCP is an essential member of the healthcare team for delivery of patient-centered care in the ICU.
Causal inference is a critical research topic across many domains, such as statistics, computer science, education, public policy, and economics, for decades. Nowadays, estimating causal effect from observational data has become an appealing research direction owing to the large amount of available data and low budget requirement, compared with randomized controlled trials. Embraced with the rapidly developed machine learning area, various causal effect estimation methods for observational data have sprung up. In this survey, we provide a comprehensive review of causal inference methods under the potential outcome framework, one of the well-known causal inference frameworks. The methods are divided into two categories depending on whether they require all three assumptions of the potential outcome framework or not. For each category, both the traditional statistical methods and the recent machine learning enhanced methods are discussed and compared. The plausible applications of these methods are also presented, including the applications in advertising, recommendation, medicine, and so on. Moreover, the commonly used benchmark datasets as well as the open-source codes are also summarized, which facilitate researchers and practitioners to explore, evaluate and apply the causal inference methods.
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.
Background
Presumed serious infection (PSI) is defined as a blood culture drawn and new antibiotic course of at least 4 days among pediatric patients with Central Venous Lines (CVLs). Early PSI prediction and use of medical interventions can prevent adverse outcomes and improve the quality of care.
Methods
Clinical features including demographics, laboratory results, vital signs, characteristics of the CVLs and medications used were extracted retrospectively from electronic medical records. Data were aggregated across all hospitals within a single pediatric health system and used to train machine learning models (XGBoost and ElasticNet) to predict the occurrence of PSI 8 hours prior to clinical suspicion. Prediction for PSI was benchmarked against PRISM-III.
Results
Our model achieved an area under the receiver operating characteristic curve of 0.84 (95% CI = [0.82, 0.85]), sensitivity of 0.73 [0.69, 0.74], and positive predictive value (PPV) of 0.36 [0.34, 0.36]. The PRISM-III conversely achieved a lower sensitivity of 0.19 [0.16, 0.22] and PPV of 0.30 [0.26, 0.34] at a cut-off of >= 10. The features with the most impact on the PSI prediction were maximum diastolic blood pressure prior to PSI prediction (mean SHAP = 3.4), height (mean SHAP = 3.2), and maximum temperature prior to PSI prediction (mean SHAP = 2.6).
Conclusion
A machine learning model using common features in the electronic medical records can predict the onset of serious infections in children with central venous lines at least 8 hours prior to when a clinical team drew a blood culture.
Introduction:
The Medication Regimen Complexity -Intensive Care Unit (MRC-ICU) is the first tool for measuring medication regimen complexity in critically ill patients. This study tested machine learning (ML) models to investigate the relationship between medication regimen complexity and patient outcomes.
Methods:
This study was a single-center, retrospective observational evaluation of 130 adults admitted to the medical ICU. The MRC-ICU score was utilized to improve the inpatient model's prediction accuracy. Three models were proposed: model I, demographic data without medication data; model II, demographic data and medication regimen complexity variables; and model III: demographic data and the MRC-ICU score. A total of 6 ML classifiers was developed: k-nearest neighbor (KNN), naïve Bayes (NB), random forest, support vector machine, neural network, and logistic classifier (LC). They were developed and tested using electronic health record data to predict inpatient mortality.
Results:
The results demonstrated that adding medication regimen complexity variables (model II) and the MRC-ICU score (model III) improved inpatient mortality prediction.. The LC outperformed the other classifiers (KNN and NB), with an overall accuracy of 83%, sensitivity (Se) of 87%, specificity of 67%, positive predictive value of 93%, and negative predictive value of 46%. The APACHE III score and the MRC-ICU score at the 24-hour interval were the 2 most important variables.
Conclusion and relevance:
Inclusion of the MRC-ICU score improved the prediction of patient outcomes on the previously established APACHE III score. This novel, proof-of-concept methodology shows promise for future application of the MRC-ICU scoring tool for patient outcome predictions.
Objectives:
Provide a multiorganizational statement to update the statement from a paper in 2000 about critical care pharmacy practice and makes recommendations for future practice.
Design:
The Society of Critical Care Medicine, American College of Clinical Pharmacy Critical Care Practice and Research Network, and the American Society of Health-Systems Pharmacists convened a joint task force of 15 pharmacists representing a broad cross-section of critical care pharmacy practice and pharmacy administration, inclusive of geography, critical care practice setting, and roles. The Task Force chairs reviewed and organized primary literature, outlined topic domains, and prepared the methodology for group review and consensus. A modified Delphi method was used until consensus (> 66% agreement) was reached for each practice recommendation. Previous position statement recommendations were reviewed and voted to either retain, revise, or retire. Recommendations were categorized by level of ICU service to be applicable by setting, and grouped into five domains: patient care, quality improvement, research and scholarship, training and education, and professional development.
Main results:
There are 82 recommendation statements: forty-four original recommendations and 38 new recommendation statements. Thirty-four recommendations were made for patient care, primarily relating to critical care pharmacist duties and pharmacy services. In the quality improvement domain, 21 recommendations address the role of the critical care pharmacist in patient and medication safety, clinical quality programs, and analytics. Nine recommendations were made in the domain of research and scholarship. Ten recommendations are in the domain of training and education and eight recommendations regarding professional development.
Conclusions:
The statements recommended by this taskforce delineate the activities of a critical care pharmacist and the scope of pharmacy services within the ICU. Effort should be made from all stakeholders to implement the recommendations provided, with continuous effort toward improving the delivery of care for critically ill patients.
Objectives:
To provide a multiorganizational statement to update recommendations for critical care pharmacy practice and make recommendations for future practice. A position paper outlining critical care pharmacist activities was last published in 2000. Since that time, significant changes in healthcare and critical care have occurred.
Design:
The Society of Critical Care Medicine, American College of Clinical Pharmacy Critical Care Practice and Research Network, and the American Society of Health-Systems Pharmacists convened a joint task force of 15 pharmacists representing a broad cross-section of critical care pharmacy practice and pharmacy administration, inclusive of geography, critical care practice setting, and roles. The Task Force chairs reviewed and organized primary literature, outlined topic domains, and prepared the methodology for group review and consensus. A modified Delphi method was used until consensus (> 66% agreement) was reached for each practice recommendation. Previous position statement recommendations were reviewed and voted to either retain, revise, or retire. Recommendations were categorized by level of ICU service to be applicable by setting and grouped into five domains: patient care, quality improvement, research and scholarship, training and education, and professional development.
Main results:
There are 82 recommendation statements: 44 original recommendations and 38 new recommendation statements. Thirty-four recommendations represent the domain of patient care, primarily relating to critical care pharmacist duties and pharmacy services. In the quality improvement domain, 21 recommendations address the role of the critical care pharmacist in patient and medication safety, clinical quality programs, and analytics. Nine recommendations were made in the domain of research and scholarship. Ten recommendations were made in the domain of training and education and eight recommendations regarding professional development.
Conclusions:
Critical care pharmacists are essential members of the multiprofessional critical care team. The statements recommended by this taskforce delineate the activities of a critical care pharmacist and the scope of pharmacy services within the ICU. Effort should be made from all stakeholders to implement the recommendations provided, with continuous effort toward improving the delivery of care for critically ill patients.
Background
The MRC-ICU, a novel regimen complexity scoring tool, provides an objective measure of medication regimen complexity in critically ill patients. The MRC-ICU may have the ability to evaluate the impact of critical care pharmacists on patient outcomes but requires further validation. The objective of this study was to confirm the external validity of the MRC-ICU scoring tool at multiple institutions and intensive care unit (ICU) settings.
Methods
This was a multicenter, prospective, observational study. The electronic medical record was reviewed to collect patient demographics and patient outcomes, and the medication administration record was reviewed to collect MRC-ICU scores at 24 hours, 48 hours, and ICU discharge. Validation was performed by assessing convergent and divergent validity of the score. Spearman rank-order correlation was used to determine correlation.
Results
A total of 230 patients were evaluated across both centers in both medical ICUs and surgical ICUs. Differences between the original center and the new site included that total number of orders (29 vs 126; P < 0.001) and total number of medication orders (17 vs 36; P < 0.001) were higher at the new site, whereas the original site had higher overall MRC-ICU scores (14 vs 11; P = 0.004). The MRC-ICU showed appropriate convergent validity with number of orders and medication orders (all P < 0.001) and appropriate divergent validity with no significant correlation found between age, weight, or gender (all P > 0.05).
Conclusions
External validity of the MRC-ICU has been confirmed through evaluation at an external site and in the surgical ICU population. The MRC-ICU scoring tool requires prospective evaluation to provide objective data regarding optimal pharmacist use.
Purpose:
To develop an evidence-based tool that will provide concise guidance to pharmacy students who want to become competitive postgraduate year 1 (PGY1) residency applicants.
Methods:
A systematic literature search was conducted to identify articles describing student or school factors and specific interventions or activities associated with improved or decreased residency match rates, as well as studies describing residency program directors' (RPDs') or preceptors' perceptions of qualified applicants. An initial checklist was developed, with an item for each relevant factor. A consensus on checklist items was built through a 2-round Delphi process with a panel of RPDs. Ultimately, items that received a median score of at least 5 on a 7-point scale with less than one-third of the ratings being a 1, 2, or 3 were included.
Results:
The initial checklist of 34 items, primarily related to grade point average, professional involvement, work experience, or professional development, was evaluated by a panel of 25 RPD participants. Six of 34 items (18%) were reevaluated in round 2, along with 1 added item and 4 items substantively modified based on comments; 2 items were merged. Ultimately, 33 items met the criteria for consensus and were included in the final checklist.
Conclusion:
A checklist of items to guide prospective pharmacy residency applicants was developed through a systematic literature search and verified by program directors using a Delphi process.
Purpose
The purpose of this study was to characterize dynamic changes in medication regimen complexity over time in critically ill adults and to validate a modified version of the medication regimen complexity–intensive care unit (MRC-ICU) scoring tool.
Summary
A single-center, retrospective, observational chart review was conducted with a primary aim of assessing changes in medication regimen complexity over time, as measured by both the 39-item MRC-ICU scoring tool and a modified version (the mMRC-ICU) containing just 17 items. Secondary aims included validation of the mMRC-ICU and exploration of relationships between medication regimen complexity and ICU length of stay (LOS), inpatient mortality, and patient acuity. Adults admitted to a medical ICU from November 2016 through June 2017 were included. The medication regimens of a total of 130 patients were scored in order to test, modify, and validate the MRC-ICU and mMRC-ICU tools. The modified tool was validated by evaluating correlation of mMRC-ICU scores with MRC-ICU scores and with patient outcomes including patient acuity, ICU LOS, and inpatient mortality. mMRC-ICU scores were collected at 24 and 48 hours after admission and at ICU discharge to evaluate changes over time. Significant changes in medication regimen complexity over time were observed, with the highest scores observed at 24 hours after admission.
Conclusion
Medication regimen complexity may provide valuable insights into pharmacist activity and resource allocation. Further validation of the MRC-ICU and mMRC-ICU scoring tools in other critically ill populations and at external sites is required.
Background
Clinical pharmacists are established members of the interprofessional patient care team, but limited guidance for the optimal utilization of pharmacy resources is available. Objective measurement of medication regimen complexity offers a novel process for evaluating pharmacist activity. The purpose of this study was to evaluate the relationship between medication regimen complexity, as measured by a novel medication regimen complexity scoring tool (MRC‐ICU), and both pharmacist interventions and drug‐drug interactions (DDIs).
Methods
This was a multi‐center, prospective, observational study. The electronic medical record was reviewed to collect patient demographics, patient outcomes, and MRC‐ICU and modified MRC‐ICU (mMRC‐ICU) score at 24, 48 hours, and at discharge. Pharmacist interventions were recorded during the patients' intensive care unit (ICU) stay. DDIs were also evaluated at 24, 48 hours, and at discharge. Spearman's rank‐order correlation was used to determine any correlation between the MRC‐ICU score at each time point and the number of pharmacist interventions and DDIs.
Results
A total of 153 patients were evaluated from both centers. The median MRC‐ICU at 24 hours was 11 (interquartile range [IQR] 7‐15). MRC‐ICU at 24 hours was correlated with interventions at 24 hours ( r s .439, P <.001). Furthermore, MRC‐ICU was correlated with total DDIs ( r s .4, P < .001). A modified version of the MRC‐ICU was also correlated with number of pharmacist interventions ( P < .001) and DDIs ( P < .001).
Conclusions
Medication regimen complexity showed a relationship with number of pharmacist interventions and number of DDIs.
Objective:
To assess clinician perceptions of a machine learning-based early warning system to predict severe sepsis and septic shock (Early Warning System 2.0).
Design:
Prospective observational study.
Setting:
Tertiary teaching hospital in Philadelphia, PA.
Patients:
Non-ICU admissions November-December 2016.
Interventions:
During a 6-week study period conducted 5 months after Early Warning System 2.0 alert implementation, nurses and providers were surveyed twice about their perceptions of the alert's helpfulness and impact on care, first within 6 hours of the alert, and again 48 hours after the alert.
Measurements and main results:
For the 362 alerts triggered, 180 nurses (50% response rate) and 107 providers (30% response rate) completed the first survey. Of these, 43 nurses (24% response rate) and 44 providers (41% response rate) completed the second survey. Few (24% nurses, 13% providers) identified new clinical findings after responding to the alert. Perceptions of the presence of sepsis at the time of alert were discrepant between nurses (13%) and providers (40%). The majority of clinicians reported no change in perception of the patient's risk for sepsis (55% nurses, 62% providers). A third of nurses (30%) but few providers (9%) reported the alert changed management. Almost half of nurses (42%) but less than a fifth of providers (16%) found the alert helpful at 6 hours.
Conclusions:
In general, clinical perceptions of Early Warning System 2.0 were poor. Nurses and providers differed in their perceptions of sepsis and alert benefits. These findings highlight the challenges of achieving acceptance of predictive and machine learning-based sepsis alerts.
Background: Pressor agents are recognized as high-alert medications by the Institute for Safe Medication Practices, but little evidence is available to guide their use in septic shock. Objective: Characterize the use of pressor agents for septic shock in clinical practice. Methods: A cross-sectional electronic survey assessing demographics, institutional practices, and respondent perceptions related to pressor agents was distributed to the American College of Clinical Pharmacy Critical Care Practice and Research Network. The primary outcome was the use of a weight-based dosing (WBD) strategy versus non-WBD strategy for norepinephrine. Descriptive statistics were used to summarize survey results. Binary logistic regression was performed to determine variables associated with dosing strategies. Results: The survey was completed by 223 respondents. The typical respondent worked in a medical or mixed intensive care unit at a teaching hospital and had training and/or board certification beyond the Doctor of Pharmacy degree. Nearly all respondents (n = 221, 99%) reported norepinephrine as the first-line vasopressor for septic shock; however, 38% used WBD and 60% used non-WBD. In logistic regression, respondents located in the South and practicing at institutions with larger numbers of intensive care unit beds were more likely to use WBD for norepinephrine infusions. Similar findings were observed with epinephrine and phenylephrine. Conclusion: Wide variability exists in prescribing patterns of pressor agents and in pharmacist perceptions regarding best practices. The use of WBD varied based on institutional characteristics and resulted in higher maximum allowable infusion rates of pressor agents. Future research should compare dosing strategies to identify associations with patient outcomes.
Purpose
The purpose of this study was to develop and validate a novel medication regimen complexity–intensive care unit (MRC-ICU) scoring tool in critically ill patients and to correlate MRC with illness severity and patient outcomes.
Methods
This study was a single-center, retrospective observational chart review of adults admitted to the medical ICU (MICU) between November 2016 and June 2017. The primary aim was the development and internal validation of the MRC-ICU scoring tool. Secondary aims included external validation of the MRC-ICU and exploration of relationships between medication regimen complexity and patient outcomes. Exclusion criteria included a length of stay of less than 24 hours in the MICU, active transfer, or hospice orders at 24 hours. A total of 130 patient medication regimens were used to test, modify, and validate the MRC-ICU tool.
Results
The 39-line item medication regimen complexity scoring tool was validated both internally and externally. Convergent validity was confirmed with total medications (p < 0.0001). Score discriminant validity was confirmed by lack of association with age (p = 0.1039) or sex (p = 0.7829). The MRC-ICU score was significantly associated with ICU length of stay (p = 0.0166), ICU mortality (p = 0.0193), and patient acuity (p < 0.0001).
Conclusion
The MRC-ICU scoring tool was validated and found to correlate with length of stay, inpatient mortality, and patient acuity.
Background :
Residents and fellows often seek to emulate master clinician role models; however, the activities these expert clinical faculty pursued early in their careers are not known.
Objective :
We studied the early career clinical experiences and learning behaviors of peer-defined master academic clinicians.
Methods :
We performed a retrospective, qualitative interview study of 17 members of the University of California, San Francisco, Department of Medicine Council of Master Clinicians. Between March 1 and May 31, 2016, we interviewed participants using a semistructured interview guide surveying their early career clinical experiences and learning habits. Interviews were audio-recorded and transcribed. We used a general inductive approach to code transcripts and to identify consistent themes.
Results :
Of the 28 council members invited to participate, 17 (61%) responded and were interviewed. Participants included 12 men and 5 women, with an average of 27 years in clinical practice (range, 13-50 years). Six participants were general internists, and 11 were internal medicine subspecialists. Based on thematic analysis of interview transcripts, 4 themes of clinical development emerged: (1) consistent learning efforts; (2) rigorous skill development; (3) cultivating habits of mind; and (4) clinically rich environments.
Conclusions :
Our study describes the early career experiences and learning behaviors of master clinicians. We aggregated key dimensions of the findings into a guide for residents, fellows, and junior clinicians interested in the pursuit of clinical excellence.
Objectives:
To develop an acute kidney injury risk prediction model using electronic health record data for longitudinal use in hospitalized patients.
Design:
Observational cohort study.
Setting:
Tertiary, urban, academic medical center from November 2008 to January 2016.
Patients:
All adult inpatients without pre-existing renal failure at admission, defined as first serum creatinine greater than or equal to 3.0 mg/dL, International Classification of Diseases, 9th Edition, code for chronic kidney disease stage 4 or higher or having received renal replacement therapy within 48 hours of first serum creatinine measurement.
Interventions:
None.
Measurements and main results:
Demographics, vital signs, diagnostics, and interventions were used in a Gradient Boosting Machine algorithm to predict serum creatinine-based Kidney Disease Improving Global Outcomes stage 2 acute kidney injury, with 60% of the data used for derivation and 40% for validation. Area under the receiver operator characteristic curve (AUC) was calculated in the validation cohort, and subgroup analyses were conducted across admission serum creatinine, acute kidney injury severity, and hospital location. Among the 121,158 included patients, 17,482 (14.4%) developed any Kidney Disease Improving Global Outcomes acute kidney injury, with 4,251 (3.5%) developing stage 2. The AUC (95% CI) was 0.90 (0.90-0.90) for predicting stage 2 acute kidney injury within 24 hours and 0.87 (0.87-0.87) within 48 hours. The AUC was 0.96 (0.96-0.96) for receipt of renal replacement therapy (n = 821) in the next 48 hours. Accuracy was similar across hospital settings (ICU, wards, and emergency department) and admitting serum creatinine groupings. At a probability threshold of greater than or equal to 0.022, the algorithm had a sensitivity of 84% and a specificity of 85% for stage 2 acute kidney injury and predicted the development of stage 2 a median of 41 hours (interquartile range, 12-141 hr) prior to the development of stage 2 acute kidney injury.
Conclusions:
Readily available electronic health record data can be used to predict impending acute kidney injury prior to changes in serum creatinine with excellent accuracy across different patient locations and admission serum creatinine. Real-time use of this model would allow early interventions for those at high risk of acute kidney injury.
Objective:
Machine learning methods are flexible prediction algorithms that may be more accurate than conventional regression. We compared the accuracy of different techniques for detecting clinical deterioration on the wards in a large, multicenter database.
Design:
Observational cohort study.
Setting:
Five hospitals, from November 2008 until January 2013.
Patients:
Hospitalized ward patients INTERVENTIONS:: None MEASUREMENTS AND MAIN RESULTS:: Demographic variables, laboratory values, and vital signs were utilized in a discrete-time survival analysis framework to predict the combined outcome of cardiac arrest, intensive care unit transfer, or death. Two logistic regression models (one using linear predictor terms and a second utilizing restricted cubic splines) were compared to several different machine learning methods. The models were derived in the first 60% of the data by date and then validated in the next 40%. For model derivation, each event time window was matched to a non-event window. All models were compared to each other and to the Modified Early Warning score, a commonly cited early warning score, using the area under the receiver operating characteristic curve (AUC). A total of 269,999 patients were admitted, and 424 cardiac arrests, 13,188 intensive care unit transfers, and 2,840 deaths occurred in the study. In the validation dataset, the random forest model was the most accurate model (AUC, 0.80 [95% CI, 0.80-0.80]). The logistic regression model with spline predictors was more accurate than the model utilizing linear predictors (AUC, 0.77 vs 0.74; p < 0.01), and all models were more accurate than the MEWS (AUC, 0.70 [95% CI, 0.70-0.70]).
Conclusions:
In this multicenter study, we found that several machine learning methods more accurately predicted clinical deterioration than logistic regression. Use of detection algorithms derived from these techniques may result in improved identification of critically ill patients on the wards.