David J. Murphy’s research while affiliated with Emory University and other places

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.

Background Critical care pharmacists are well‐established, valuable members of the intensive care unit interprofessional team with unique skills to perform comprehensive medication management in complex critically ill patients. However, standardized and consequential productivity metrics for critical care pharmacists have not been established. Objective To characterize the utilization and perception of contemporary critical care pharmacy productivity metrics utilized among individual institutions. Design, Setting, and Participants An electronic survey was distributed to critical care pharmacist members of the Society of Critical Care Medicine Clinical Pharmacy and Pharmacology Section and the American College of Clinical Pharmacy Critical Care Practice and Research Network. Main Outcomes and Measures The survey included 23 questions to assess institution demographics, individual respondent demographics, institution practices, and individual respondent perceptions about the value of critical care pharmacist productivity metrics. Results A total of 204 critical care pharmacists, largely from the United States, responded to the survey between July and November 2022. Institutional metrics captured by more than 50% of the respondents' institutions included order verification rate/number of orders verified (60%), number of clinical interventions (57%), and intravenous to enteral product interchanges (52%). Of these metrics, critical care pharmacists only agreed with the value of the number of clinical interventions, were indifferent to the value of intravenous to oral product interchanges, and disagreed with the value of order verification rate/number of orders verified. Conclusions Significant discrepancies exist between institutional productivity metric practices and their perceived value and utility among critical care pharmacists.

Background: Critically ill patients are managed with complex medication regimens that require medication management to optimize safety and efficacy. When performed by a critical care pharmacist (CCP), discrete medication management activities are termed medication interventions. The ability to define CCP workflow and intervention timeliness depends on the ability to predict the medication management needs of individual intensive care unit (ICU) patients. The purpose of this study was to develop prediction models for the number and intensity of medication interventions in critically ill patients. Methods: This was a retrospective, observational cohort study of adult patients admitted to an ICU between June 1, 2020 and June 7, 2023. Models to predict number of pharmacist interventions using both patient and medication related predictor variables collected at either baseline or in the first 24 hours of ICU stay were created. Both regression and supervised machine learning models (Random Forest, Support Vector Machine, XGBoost) were developed. Root mean square derivation (RMSE), mean absolute error (MAE), and symmetric mean absolute percentage error (sMAPE) were calculated. Results: In a cohort of 13,373 patients, the average number of interventions was 4.7 (standard deviation (SD) 7.1) and intervention intensity was 24.0 (40.3). Among the ML models, the Random Forest model had the lowest RMSE (9.26) while Support Vector Machine had the lowest MAE (4.71). All machine learning models performed similarly to the stepwise logistic regression model, and these performed better than a base model combining severity of illness with medication regimen complexity scores. Conclusions: Intervention quantity can be predicted using patient-specific factors. While inter-institutional variation in intervention documentation precludes external validation, our results provide a framework workload modeling at any institution.

Background: Medication management in the intensive care unit (ICU) is causally linked to both treatment success and potential adverse drug events (ADEs), often associated with deleterious consequences. Patients with higher severity of illness tend to require more management. The purpose of this evaluation was to explore the effect of comprehensive medication management (CMM) on mortality in critically ill patients. Methods: In this retrospective cohort study of adult ICU patients, CMM was measured by critical care pharmacist (CCP) medication interventions. Propensity score matching was performed to generate a balanced 1:1 matched cohort, and logistic regression was applied for estimating propensity scores. The primary outcome was the odds of hospital mortality. Hospital and ICU length of stay were also assessed. Results: In a cohort of 10,441 ICU patients, the unadjusted mortality rate was 11% with a mean APACHE II score of 9.54 and Medication Regimen Complexity-Intensive Care Unit (MRC-ICU) score of 5.78. Compared with CCP interventions less than 3, more CCP interventions was associated with a significantly reduced risk of mortality (estimate -0.04, 95% confidence interval -0.06 - -0.03, p < 0.01) and shorter length of ICU stay (estimate -2.77, 95% CI -2.98 - - 2.56, p < 0.01). Conclusions: The degree by which CCPs deliver CMM in the ICU is directly associated with reduced hospital mortality independent of patient characteristics and medication regimen complexity.

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.

Background: In critically ill patients, complex relationships exist among patient disease factors, medication management, and mortality. Considering the potential for nonlinear relationships and the high dimensionality of medication data, machine learning and advanced regression methods may offer advantages over traditional regression techniques. The purpose of this study was to evaluate the role of different modeling approaches incorporating medication data for mortality prediction. Methods: This was a single-center, observational cohort study of critically ill adults. A random sample of 991 adults admitted ≥ 24 hours to the intensive care unit (ICU) from 10/2015 to 10/2020 were included. Models to predict hospital mortality at discharge were created. Models were externally validated against a temporally separate dataset of 4,878 patients. Potential mortality predictor variables (n=27, together with 14 indicators for missingness) were collected at baseline (age, sex, service, diagnosis) and 24 hours (illness severity, supportive care use, fluid balance, laboratory values, MRC-ICU score, and vasopressor use) and included in all models. The optimal traditional (equipped with linear predictors) logistic regression model and optimal advanced (equipped with nature splines, smoothing splines, and local linearity) logistic regression models were created using stepwise selection by Bayesian information criterion (BIC). Supervised, classification-based ML models [e.g., Random Forest, Support Vector Machine (SVM), and XGBoost] were developed. Area under the receiver operating characteristic (AUROC), positive predictive value (PPV), and negative predictive value (NPV) were compared among different mortality prediction models. Results: A model including MRC-ICU in addition to SOFA and APACHE II demonstrated an AUROC of 0.83 for hospital mortality prediction, compared to AUROCs of 0.72 and 0.81 for APACHE II and SOFA alone. Machine learning models based on Random Forest, SVM, and XGBoost demonstrated AUROCs of 0.83, 0.85, and 0.82, respectively. Accuracy of traditional regression models was similar to that of machine learning models. MRC-ICU demonstrated a moderate level of feature importance in both XGBoost and Random Forest. Across all ten models, performance was lower on the validation set. Conclusions: While medication data were not included as a significant predictor in regression models, addition of MRC-ICU to severity of illness scores (APACHE II and SOFA) improved AUROC for mortality prediction. Machine learning methods did not improve model performance relative to traditional regression methods.