Matthew M. Ruppert

Background: Traditional methods of surgical decision making heavily rely on human experience and prompt actions, which are variable. A data-driven system that generates treatment recommendations based on patient states can be a substantial asset in perioperative decision-making for cases of intraoperative hypotension in which suboptimal management is associated with acute kidney injury (AKI), a common and morbid postoperative complication. Methods: In this retrospective cohort study, we analyzed 50,021 surgeries from 42,547 adult patients who underwent major surgery at a quaternary care hospital between 2014 and 2020. We developed a deep reinforcement learning model to recommend the optimum doses of intravenous fluids and vasopressors during surgery to avoid intraoperative hypotension and AKI defined by Kidney Disease: Improving Global Outcomes serum creatinine criteria within three days following surgery. Results: The developed model replicated 69% of physician’s decisions for the dosage of vasopressors and proposed higher or lower dosage of vasopressors than received in 10% and 21% of the treatments, respectively. In terms of intravenous fluids, the model’s recommendations were within 0.05 ml/kg/15 min of the actual dose in 41% of the cases, with higher or lower doses recommended for 27% and 32% of the treatments, respectively. The reinforcement learning policy resulted in a higher estimated policy value compared to the physicians’ actual treatments, as well as random policies and zero-drug policies. AKI incidence was lowest in patients who received medication dosages that aligned with our agent model’s decisions. Conclusions: Our findings suggest that implementation of the model’s policy has the potential to lower postoperative AKI and improve other outcomes driven by intraoperative hypotension.

Key Points: The developed dynamic model for predicting progression to stage 2 or higher AKI using multicenter data had robust performance. Clinical decision support implementation of the developed model could help prevent AKI progression. Kinetic eGFR, nephrotoxic drug burden, and BUN were the top features and remained the same across the models and sites. Background: AKI is an abrupt decline in kidney function that occurs in about 20% of hospitalized admissions and may lead to irreversible kidney damage. Methods: We developed and externally validated deep learning models to dynamically predict progression to stage 2 or higher AKI defined by Kidney Disease Improving Global Outcomes serum creatinine criteria within the next 48 hours. We used an extensive set of predictors including demographics, admission source, comorbidities, medications, laboratory, and vitals measurements. Results: Our retrospective study includes adult noncritical care patients at the University of Pittsburgh Medical Center (UPMC; 2018–2022; n =39,755) and the University of Florida Health (UFH; 2012–2019; n =122,324). In the UFH and UPMC development cohort, the mean age was 55 and 71 and 55% ( n =47,350) and 54% ( n =15,128) were female, respectively. Stage 2 or higher AKI occurred in 3% ( n =3257) and 8% ( n =2296) of UFH and UPMC patients, respectively. Area under the receiver operating characteristic curve values with 95% confidence interval (CI) ranged between 0.77 (95% CI, 0.75 to 0.78; UPMC Model—model trained on UPMC patients) and 0.81 (95% CI, 0.79 to 0.82; UFH Model—model trained on University of Florida patients) for the UFH test cohort and between 0.79 (95% CI, 0.78 to 0.8; UFH Model) and 0.83 (95% CI, 0.82 to 0.84; UPMC Model) for the UPMC test cohort. UFH-UPMC Model achieved an area under the receiver operating characteristic curve of 0.81 (95% CI, 0.80 to 0.83) for UFH and 0.82 (95% CI, 0.81 to 0.84) for UPMC test cohorts. Kinetic eGFR, nephrotoxic drug burden, and BUN remained the features with the highest influence across the models and institutions. Conclusions: The model developed using multicenter data had robust performance, suggesting that implementation could help prevent AKI progression.

OBJECTIVES: The aims of this scoping review were to: 1) explore factors driving surgical ICU (SICU) admission decisions, 2) provide an environmental scan of SICU admission practices, and 3) identify underexamined domains relevant for SICU triage, admission, and discharge inquiries. DATA SOURCES: Embase, PubMed, and Medline were queried from inception to April 18, 2024, for English-language peer-reviewed studies related to adult SICU admission criteria and decision-making; neonatal ICU, PICU, veterinary ICU, and military ICU data and gray literature were excluded. Studies were not limited by design. STUDY SELECTION: Following duplicate removal, 363 of the initial 625 abstracts remained. After content screening, 54 abstracts remained topic aligned. Full-text review identified 44 articles appropriate for analysis. DATA EXTRACTION: Abstracted data addressed SICU structure, function, findings, and potential future directions. DATA SYNTHESIS: Most included studies (n = 23, 52%) focused on identifying risk factors for SICU admission or risk factors for the need for SICU admission, including demographics, comorbidities, and procedural specifics. Admission protocol evaluation studies were less common (n = 5, 11%), but offered promise in reducing unnecessary admissions using preoperative or postoperative interventions. Future inquiry domains included admission and discharge protocol development (n = 17, 39%), risk factors for ICU admission or the need for ICU admission (n = 16, 36%), multicenter studies (n = 16, 36%), additional or specific patient populations (n = 15, 34%), prospective studies (n = 14, 32%), costs (n = 6, 14%), and implementation of embedded clinical decision-support aids to inform SICU triage decision-making (n = 2, 5%). No included studies presented results regarding SICU discharge decision-making or ICU stress adaptations relevant during surge episodes. CONCLUSIONS: Research on SICU triage decision-making primarily focuses at admission risk factor discovery, with less emphasis on protocol evaluation and implementation practices. Future research should focus on refining existing SICU triage approaches that include discharge and surge-based decision-making coupled with deployable clinical decision-support aids.

Background: Electronic health records (EHRs) have an enormous potential to advance medical research and practice through easily accessible and interpretable EHR-derived databases. Attainability of this potential is limited by issues with data quality (DQ) and performance assessment. Objective: This review aims to streamline the current best practices on EHR DQ and performance assessments as a replicable standard for researchers in the field. Methods: PubMed was systematically searched for original research articles assessing EHR DQ and performance from inception until May 7, 2023. Results: Our search yielded 26 original research articles. Most articles had 1 or more significant limitations, including incomplete or inconsistent reporting (n=6, 30%), poor replicability (n=5, 25%), and limited generalizability of results (n=5, 25%). Completeness (n=21, 81%), conformance (n=18, 69%), and plausibility (n=16, 62%) were the most cited indicators of DQ, while correctness or accuracy (n=14, 54%) was most cited for data performance, with context-specific supplementation by recency (n=7, 27%), fairness (n=6, 23%), stability (n=4, 15%), and shareability (n=2, 8%) assessments. Artificial intelligence–based techniques, including natural language data extraction, data imputation, and fairness algorithms, were demonstrated to play a rising role in improving both dataset quality and performance. Conclusions: This review highlights the need for incentivizing DQ and performance assessments and their standardization. The results suggest the usefulness of artificial intelligence–based techniques for enhancing DQ and performance to unlock the full potential of EHRs to improve medical research and practice.

The degree to which artificial intelligence healthcare research is informed by data and stakeholders from community settings has not been previously described. As communities are the principal location of healthcare delivery, engaging them could represent an important opportunity to improve scientific quality. This scoping review systematically maps what is known and unknown about community-engaged artificial intelligence research and identifies opportunities to optimize the generalizability of these applications through involvement of community stakeholders and data throughout model development, validation, and implementation. Embase, PubMed, and MEDLINE databases were searched for articles describing artificial intelligence or machine learning healthcare applications with community involvement in model development, validation, or implementation. Model architecture and performance, the nature of community engagement, and barriers or facilitators to community engagement were reported according to PRISMA extension for Scoping Reviews guidelines. Of approximately 10,880 articles describing artificial intelligence healthcare applications, 21 (0.2%) described community involvement. All articles derived data from community settings, most commonly by leveraging existing datasets and sources that included community subjects, and often bolstered by internet-based data acquisition and subject recruitment. Only one article described inclusion of community stakeholders in designing an application–a natural language processing model that detected cases of likely child abuse with 90% accuracy using harmonized electronic health record notes from both hospital and community practice settings. The primary barrier to including community-derived data was small sample sizes, which may have affected 11 of the 21 studies (53%), introducing substantial risk for overfitting that threatens generalizability. Community engagement in artificial intelligence healthcare application development, validation, or implementation is rare. As healthcare delivery occurs primarily in community settings, investigators should consider engaging community stakeholders in user-centered design, usability, and clinical implementation studies to optimize generalizability.

Background: Machine learning–enabled clinical information systems (ML-CISs) have the potential to drive health care delivery and research. The Fast Healthcare Interoperability Resources (FHIR) data standard has been increasingly applied in developing these systems. However, methods for applying FHIR to ML-CISs are variable. Objective: This study evaluates and compares the functionalities, strengths, and weaknesses of existing systems and proposes guidelines for optimizing future work with ML-CISs. Methods: Embase, PubMed, and Web of Science were searched for articles describing machine learning systems that were used for clinical data analytics or decision support in compliance with FHIR standards. Information regarding each system’s functionality, data sources, formats, security, performance, resource requirements, scalability, strengths, and limitations was compared across systems. Results: A total of 39 articles describing FHIR-based ML-CISs were divided into the following three categories according to their primary focus: clinical decision support systems (n=18), data management and analytic platforms (n=10), or auxiliary modules and application programming interfaces (n=11). Model strengths included novel use of cloud systems, Bayesian networks, visualization strategies, and techniques for translating unstructured or free-text data to FHIR frameworks. Many intelligent systems lacked electronic health record interoperability and externally validated evidence of clinical efficacy. Conclusions: Shortcomings in current ML-CISs can be addressed by incorporating modular and interoperable data management, analytic platforms, secure interinstitutional data exchange, and application programming interfaces with adequate scalability to support both real-time and prospective clinical applications that use electronic health record platforms with diverse implementations.

BACKGROUND: In traumatic hemorrhage, hybrid operating rooms offer near simultaneous performance of endovascular and open techniques, with correlations to earlier hemorrhage control, fewer transfusions, and possible decreased mortality. However, hybrid operating rooms are resource intensive. This study quantifies and describes a single-center experience with the complications, cost-utility, and value of a dedicated trauma hybrid operating room. METHODS: This retrospective cohort study evaluated 292 consecutive adult trauma patients who underwent immediate (p = 0.005) and, in the 4- to 24-hour postadmission period, required less red blood cell (mean, 1.0 vs. 0 U, p = 0.001) and plasma (mean, 1.0 vs. 0 U, p < 0.001) transfusions. Complications were similar except for a significant decrease in pneumonia (7% vs. 4%, p = 0.008). Severe complications (Clavien-Dindo classification, ≥3) were similar. Across the patient admission, costs were not significantly different ($50,023 vs. $54,740, p = 0.637). There was no change in overall value (1.00 vs. 1.07, p = 0.778). CONCLUSION: The conversion of our standard trauma operating room to an endovascular hybrid operating room provided measurable improvements in hemorrhage control, red blood cell and plasma transfusions, and postoperative pneumonia without significant increase in cost. Value was unchanged. LEVEL OF EVIDENCE: Economic/Value-Based Evaluations; Level III.

During the early stages of hospital admission, clinicians use limited information to make decisions as patient acuity evolves. We hypothesized that clustering analysis of vital signs measured within six hours of hospital admission would reveal distinct patient phenotypes with unique pathophysiological signatures and clinical outcomes. We created a longitudinal electronic health record dataset for 75,762 adult patient admissions to a tertiary care center in 2014–2016 lasting six hours or longer. Physiotypes were derived via unsupervised machine learning in a training cohort of 41,502 patients applying consensus k-means clustering to six vital signs measured within six hours of admission. Reproducibility and correlation with clinical biomarkers and outcomes were assessed in validation cohort of 17,415 patients and testing cohort of 16,845 patients. Training, validation, and testing cohorts had similar age (54–55 years) and sex (55% female), distributions. There were four distinct clusters. Physiotype A had physiologic signals consistent with early vasoplegia, hypothermia, and low-grade inflammation and favorable short-and long-term clinical outcomes despite early, severe illness. Physiotype B exhibited early tachycardia, tachypnea, and hypoxemia followed by the highest incidence of prolonged respiratory insufficiency, sepsis, acute kidney injury, and short- and long-term mortality. Physiotype C had minimal early physiological derangement and favorable clinical outcomes. Physiotype D had the greatest prevalence of chronic cardiovascular and kidney disease, presented with severely elevated blood pressure, and had good short-term outcomes but suffered increased 3-year mortality. Comparing sequential organ failure assessment (SOFA) scores across physiotypes demonstrated that clustering did not simply recapitulate previously established acuity assessments. In a heterogeneous cohort of hospitalized patients, unsupervised machine learning techniques applied to routine, early vital sign data identified physiotypes with unique disease categories and distinct clinical outcomes. This approach has the potential to augment understanding of pathophysiology by distilling thousands of disease states into a few physiological signatures.