Simon, György

Abstract Background Sepsis is a life-threatening condition in which delayed recognition and treatment are associated with increased mortality. While predictive models such as Epic’s Early Detection of Sepsis Model (ESM) were developed to support early intervention, their real-world impact after integration into clinical workflows remains difficult to evaluate. Objectives To evaluate the real-world impact of ESM integrated into clinical workflow on clinical outcomes, antibiotic use, and harm-benefit tradeoffs. Methods We conducted a quasi-experimental study in a single healthcare system using encounter-level data from inpatient settings. Inpatient mortality, prolonged hospitalization, antibiotic use, and sepsis prevalence were compared between the pre-implementation period (3 June 2023 to 20 August 2024) and the online period (21 August 2024 to 26 December 2024) when the model became visible to clinicians. We also applied a counterfactual framework using models trained on pre-implementation data to estimate expected outcomes without ESM and to quantify harms related to overtreatment and delayed treatment. Results Among 101,138 encounters, 86,884 occurred during the pre-implementation period and 14,254 during the online period. In unadjusted analyses, the online period had lower inpatient mortality, prolonged hospitalization, antibiotic use, and sepsis prevalence (all p≤0.002). In the counterfactual analyses, observed outcomes were lower than expected without ESM for mortality (1.21% vs 1.82%; p<0.001), prolonged hospitalization (5.56% vs 7.95%; p<0.001), and antibiotic use (43.52% vs 47.04%; p<0.001). False positive harm (37.72% vs 41.68%; p<0.001) was also lower than expected. Conclusions Integration of ESM into clinical workflow was associated with improved patient outcomes, reduced antibiotic use, and decreased harm from overtreatment, without evidence of increased harm from delayed treatment, supporting a positive net clinical benefit and the safety and effectiveness of ESM under Software as a Medical Device principles.

Abstract Objectives In the general hospital wards, machine learning (ML)-based early warning systems (EWSs) can identify patients at risk of deterioration to facilitate rescue interventions. We assess subpopulation performance of a ML-based EWS on medical and surgical adult patients admitted to general hospital wards. Materials and Methods We assessed the scores of an EWS integrated into the electronic health record and calculated every 15 minutes to predict a composite adverse event (AE): all-cause mortality, transfer to intensive care, cardiac arrest, or rapid response team evaluation. The distributions of the First Score 3 hours after admission, the Highest Score at any time during the hospitalization, and the Last Score just before an AE or dismissal without an AE were calculated. The Last Score was used to calculate the area under the receiver operating characteristic curve (ROC-AUC) and the precision-recall curve (PRC-AUC). Results From August 23, 2021 to March 31, 2022, 35 937 medical admissions had 2173 (6.05%) AE compared to 25 214 surgical admissions with 4984 (19.77%) AE. Medical and surgical admissions had significant different (P &lt;.001) distributions of the First Score, Highest Score, and Last Score among those with an AE and without an AE. The model performed better in the medical group when compared to the surgical group, ROC-AUC 0.869 versus 0.677, and RPC-AUC 0.988 versus 0.878, respectively. Discussion Heterogeneity of medical and surgical patients can significantly impact the performance of a ML-based EWS, changing the model validity and clinical discernment. Conclusions Characterization of the target patient subpopulations has clinical implications and should be considered when developing models to be used in general hospital wards.

Prolonged QT interval is an independent risk factor for all-cause mortality. However, evaluation of mortality associated to the implementation of a clinical decision support system to increase awareness and provide management recommendations has been challenging. Here we present our attempt to develop a model using only electronic data and different control groups.

Abstract Modern AI-based clinical decision support models owe their success in part to the very large number of predictors they use. Safe and robust decision support, especially for intervention planning, requires causal, not associative, relationships. Traditional methods of causal discovery, clinical trials and extracting biochemical pathways, are resource intensive and may not scale up to the number and complexity of relationships sufficient for precision treatment planning. Computational causal structure discovery (CSD) from electronic health records (EHR) data can represent a solution, however, current CSD methods fall short on EHR data. This paper presents a CSD method tailored to the EHR data. The application of the proposed methodology was demonstrated on type-2 diabetes mellitus. A large EHR dataset from Mayo Clinic was used as development cohort, and another large dataset from an independent health system, M Health Fairview, as external validation cohort. The proposed method achieved very high recall (.95) and substantially higher precision than the general-purpose methods (.84 versus .29, and .55). The causal relationships extracted from the development and external validation cohorts had a high (81%) overlap. Due to the adaptations to EHR data, the proposed method is more suitable for use in clinical decision support than the general-purpose methods.

Objective: Liver transplantation is a costly and risky procedure, representing 25 050 procedures worldwide in 2013, with 6729 procedures performed in the United States in 2014. Considering the scarcity of organs and uncertainty regarding prognosis, limited studies address the variety of risk factors before transplantation that might contribute to predicting patient’s survival and therefore developing better models that address a holistic view of transplant patients. This critical review aimed to identify predictors of liver transplant patient survival included in large-scale studies and assess the gap in risk factors from a holistic approach using the Wellbeing Model and the Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) statement. Data Source: Search of the Cumulative Index to Nursing and Allied Health Literature (CINAHL), Medline, and PubMed from the 1980s to July 2014. Study Selection: Original longitudinal large-scale studies, of 500 or more subjects, published in English, Spanish, or Portuguese, which described predictors of patient survival after deceased donor liver transplantation. Data Extraction: Predictors were extracted from 26 studies that met the inclusion criteria. Data Synthesis: Each article was reviewed and predictors were categorized using a holistic framework, the Wellbeing Model (health, community, environment, relationship, purpose, and security dimensions). Conclusions: The majority (69.7%) of the predictors represented the Wellbeing Model Health dimension. There were no predictors representing the Wellbeing Dimensions for purpose and relationship nor emotional, mental, and spiritual health. This review showed that there is rigorously conducted research of predictors of liver transplant survival; however, the reported significant results were inconsistent across studies, and further research is needed to examine liver transplantation from a whole-person perspective.

Background/Aims: Due to the progressive nature of type 2 diabetes mellitus (T2DM), deterioration in a patient’s general health is inevitable. Hence, the overall health of a T2DM patient is poor. Markers of worsening overall health such as metabolic abnormalities are predominant in the progression to any of the T2DM complications, which mask patterns of progression to individual complications, thereby making it difficult to predict which particular complication a patient will progress to (i.e. direction of progression). We aim to unmask the patterns and develop the most distinctive and predictive markers of progression to each individual complication. Methods: We take a two-step modeling approach using 94,536 T2DM patients’ 10-year, de-identified data from the OptumLabs™ Data Warehouse, a database that includes retrospective administrative claims data on commercially insured and Medicare Advantage enrollees, as well as electronic medical record data from a nationwide network of provider groups. First, we build a “general progression” model that predicts development of any new complication and captures markers of general health deterioration. Next, we develop “differential progression” models that predict progression to individual complications. We use least absolute shrinkage and selection operator (LASSO)-penalized Cox regressions to select variables and penalize the “differential progression” models against the “general progression” model such that “differential progression” patterns become unmasked. Significance of markers is determined via permutation test and predictive performance is evaluated through bootstrap estimation. Results: For a 6-year follow-up period, 31,968 (34%) of all patients progressed to at least one complication: chronic kidney disease (12%), ischemic heart disease (11%), cerebrovascular disease (8%), congestive heart failure (5%), peripheral vascular disease (5%), and renal failure (1%). In this ongoing research, we anticipate our predictive model to demonstrate improved interpretation of progression to each individual complication without causing reduced predictive performance. Conclusion: We study the progression of T2DM to multiple complications systematically and comprehensively by applying data mining techniques on the large amount of claims and clinical data from the OptumLabs Data Warehouse. By unmasking previously masked patterns and developing markers that suggest progression to a specific target complication, our study findings will assist clinicians in the management and treatment of T2DM.