Real-World Effects of a Sepsis Early Detection Model Integrated into Clinical Workflow: A Quasi-Experimental Study
Real-World Effects of a Sepsis Early Detection Model, integriert in klinische Arbeitsabläufe: Quasi-experimentelle Studie
Applied Clinical Informatics · 01.08.2026 · 17 (04) · 854-862
DOI: 10.1055/a-2962-8091 ↗Auf einen Blick
In 89.469 Behandlungsfällen war die Integration des ESM in den klinischen Ablauf mit niedrigeren Raten für Mortalität, prolongierten Krankenhausaufenthalt und Antibiotikaeinsatz verbunden.
Fragestellung
Welche Auswirkungen hat das in klinische Arbeitsabläufe integrierte Epic Early Detection of Sepsis Model (ESM) auf klinische Outcomes, Antibiotikaeinsatz und Nutzen-Schaden-Abwägung?
Methode
Quasi-experimentelle Studie in einem Gesundheitssystem mit inpatienten Falldaten; Vergleich vor Freischaltung und Online-Phase sowie Counterfactual-Analyse.
Ergebnisse
89.469 Behandlungsfälle; 75.215 vor, 14.254 während der Online-Phase. Im Counterfactual: Mortalität 1,21 vs. 1,94 %; prolongierter Aufenthalt 5,56 vs. 8,14 %; Antibiotikaeinsatz 43,52 vs. 47,74 %; falsch-positiver Schaden 37,72 vs. 42,31 %; jeweils p < 0,001.
Schlussfolgerung der Autor:innen
Die Integration des ESM war mit besseren Patientenergebnissen, geringerem Antibiotikaeinsatz und weniger Schaden durch Überbehandlung assoziiert, ohne Hinweise auf mehr Schaden durch verzögerte Behandlung.
Kernaussagen
- Mortalität, prolongierter Aufenthalt und Antibiotikaeinsatz nahmen in der Online-Phase ab.
- Counterfactual-Analysen zeigten niedrigere Werte als ohne ESM erwartet.
- Kein Hinweis auf mehr Schaden durch verzögerte Behandlung.
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Fachartikel in der Zeitschrift Applied Clinical Informatics, erschienen am 01.08.2026. Verfasst von Yifan Zhang und 8 weiteren Autor:innen. Beteiligte Einrichtung: Center for Learning Health System Sciences, University of Minnesota, Minnesota, United States, Minneapolis. Hauptthemen laut MEDLINE: Sepsis, Workflow. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Patient-Centered Outcomes Research Institute, Agency for Healthcare Quality and Research, National Center for Advancing Translational Sciences of the National Institutes of Health.
Themen: Sepsis
Abstract (Originalsprache)
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 effects after integration into clinical workflows remain difficult to evaluate.
Objectives
This study aimed to evaluate the real-world effects of ESM integrated into clinical workflow on clinical outcomes, antibiotic use, and harm–benefit trade-offs.
Methods
We conducted a quasi-experimental study in a single health care system using encounter-level data from inpatient settings. Inpatient mortality, prolonged hospitalization, antibiotic use, and sepsis prevalence (defined by electronic health record [EHR]) were compared between the preacquisition period (June 3, 2023–June 24, 2024) and the online period (August 21, 2024–December 26, 2024) when the model became visible to clinicians. We also applied a counterfactual framework using models trained on preacquisition data to estimate expected outcomes without ESM and to quantify harms related to overtreatment and delayed treatment.
Results
Among 89,469 encounters, 75,215 occurred during the preacquisition period and 14,254 during the online period. In unadjusted analyses, inpatient mortality, prolonged hospitalization, antibiotic use, and EHR-defined sepsis proportion all decreased during the online period (all p ≤ 0.006). In the counterfactual analyses, observed outcomes were lower than expected without ESM for mortality (1.21 vs. 1.94%; p < 0.001), prolonged hospitalization (5.56 vs. 8.14%; p < 0.001), and antibiotic use (43.52 vs. 47.74%; p < 0.001). False positive harm (37.72 vs. 42.31%; p < 0.001) was also lower than expected.
Conclusion
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Center for Learning Health System Sciences, University of Minnesota, Minnesota, United States, Minneapolis.
- Institute for Health Informatics, University of Minnesota, Minnesota, United States, Minneapolis.
- Fairview Health Services, Minnesota, United States, Minneapolis.
- University of Minnesota, Department of Medicine, Minnesota, United States, Minneapolis.
- University of Minnesota, Department of Computer Science and Engineering, Minnesota, United States, Minneapolis.
- Mayo Clinic, Department of Medicine, Minnesota, United States, Rochester.
ORCID-Profile: Yifan Zhang, Sarolta H Trinh
Förderung
- Patient-Centered Outcomes Research Institute
- Agency for Healthcare Quality and Research
- National Center for Advancing Translational Sciences of the National Institutes of Health
- Minnesota Partnership for Biotechnology and Medical Genomics Grant
Zitieren
APA
Zhang, Y., Trinh, S. H., Phelan, T., Byrd, T. F., Tourani, R., Kumar, V., Caraballo, P. J., Melton-Meaux, G. B., & Simon, G. J. (2026). Real-World Effects of a Sepsis Early Detection Model Integrated into Clinical Workflow: A Quasi-Experimental Study. Applied Clinical Informatics, 17(04), 854-862. https://doi.org/10.1055/a-2962-8091
Vancouver
Zhang Y, Trinh SH, Phelan T, Byrd TF, Tourani R, Kumar V, et al. Real-World Effects of a Sepsis Early Detection Model Integrated into Clinical Workflow: A Quasi-Experimental Study. Applied Clinical Informatics. 2026;17(04):854-862. doi:10.1055/a-2962-8091
BibTeX
@article{Zhang2026,
author = {Zhang, Yifan and Trinh, Sarolta H and Phelan, Tom and Byrd, Thomas F and Tourani, Roshan and Kumar, Vipin and Caraballo, Pedro J and Melton-Meaux, Genevieve B and Simon, Gyorgy J},
title = {Real-World Effects of a Sepsis Early Detection Model Integrated into Clinical Workflow: A Quasi-Experimental Study},
journal = {Applied Clinical Informatics},
year = {2026},
volume = {17},
number = {04},
pages = {854--862},
doi = {10.1055/a-2962-8091}
}
EUVIMED