Operationalization of Artificial Intelligence Applications in the Intensive Care Unit
Operationalisierung von Anwendungen künstlicher Intelligenz auf der Intensivstation
JAMA Network Open · 23.07.2025 · 8 (7) · e2522866
DOI: 10.1001/jamanetworkopen.2025.22866 ↗Auf einen Blick
Die systematische Übersichtsarbeit zeigt: Die meisten KI-Studien in der Intensivmedizin blieben in frühen Entwicklungsstufen. Nur wenige erreichten klinische Integration; eine vollständige Implementierung wurde nicht gefunden.
Fragestellung
Wie weit ist die Operationalisierung von KI-Systemen auf der Intensivstation entwickelt, gemessen an Fortschritt, technischer Reife und Verzerrungsrisiko?
Methode
Systematische Übersichtsarbeit; 5 Datenbanken wurden für Studien vom 28. Juli 2020 bis 10. Juni 2024 durchsucht. Bewertung mit PROBAST, Klassifikation nach TRL.
Ergebnisse
1.263 Studien erfüllten die Einschlusskriterien. 936 (74 %) waren TRL 4 oder darunter; externe Validierung (TRL 5) erreichten 24 %. 25 (2 %) kamen zur klinischen Integration (TRL≥6), keine zu TRL 9. Hohes Verzerrungsrisiko bei 581/1103 Studien (53 %).
Einschränkungen
Nur 207 Studien (16 %) nannten Berichtsstandards; die Einhaltung stieg von 14 % 2021 auf 23 % 2024.
Schlussfolgerung der Autor:innen
Trotz starkem Wachstum bleibt der Übergang von der Entwicklung zur klinischen Implementierung begrenzt und hat sich über die Zeit nur wenig verbessert.
Kernaussagen
- 74 % der Studien waren TRL 4 oder darunter
- Nur 25 Studien erreichten klinische Integration (TRL≥6)
- Hohes Verzerrungsrisiko bei 53 % der bewerteten Studien
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Systematische Übersicht in der Zeitschrift JAMA Network Open, online erschienen am 23.07.2025. Verfasst von Willemijn E M Berkhout und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Adult Intensive Care, Erasmus MC University Medical Center, Rotterdam, the Netherlands. Hauptthemen laut MEDLINE: Intensive Care Units, Artificial Intelligence. Die Arbeit wurde bisher 84-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Themen: Künstliche Intelligenz in der Pflege, Intensivpflege
Abstract (Originalsprache)
Importance Artificial intelligence (AI) presents transformative opportunities to address the increasing challenges faced by health care systems globally. Particularly, in data-rich environments, such as intensive care units (ICUs), AI could assist in enhancing clinical decision-making, streamline workflows, and improve patient outcomes. Despite these promising applications, the practical implementation of AI in clinical settings remains limited.
Objective
To systematically evaluate AI system operationalization in the ICU, focusing on the AI field’s progress over time, technical maturity, and risk of bias. Evidence Review In this systematic review, 5 databases (Embase, MEDLINE ALL, Web of Science Core Collection, Cochrane Central Register of Controlled Trials, and Google Scholar) were searched for studies published from July 28, 2020, to June 10, 2024. Eligible studies evaluated AI applications designed for use within ICUs for adults (aged ≥16 years) and used data collected during ICU stays. Two reviewers independently screened titles and abstracts, with a third reviewer resolving disagreements. Data extraction included AI application aims, dataset origins, technology readiness level (TRL) categorization, and the use of reporting standards. Risk of bias was assessed using the PROBAST (Prediction Model Study Risk of Bias Assessment Tool).
Findings
Of 17 401 screened records, 1263 studies met the inclusion criteria. A total of 936 studies (74% of all studies) were classified as TRL 4 or below, indicating early-stage development or initial validation. Among these, 447 (37%) used internal datasets, 562 (46%) used MIMIC (Medical Information Mart for Intensive Care) datasets (I-IV), and 78 (6%) used the open-source eICU Collaborative Research Database. External validation (TRL 5) was achieved by 24% of studies. Only 25 (2%) progressed to clinical integration (TRL≥6), with no studies reaching full implementation (TRL 9). Although approximately half of generative AI models reached a higher TRL (14 [47%] with TRL 5), none reached clinical integration. Additionally, only 207 studies (16%) referenced reporting standards, with adherence modestly increasing from 14% in 2021 to 23% in 2024. High risk of bias was identified in 581 of 1103 studies (53%), primarily due to methodologic shortcomings in the analysis domain. Conclusions and Relevance Despite substantial growth in AI research within intensive care medicine in recent years, the transition from development to clinical implementation still remains limited and has made little progress over time. A paradigm shift is urgently required in the medical literature—one that moves beyond retrospective validation toward the operationalization and prospective testing of AI for tangible clinical impact.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Adult Intensive Care, Erasmus MC University Medical Center, Rotterdam, the Netherlands.
- Erasmus MC Datahub, University Center Rotterdam, Rotterdam, the Netherlands.
- Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands.
- Department of Intensive Care, Elisabeth-TweeSteden Hospital, Tilburg, the Netherlands.
- Department of Surgical Oncology and Gastrointestinal Surgery, Erasmus MC Cancer Center, University Medical Center Rotterdam, Rotterdam, the Netherlands.
- Cardiovascular Research Institute Düsseldorf (CARID), Medical Faculty and University Hospital of Düsseldorf, Heinrich-Heine University Düsseldorf, Düsseldorf, Germany.
Zitieren
APA
Berkhout, W. E. M., van Wijngaarden, J. J., Workum, J. D., van de Sande, D., Hilling, D. E., Jung, C., Meyfroidt, G., Gommers, D., Buijsman, S. N. R., & van Genderen, M. E. (2025). Operationalization of Artificial Intelligence Applications in the Intensive Care Unit. JAMA Network Open, 8(7), e2522866. https://doi.org/10.1001/jamanetworkopen.2025.22866
Vancouver
Berkhout WEM, van Wijngaarden JJ, Workum JD, van de Sande D, Hilling DE, Jung C, et al. Operationalization of Artificial Intelligence Applications in the Intensive Care Unit. JAMA Network Open. 2025;8(7):e2522866. doi:10.1001/jamanetworkopen.2025.22866
BibTeX
@article{Berkhout2025,
author = {Berkhout, Willemijn E M and van Wijngaarden, Julia J and Workum, Jessica D and van de Sande, Davy and Hilling, Denise E and Jung, Christian and Meyfroidt, Geert and Gommers, Diederik and Buijsman, Stefan N R and van Genderen, Michel E},
title = {Operationalization of Artificial Intelligence Applications in the Intensive Care Unit},
journal = {JAMA Network Open},
year = {2025},
volume = {8},
number = {7},
pages = {e2522866},
doi = {10.1001/jamanetworkopen.2025.22866}
}
EUVIMED