AI for Health Care Quality and Patient Safety: Scoping Review of Diagnostic, Predictive, and Decision Support Applications
KI für Versorgungsqualität und Patientensicherheit: Scoping Review zu diagnostischen, prädiktiven und Entscheidungsunterstützungs-Anwendungen
Journal of Medical Internet Research · 21.09.2026 · 28 · e95157-e95157
DOI: 10.2196/95157 ↗Auf einen Blick
Die Scoping-Übersicht zu 275 Publikationen zeigt breite, aber uneinheitliche Evidenz zu KI in der Versorgungsqualität und Patientensicherheit. Prospektive und externe Validierung waren selten.
Fragestellung
Die Übersicht kartierte die Evidenz zu KI für Versorgungsqualität und Patientensicherheit über Anwendungsbereiche hinweg und erfasste Reifegrad und Barrieren.
Methode
Scoping Review nach Joanna Briggs Institute und PRISMA-ScR; Suche in 5 Datenbanken für englischsprachige Publikationen vom 1. Januar 2017 bis 30. April 2026.
Ergebnisse
43.394 Treffer, 275 in die Kerndarstellung aufgenommen. Abgedeckt waren diagnostische KI, prädiktive Analytik, klinische Entscheidungsunterstützung/Implementierung und ökonomische bzw. Wertbewertung.
Einschränkungen
Workflow- oder Prozessmaße, Equity-Analysen, formale ökonomische Evaluationen und Monitoring nach Einführung waren selten.
Schlussfolgerung der Autor:innen
Die Autor:innen nennen 5 wiederkehrende Barrieren für den Transfer von KI in klinischen Wert: begrenzte prospektive externe Validierung, workflowvermittelte Wirksamkeit, fragmentierte Infrastruktur, Defizite bei Equity und Generalisierbarkeit sowie wirtschaftliche und Governance-Unsicherheit.
Kernaussagen
- 275 Publikationen in 4 Anwendungsdomänen
- Workflow-/Prozessmaße nur in 13 (4,7 %) Records
- Formale ökonomische Evaluationen nur in 4 (1,5 %) Records
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Scoping Review in der Zeitschrift Journal of Medical Internet Research, online erschienen am 21.09.2026. Verfasst von Yang Xu und 2 weiteren Autor:innen. Beteiligte Einrichtung: Artificial Intelligence and Mathematical Modelling Lab, Dalla Lana School of Public Health, University of Toronto, Room 500, 155 College Street, Toro…. Hauptthemen laut MEDLINE: Quality of Health Care, Artificial Intelligence, Patient Safety, Decision Support Systems, Clinical. Die Arbeit nennt 75 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Themen: Patientensicherheit
Abstract (Originalsprache)
Background
AI systems have achieved strong performance on discrete diagnostic, predictive, and decision support tasks; yet, translation into sustained clinical benefit remains uneven. Existing reviews often examine single application areas, obscuring barriers that operate across the health care AI ecosystem.
Objective
This review aimed to map the published evidence on AI for health care quality and patient safety across application domains, characterize evidence maturity, and identify cross-domain barriers that limit translation into clinical value.
Methods
We conducted a scoping review following Joanna Briggs Institute methodology and reported it according to PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews), with search documentation guided by PRISMA-S (Preferred Reporting Items for Systematic Reviews and Meta-Analyses literature search extension). Five databases (MEDLINE via PubMed, Scopus, Web of Science Core Collection, IEEE Xplore, and CINAHL Plus with Full Text) were searched for English-language records published from January 1, 2017, to April 30, 2026. Eligibility followed the population-concept-context framework. Application domains were coded nonmutually. World Health Organization (WHO) quality of care dimensions served as a deductive scaffold, and recurring constraints were grouped into cross-domain barriers. Methodological characteristics were charted descriptively, informed by validation approach, implementation context, and established AI reporting frameworks.
Results
The search identified 43,394 records, of which 275 were retained in the core charting corpus after staged screening. The evidence covered 4 nonmutually coded domains: diagnostic AI (n=142, 51.6%), predictive analytics (n=192, 69.8%), clinical decision support or implementation-related applications (n=233, 84.7%), and economic or value assessment (n=53, 19.3%). It was broad but uneven in maturity, with the same gaps across all 4 domains. Prospective and external validation were uncommon, and retrospective results often lacked evidence of improved care. Workflow or process measures were recorded in only 13 (4.7%) records, and explicit equity or subgroup analyses were recorded in 20 (7.3%) records, indicating limited measurement of real-world impact. Economic and governance evidence was also thin, with formal economic evaluations found in 4 (1.5%) records and little attention to monitoring models after deployment. These gaps indicate limited evidence on how AI performs in clinical practice.
Conclusions
We identified 5 recurring barriers to translating health care AI into clinical value: limited prospective external validation, workflow-mediated effectiveness, infrastructure fragmentation, equity and generalizability deficits, and economic and governance uncertainty. Unlike domain-specific reviews, this review maps evidence across the 4 domains, locates the barriers within the WHO quality of care dimensions, and distinguishes descriptive findings from interpretive synthesis. The binding constraint on clinical value is no longer primarily technical but structural, recurring across domains. Health systems and regulators should therefore treat prospective external validation, workflow-integrated deployment, infrastructure readiness, equity monitoring, and lifecycle governance as prerequisites for responsible adoption.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Artificial Intelligence and Mathematical Modelling Lab, Dalla Lana School of Public Health, University of Toronto, Room 500, 155 College Street, Toronto, ON, M5T 3M7, Canada, 1 416-978-0901.
- Institute of Health Policy, Management and Evaluation, University of Toronto, Toronto, ON, Canada.
- Global South Artificial Intelligence for Pandemic and Epidemic Preparedness and Response Network, Toronto, ON, Canada.
- Africa-Canada Artificial Intelligence and Data Innovation Consortium, Toronto, ON, Canada.
- Munk School of Global Affairs and Public Policy, University of Toronto, Toronto, ON, Canada.
- Department of Mathematics, Bahen Centre for Information Technology, University of Toronto, Toronto, ON, Canada.
Zitieren
APA
Xu, Y., Veillard, J., & Kong, J. D. (2026). AI for Health Care Quality and Patient Safety: Scoping Review of Diagnostic, Predictive, and Decision Support Applications. Journal of Medical Internet Research, 28, e95157-e95157. https://doi.org/10.2196/95157
Vancouver
Xu Y, Veillard J, Kong JD. AI for Health Care Quality and Patient Safety: Scoping Review of Diagnostic, Predictive, and Decision Support Applications. Journal of Medical Internet Research. 2026;28:e95157-e95157. doi:10.2196/95157
BibTeX
@article{Xu2026,
author = {Xu, Yang and Veillard, Jeremy and Kong, Jude Dzevela},
title = {AI for Health Care Quality and Patient Safety: Scoping Review of Diagnostic, Predictive, and Decision Support Applications},
journal = {Journal of Medical Internet Research},
year = {2026},
volume = {28},
pages = {e95157--e95157},
doi = {10.2196/95157}
}
EUVIMED