EUVIMEDDescoperă EUVIMED
Scoping ReviewOpen access

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

Yang Xu, Jeremy Veillard, Jude Dzevela Kong

Journal of Medical Internet Research · 2026-09-21 · 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.

At a glance

Scoping Review in Journal of Medical Internet Research, published online on 2026-09-21. Written by Yang Xu and 2 co-authors. Institution: Artificial Intelligence and Mathematical Modelling Lab, Dalla Lana School of Public Health, University of Toronto, Room 500, 155 College Street, Toro…. Major MEDLINE topics: Quality of Health Care, Artificial Intelligence, Patient Safety, Decision Support Systems, Clinical. 75 references. The full text is freely available in PubMed Central.

Auf einen BlickRezumatSubjectsDate bibliograficeCiteRelated studies

Abstract (original language)

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.

Subjects

MeSH terms (MEDLINE)

Quality of Health CareArtificial IntelligencePatient SafetyDecision Support Systems, ClinicalHumans

Author keywords

AIclinical decision supportdiagnostic accuracyhealth careimplementation science

Authors and institutions

  • 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.

Cite

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}
}
Start for free →