Artificial intelligence in mental health care: a scoping review of reviews
Künstliche Intelligenz in der psychischen Gesundheitsversorgung: Scoping-Review von Reviews
Frontiers in Psychiatry · 03.03.2026 · 17
DOI: 10.3389/fpsyt.2026.1688043 ↗Auf einen Blick
31 Reviews zeigen: Unter interner Validierung wurden oft hohe Leistungen berichtet, extern oder prospektiv validierte Ergebnisse waren seltener und meist schwächer. Chatbots verbesserten depressive Symptome kurzzeitig gering bis moderat.
Fragestellung
Welche Evidenz gibt es zu Anwendungen künstlicher Intelligenz in der psychischen Gesundheitsversorgung über Reviews hinweg?
Methode
Scoping-Review von Reviews nach PRISMA-ScR und Joanna-Briggs-Institut; Suche in MEDLINE, Embase, PsycINFO und IEEE Xplore.
Ergebnisse
31 Reviews eingeschlossen. Fokus auf Depression und Angst. Interne AUCs lagen in früheren Synthesen meist bei ≈0,80–0,88; extern/prospektiv validierte Leistung war selten. Chatbots: kleine bis moderate kurzfristige Effekte bei Depression (SMD ≈0,2–0,6).
Einschränkungen
Interne und externe Kennzahlen wurden nicht gepoolt; viele Chatbot-Studien waren kurz und klein, mit wenigen randomisierten oder pragmatischen Studien.
Schlussfolgerung der Autor:innen
KI-Anwendungen reichen über das Versorgungsspektrum, sind aber noch früh in der Translation. Gute interne Leistung nimmt bei externer Prüfung oft ab; Nutzen, Governance und Implementierung bleiben unvollständig.
Kernaussagen
- Starke interne Leistung, aber seltene externe oder prospektive Validierung
- Chatbots: kurzfristige Effekte vor allem bei Depression, weniger bei Angst/Stress
- Adoption wird durch Usability, EHR-Integration und Governance begrenzt
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 Frontiers in Psychiatry, online erschienen am 03.03.2026. Verfasst von Mohammad S Abu-Mahfouz und 3 weiteren Autor:innen. Beteiligte Einrichtung: Almoosa College of Health Sciences, Al Ahsa, Saudi Arabia. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
Artificial intelligence (AI) is rapidly entering mental health care, but most models remain proof-of-concept, with limited external validation and substantial risk of overfitting.
Methods
This scoping review of reviews adhered to the PRISMA-ScR checklist and Joanna Briggs Institute guidance. We searched MEDLINE, Embase, PsycINFO, and IEEE Xplore. Eligible publications encompassed systematic, scoping, narrative, integrative, meta-analytic, and patent reviews. Findings were synthesised thematically.
Results
Thirty-one reviews were included. Evidence concentrated on depression and anxiety; schizophrenia, bipolar disorder, perinatal mental health, autism spectrum conditions, older adults, nurses, and allied professionals were under-represented. Across screening, diagnosis/classification, and risk prediction, high accuracy was frequently reported under internal validation; in prior syntheses, typical internal AUCs clustered around ≈0.80–0.88 whereas externally or prospectively validated performance was scarce and typically attenuated. Signals were strongest for narrow, feedback-rich tasks, with greater decay for general-purpose models and longer prediction horizons. Conversational agents produced small-to-moderate short-term improvements in depressive symptoms (SMD ≈0.2–0.6); effects for anxiety and stress were smaller or inconsistent and varied with comparator stringency, follow-up (≤8–12 weeks vs longer), and the degree of human guidance. Most chatbot evaluations were short and small-scale, with few randomized or pragmatic trials and limited data on durability beyond 12 weeks. Real-world implementation was limited; several reviews identified usability and electronic health-record integration as prerequisites for adoption, and explainability alone rarely conferred actionability without clinician training. Ethical readiness was incomplete: privacy and bias were commonly discussed, but accountability, post-deployment monitoring, and crisis-escalation protocols were inconsistently specified. Economic evaluations were uncommon and rarely accounted for integration, maintenance, or re-training costs. Workforce outcomes (literacy, confidence, readiness) were infrequently measured. Internal and external metrics were not pooled.
Conclusions
AI applications span the mental-health care continuum but remain early in translation. Performance that appears strong under internal validation often attenuates on external or prospective testing; symptomatic gains are concentrated in depression/anxiety and may diminish over longer follow-up; and adoption is constrained by usability, EHR integration, and incomplete governance. The cross-review signal highlights consistent gaps in accountability, post-deployment monitoring and crisis escalation, equity reporting, workforce readiness, and life-cycle economics (including integration, monitoring, and re-training). Addressing these gaps through externally validated and monitored deployments, routine content/guardrail audits for chatbots with human escalation, predefined subgroup performance and bias auditing, and implementation strategies that pair explainability with clinician training and measure workforce endpoints would better align the evidence base with safe, effective, and sustainable clinical use.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Almoosa College of Health Sciences, Al Ahsa, Saudi Arabia.
Zitieren
APA
Abu-Mahfouz, M. S., AlFehaid, S., Burqan, H. M., & El Arab, R. A. (2026). Artificial intelligence in mental health care: a scoping review of reviews. Frontiers in Psychiatry, 17. https://doi.org/10.3389/fpsyt.2026.1688043
Vancouver
Abu-Mahfouz MS, AlFehaid S, Burqan HM, El Arab RA. Artificial intelligence in mental health care: a scoping review of reviews. Frontiers in Psychiatry. 2026;17. doi:10.3389/fpsyt.2026.1688043
BibTeX
@article{AbuMahfouz2026,
author = {Abu-Mahfouz, Mohammad S and AlFehaid, Sarah and Burqan, Hala M and El Arab, Rabie Adel},
title = {Artificial intelligence in mental health care: a scoping review of reviews},
journal = {Frontiers in Psychiatry},
year = {2026},
volume = {17},
doi = {10.3389/fpsyt.2026.1688043}
}
EUVIMED