A systematic review of the use of artificial intelligence in mental health–based diabetes care: Current applications and future directions
Authors' conclusion
AI shows promise in addressing mental health needs in diabetes care. However, current research is narrow in scope and lacks methodological rigour in some respects.
Study context
- Population
- Peer-reviewed, empirical, quantitative human studies of artificial intelligence (AI)-based methods in diabetes contexts involving mental health factors
- Participants
- 41 studies
- Outcome
- Characteristics of AI research in mental health-based diabetes care
Methodological detailsPRISMA, pre-registered on PROSPERO, nine databases, independent screening and data extraction by two reviewers
- PRISMA
- Pre-registered on PROSPERO
- Nine databases
- Independent screening and data extraction by two reviewers
Pooled result
As reported in the abstract
- Observational designs
- 83%
- Cross-sectional designs
- 56%
- Focused on assessment rather than intervention
- 88%
- Targeted depression
- 56%
- Supervised learning algorithms used
- 83%
Further pooled results
Methodological limitations
- Limited diversity in samples and outcomes, minimal use of prospective experimental and RCT-based designs, overreliance on supervised learning algorithms
Original publication
A systematic review of the use of artificial intelligence in mental health–based diabetes care: Current applications and future directions. Diabet Med. Published 28 March 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →