Performance of artificial intelligence in diabetes-related foot ulcer detection and assessment: a scoping review of clinical validation studies
Authors' conclusion
These findings suggest early-stage evidence of promising AI diagnostic performance.
Study context
- Population
- Adults with diabetes and foot ulcers; studies using learning-based artificial intelligence (AI) models for DFU detection and assessment reporting clinical validation outcomesstudies, 8 countries
- Participants
- 11 adults
- Outcome
- AI diagnostic performance and wound measurement
Methodological detailsArksey and O'Malley framework, PRISMA-ScR, Search of PubMed, MEDLINE, CINAHL, Scopus and Google Scholar; studies published 2020–2026
- Arksey and O'Malley framework
- PRISMA-ScR
- Search of PubMed, MEDLINE, CINAHL, Scopus and Google Scholar; studies published 2020–2026
Performance
As reported in the abstract
Sensitivity
91-100%
Specificity
20-96.8%
Intraclass correlation coefficients for wound measurement reliability
0.825-0.998
Reduction in manual area overestimation by AI systems
13.4-25.2%
Further findings
Factors influencing AI performance (NASSS domains)
- Technological: image quality, algorithmic misclassification; adopter-level: digital literacy limitations; organisational system-level: infrastructure instability, data privacy concerns
Original publication
Performance of artificial intelligence in diabetes-related foot ulcer detection and assessment: a scoping review of clinical validation studies. Diabetes Res Clin Pract. Published 5 August 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →