Generative artificial intelligence in osteoarthritis: A systematic scoping review of current applications and future directions
Authors' conclusion
While GenAI holds unique potential to transform OA care and research, current studies are small-scale and heterogeneous, with limited exploration of applications beyond imaging data.
Study context
- Population
- English-language studies detailing applications of generative AI in OA; Medline, EMBASE, Pubmed and Scopus searched to December 202549 studies
- Outcome
- Current applications of generative AI in OA care and research
Main finding
As reported in the abstract
Applications of generative AI in OA (49 studies, four domains)
- Large language models to diagnose OA and/or make guideline-concordant treatment recommendations
- 12 studies, 25%
- Large language models to generate patient-facing materials
- 15 studies, 31%
- Large language models, other applications
- three studies, 6%
- Generation of synthetic data, primarily imaging datasets
- eight studies, 16%
- Synthetic data improved accuracy of downstream classification
- 5-19%
- Analysis of imaging data
- ten studies, 20%
- Accuracy of generative models in OA severity grading
- 70-90%
- Analysis and integration of multi-omic data; variational autoencoder frameworks uncovered biologically-distinct OA subgroups associated with clinical outcomes
- one study, 2%
Original publication
Generative artificial intelligence in osteoarthritis: A systematic scoping review of current applications and future directions. Osteoarthritis Cartilage. Published 11 March 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →