Large language models in rheumatology-centered research: A scoping review of model openness and reporting practices
Authors' conclusion
LLM-based rheumatology research largely depends on closed models with inconsistent reporting of reproducibility-critical details and minimal code sharing.
Study context
- Population
- English-language peer-reviewed original rheumatology research using large language models (LLMs), PubMed/MEDLINE, 1 November 2022 to 23 January 2026185 records screened
- Participants
- 63 studies
- Outcome
- Model openness and reporting practices
Methodological detailsdual independent screening, LLM-assisted data extraction verified by authors
- Dual independent screening
- LLM-assisted data extraction verified by authors
Main finding
As reported in the abstract
- Closed/proprietary LLMs
- n = 50/63; 79.37%
- Exclusive use of open-weight models
- n = 4/63; 6.35%
- Hybrid use
- n = 9/63; 14.29%
- OpenAI models
- n = 55/63; 87.30%
- Interaction language not reported
- n = 42/63; 66.67%
- Access mode reported
- n = 19/63; 30.16%
- Output generation date reported
- n = 33/63; 52.38%
- Prompts shared
- n = 48/63; 76.19%
- Code publicly available
- n = 4/63; 6.35%
- Data publicly available
- n = 13/63; 20.63%
Further findings
Study focus
- Research-focused
- n = 26/63; 41.27%
- Education-focused
- n = 20/63; 31.75%
Original publication
Large language models in rheumatology-centered research: A scoping review of model openness and reporting practices. Semin Arthritis Rheum. Published 9 May 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →