Synthetic data in rheumatology: a systematic literature review.
5 affiliations
- 1Rheumatology Unit, Department of Precision and Regenerative Medicine-Ionian Area (DiMePRe-J), University of Bari "Aldo Moro", Bari, Italy.
- 2Division of Rheumatology, Department of Internal Medicine, Faculty of Medicine, Sakarya University, Sakarya, Turkey.
- 3Department of Rheumatology, Royal Wolverhampton NHS Trust, Wolverhampton, UK.
- 4Institute of Inflammation and Ageing, University of Birmingham, Birmingham, UK.
- 5Francis Crick Institute, Camden, London, UK.
Abstract
Objective
To systematically review the methods, validation frameworks, applications and regulatory landscape of synthetic data generation in healthcare, with a specific focus on rheumatology.Methods
We searched PubMed/MEDLINE, Embase and arXiv (January 2016-January 2026). From 1099 database records and 7 expert-identified studies, 701 remained after removing 405 duplicates. Title and abstract screening excluded 353 records; full-text assessment of 348 articles excluded 120 (E1: n = 62; E2: n = 1; E3: n = 23; E4: n = 34), yielding 228 studies. Quality assessment of 13 rheumatology-specific studies using a 10-item checklist revealed 1 high-quality, 8 moderate-quality, and 4 low-quality studies, with systematic gaps in privacy evaluation (2/13) and reproducibility (1/13).Results
The 228 included studies encompassed six generation-method categories (generative adversarial networks, diffusion models, large language models, statistical methods, rule-based simulators and hybrid approaches) and five thematic categories (digital twins, privacy-preserving methods, reviews, validation frameworks and healthcare applications), detailed in the supplementary methods. Validation remained inconsistent, with only a minority evaluating fidelity, utility and privacy simultaneously. In rheumatology, 13 studies spanned rheumatoid arthritis (n = 3), osteoarthritis (n = 3), Sjogren's syndrome (n = 2), systemic sclerosis (n = 2), systemic lupus erythematosus (n = 2) and ankylosing spondylitis (n = 1). Only 2 of 13 formally evaluated privacy and only 1 shared code for reproducibility.Conclusion
Synthetic data hold substantial promise for rheumatology, particularly for augmenting small cohorts in low-prevalence diseases, enabling privacy-preserving registry sharing and simulating clinical trial populations. Realizing this potential requires standardized validation, greater attention to privacy and reproducibility and regulatory clarity on synthetic health data.
Related
- Large language models in rheumatology: applications, methodological quality and clinical translation – a systematic review
- Efficacy of educational interventions on human brucellosis: a systematic review of the literature
- Multifactorial lifestyle interventions in rheumatoid arthritis: a systematic literature review
- Intersectional Barriers to and Facilitators of Educational Inclusion for Persons With Disabilities in Low‐ and Middle‐Income Countries: A Systematic Literature Review
- Altered immune response to exercise in patients with chronic fatigue syndrome/myalgic encephalomyelitis: A systematic literature review
BibTeX
@article{venerito2026synthetic,
title = {{Synthetic data in rheumatology: a systematic literature review.}},
author = {Vincenzo Venerito and Maria Morrone and Sergio Del Vescovo and Emre Bilgin and Latika Gupta and Giuseppe Lopalco and Florenzo Iannone},
journal = {Rheumatology advances in practice},
year = {2026},
month = sep,
doi = {10.1093/rap/rkag114},
url = {https://europepmc.org/article/MED/42903943},
note = {CC BY},
}
RIS
TY - JOUR
TI - Synthetic data in rheumatology: a systematic literature review.
AU - Vincenzo Venerito
AU - Maria Morrone
AU - Sergio Del Vescovo
AU - Emre Bilgin
AU - Latika Gupta
AU - Giuseppe Lopalco
AU - Florenzo Iannone
PY - 2026
DA - 2026/09/25
JO - Rheumatology advances in practice
DO - 10.1093/rap/rkag114
UR - https://europepmc.org/article/MED/42903943
AB - Objective To systematically review the methods, validation frameworks, applications and regulatory landscape of synthetic data generation in healthcare, with a specific focus on rheumatology.Methods We searched PubMed/MEDLINE, Embase and arXiv (January 2016-January 2026). From 1099 database records and 7 expert-identified studies, 701 remained after removing 405 duplicates. Title and abstract screening excluded 353 records; full-text assessment of 348 articles excluded 120 (E1: n = 62; E2: n = 1; E3: n = 23; E4: n = 34), yielding 228 studies. Quality assessment of 13 rheumatology-specific studies using a 10-item checklist revealed 1 high-quality, 8 moderate-quality, and 4 low-quality studies, with systematic gaps in privacy evaluation (2/13) and reproducibility (1/13).Results The 228 included studies encompassed six generation-method categories (generative adversarial networks, diffusion models, large language models, statistical methods, rule-based simulators and hybrid approaches) and five thematic categories (digital twins, privacy-preserving methods, reviews, validation frameworks and healthcare applications), detailed in the supplementary methods. Validation remained inconsistent, with only a minority evaluating fidelity, utility and privacy simultaneously. In rheumatology, 13 studies spanned rheumatoid arthritis (n = 3), osteoarthritis (n = 3), Sjogren's syndrome (n = 2), systemic sclerosis (n = 2), systemic lupus erythematosus (n = 2) and ankylosing spondylitis (n = 1). Only 2 of 13 formally evaluated privacy and only 1 shared code for reproducibility.Conclusion Synthetic data hold substantial promise for rheumatology, particularly for augmenting small cohorts in low-prevalence diseases, enabling privacy-preserving registry sharing and simulating clinical trial populations. Realizing this potential requires standardized validation, greater attention to privacy and reproducibility and regulatory clarity on synthetic health data.
SN - 2514-1775
ER -