EUVIMEDEUVIMED entdecken
Systematische ÜbersichtOpen Access · CC BY 4.0

Translation readiness of model-based synthetic tabular data in healthcare: a systematic review and governance audit

Simone Castagno iD, Alagu Subramanian iD, Ilias E Epanomeritakis iD, Benjamin Gompels, Stephen McDonnell iD, Mark Birch, Mihaela van der Schaar iD, Andrew McCaskie iD

Journal of the American Medical Informatics Association · 2026

DOI: 10.1093/jamia/ocag102 ↗

Kurz gefasst

Systematische Übersicht in der Zeitschrift Journal of the American Medical Informatics Association, 2026. Verfasst von Simone Castagno und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Surgery, University of Cambridge, Cambridge, CB2 0QQ, United Kingdom. Hauptthemen laut MEDLINE: Medical Informatics. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Louis and Valerie Freedman Studentship in Medical Sciences from Trinity College Cambridge and the ORUK/Versus Arthritis: AI in MSK Research Fellowship, NIHR Cambridge Biomedical Research Center, Cambridge Center for AI in Medicine.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

To evaluate the clinical applications and translation readiness of model-based synthetic tabular data in healthcare, and identify gaps in governance reporting that may hinder translation. Materials and Methods We systematically searched Ovid MEDLINE and Embase (2010-August 2025; PROSPERO: CRD42025635514) for studies that generated and applied model-based synthetic tabular data in clinical contexts. Screening used a “human-in-the-loop” large language model workflow alongside independent manual review, achieving 100% sensitivity for included studies. Unlike prior reviews focused primarily on evaluation methodology, we mapped use-cases and deployment paradigms, and audited translation-readiness reporting using a predefined governance framework (validation depth, privacy, fairness, regulatory alignment).

Results

Thirty-seven studies (2019-2025) were included. GANs predominated; other approaches included VAEs, diffusion models, LLM-based synthesis, and Bayesian networks. Dataset augmentation was the primary application, often improving downstream model performance for rare outcomes. Emerging applications included synthetic control cohorts and algorithmic bias mitigation. Translation-readiness reporting was limited: 34/37 studies (92%) relied solely on internal validation, 9/37 (24%) used formal privacy models, 6/37 (16%) reported explicit fairness evaluations, and 6/37 (16%) addressed regulatory alignment. Few studies distinguished “no-release” from “delayed-release” paradigms.

Discussion

A systemic gap exists between methodological innovation and deployment-readiness reporting. Model-based synthetic data show clear value for augmentation and class balancing, but inconsistent reporting of validation, privacy, fairness, and regulatory considerations limits confidence in clinical deployment.

Conclusion

We propose TRUST-SD (Transparency and Reporting for Utility, Safety, and Translation of Synthetic Data), an author-derived, preliminary, evidence-informed reporting checklist spanning 7 domains, as a starting point for community refinement and consensus-building.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Medical InformaticsHumansGenerative Adversarial NetworksLarge Language Models

Stichwörter der Autor:innen

generative AIgovernance and translation readinessprivacysynthetic datasystematic review

Autor:innen und Institutionen

  • Department of Surgery, University of Cambridge, Cambridge, CB2 0QQ, United Kingdom.
  • Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Cambridge, CB3 0WA, United Kingdom.

ORCID-Profile: Simone Castagno, Alagu Subramanian, Ilias E Epanomeritakis, Stephen McDonnell, Mihaela van der Schaar, Andrew McCaskie

Förderung

  • Louis and Valerie Freedman Studentship in Medical Sciences from Trinity College Cambridge and the ORUK/Versus Arthritis: AI in MSK Research Fellowship
  • NIHR Cambridge Biomedical Research Center
  • Cambridge Center for AI in Medicine
  • AstraZeneca
  • GSK
  • University of Cambridge Harding
  • Onassis Foundation Scholarship
  • Churchill Scholarship of the Winston Churchill Foundation of the United States

Zitieren

APA

Castagno, S., Subramanian, A., Epanomeritakis, I. E., Gompels, B., McDonnell, S., Birch, M., van der Schaar, M., & McCaskie, A. (2026). Translation readiness of model-based synthetic tabular data in healthcare: a systematic review and governance audit. Journal of the American Medical Informatics Association. https://doi.org/10.1093/jamia/ocag102

Vancouver

Castagno S, Subramanian A, Epanomeritakis IE, Gompels B, McDonnell S, Birch M, et al. Translation readiness of model-based synthetic tabular data in healthcare: a systematic review and governance audit. Journal of the American Medical Informatics Association. 2026. doi:10.1093/jamia/ocag102

BibTeX
@article{Castagno2026,
  author = {Castagno, Simone and Subramanian, Alagu and Epanomeritakis, Ilias E and Gompels, Benjamin and McDonnell, Stephen and Birch, Mark and van der Schaar, Mihaela and McCaskie, Andrew},
  title = {Translation readiness of model-based synthetic tabular data in healthcare: a systematic review and governance audit},
  journal = {Journal of the American Medical Informatics Association},
  year = {2026},
  doi = {10.1093/jamia/ocag102}
}
Kostenlos starten →