EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SynthCraft: An AI partner for synthetic data generation to support data access and augmentation in healthcare

Thomas Callender iD, Anders Boyd, Robert Davis, Silas Ruhrberg Estevez, Juan M Lavista Ferres, Mihaela van der Schaar

PLOS Digital Health · 09.03.2026 · 5 (3) · e0001290

DOI: 10.1371/journal.pdig.0001290 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Digital Health, online erschienen am 09.03.2026. Verfasst von Thomas Callender und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Public Health and Primary Care, University of Cambridge, Cambridge, United Kingdom. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Access to high-quality data provides the foundation for biomedical research. But data access is often limited or challenging due to privacy constraints, whilst the data themselves may be unrepresentative or sparse. Synthetic data can support both privacy-preserving data access and advanced analytical workflows, including data augmentation or the development of digital twins. However, the use of synthetic data remains limited due to the complexity of the methods themselves, their use, and their evaluation. To address this, we developed SynthCraft, an AI tool to support the principled, transparent, application of state-of-the-art synthetic data generation methods. SynthCraft couples a reinforcement learning-based reasoning engine with large language models (LLMs) to orchestrate the workflow necessary for the generation of synthetic data based on dynamic interaction with the user through natural language. We demonstrate the capability of SynthCraft with both tabular and genomic datasets: the National Health and Nutrition Examination Survey (NHANES) and the Cancer Genome Atlas (TCGA). Using SynthCraft, we analysed the privacy, statistical fidelity, and downstream utility of four different synthetic data generators both with and without explicit privacy-preserving designs when applied to both the NHANES and TCGA datasets. We show that how different generators perform differently – and that no single method was optimal – across varying use-cases and datasets. Furthermore, we demonstrate how SynthCraft can be used for data augmentation as part of a workflow to attempt to mitigate imbalances in the proportion of individuals from different ethnic backgrounds. In conclusion, a human-in-the-loop AI partner using LLMs can support the generation of synthetic datasets. Such tools could improve the quality, reproducibility, and transparency of research methods, whilst increasing their accessibility. Research into their use across different methodological areas is warranted.

Autor:innen und Institutionen

  • Department of Public Health and Primary Care, University of Cambridge, Cambridge, United Kingdom.
  • Cambridge Centre for AI in Medicine, University of Cambridge, Cambridge, United Kingdom.
  • Department of Infectious Diseases, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland.
  • Amsterdam UMC location University of Amsterdam, Department of Infectious Diseases, Meibergdreef 9, Amsterdam, The Netherlands.
  • Amsterdam Institute for Immunology and Infectious Diseases, Infectious Diseases, Amsterdam, The Netherlands.
  • Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Cambridge, United Kingdom.

ORCID-Profile: Thomas Callender

Zitieren

APA

Callender, T., Boyd, A., Davis, R., Ruhrberg Estevez, S., Lavista Ferres, J. M., & van der Schaar, M. (2026). SynthCraft: An AI partner for synthetic data generation to support data access and augmentation in healthcare. PLOS Digital Health, 5(3), e0001290. https://doi.org/10.1371/journal.pdig.0001290

Vancouver

Callender T, Boyd A, Davis R, Ruhrberg Estevez S, Lavista Ferres JM, van der Schaar M. SynthCraft: An AI partner for synthetic data generation to support data access and augmentation in healthcare. PLOS Digital Health. 2026;5(3):e0001290. doi:10.1371/journal.pdig.0001290

BibTeX
@article{Callender2026,
  author = {Callender, Thomas and Boyd, Anders and Davis, Robert and Ruhrberg Estevez, Silas and Lavista Ferres, Juan M and van der Schaar, Mihaela},
  title = {SynthCraft: An AI partner for synthetic data generation to support data access and augmentation in healthcare},
  journal = {PLOS Digital Health},
  year = {2026},
  volume = {5},
  number = {3},
  pages = {e0001290},
  doi = {10.1371/journal.pdig.0001290}
}
Kostenlos starten →