EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Generative models and synthetic data in clinical prediction models: Promoting consistency, reproducibility, and transparency

Anthony A Mangino iD, Taha Ahmed, Vincent L Sorrell

Journal of Clinical and Translational Science · 2026 · 10 (1)

DOI: 10.1017/cts.2026.10729 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Clinical and Translational Science, online erschienen am 25.03.2026. Verfasst von Anthony A Mangino und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biostatistics, University of Kentucky, USA. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Reproducibility, consistency, and transparency are essential to responsible and ethical scientific inquiry, though practices supporting these qualities are often neglected. However, in many cases data are confidential or otherwise unable to be shared publicly. This tutorial describes a method utilizing generative adversarial networks (GANs) to create synthetic data that are sufficiently similar to the original dataset in such cases where the source data cannot be shared or where the source data are too sparse as to internally validate results.

Methods

Utilizing an exemplar study that aimed to create a clinical prediction model employing a novel echocardiographic measurement to differentiate between acute coronary syndrome and Takotsubo syndrome, we demonstrate the procedure of fitting a GAN and evaluating the resulting synthetic dataset against the results from the source dataset using conventional analytic methodologies. Further, we include relevant R code and output from this process to aid in implementation.

Results

The procedure we detail yielded a synthetic dataset that was largely similar to the source data used in univariate descriptive statistics, significance testing comparing variables across datasets, data visualizations, and yielded largely comparable secondary model fit and accuracy metrics.

Conclusions

We demonstrated that through the implementation of a well-tuned GAN, synthetic data can be generated as a sufficiently faithful simulacrum of the source data for the purposes of internal validation, transparency of method, and reproducibility of analytic results.

Schlagwörter

Stichwörter der Autor:innen

Generative modelingclinical prediction modelsconsistencyreproducibilitytransparency

Autor:innen und Institutionen

  • Department of Biostatistics, University of Kentucky, USA.
  • Emory University, USA.
  • Department of Internal Medicine, University of Kentucky, USA.

ORCID-Profile: Anthony A Mangino

Zitieren

APA

Mangino, A. A., Ahmed, T., & Sorrell, V. L. (2026). Generative models and synthetic data in clinical prediction models: Promoting consistency, reproducibility, and transparency. Journal of Clinical and Translational Science, 10(1). https://doi.org/10.1017/cts.2026.10729

Vancouver

Mangino AA, Ahmed T, Sorrell VL. Generative models and synthetic data in clinical prediction models: Promoting consistency, reproducibility, and transparency. Journal of Clinical and Translational Science. 2026;10(1). doi:10.1017/cts.2026.10729

BibTeX
@article{Mangino2026,
  author = {Mangino, Anthony A and Ahmed, Taha and Sorrell, Vincent L},
  title = {Generative models and synthetic data in clinical prediction models: Promoting consistency, reproducibility, and transparency},
  journal = {Journal of Clinical and Translational Science},
  year = {2026},
  volume = {10},
  number = {1},
  doi = {10.1017/cts.2026.10729}
}
Kostenlos starten →