What question did this study set out to answer?

The aim is to create synthetic data using generative adversarial networks to improve reproducibility and transparency in clinical prediction models.

Generative Models and Synthetic Data in Clinical Prediction Models: Promoting Consistency, Reproducibility, and Transparency

View Full Paper

Ask AI

Bookmark

Authors

This tutorial demonstrates generating synthetic data for clinical prediction, enhancing reproducibility and transparency.

The aim is to create synthetic data using generative adversarial networks to improve reproducibility and transparency in clinical prediction models.
Demonstrated procedure using a clinical prediction model with echocardiographic measurements.
Utilized generative adversarial networks (GANs) to create synthetic datasets.
Evaluated the synthetic dataset against original source data using conventional analytic methodologies.
Yielded synthetic data closely resembling the source data in univariate descriptive statistics.
Achieved comparable results in significance testing between datasets.
Produced similar secondary model fit and accuracy metrics.

Mangino et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark