Article

Evaluating Fidelity and Machine Learning Utility of Synthetic Tabular Data Generated Using Generative Models

2025-09-17

Abstract excerpt

<title>Abstract</title> <p>Synthetic tabular data offers a promising solution for enabling privacy-preserving machine learning in sensitive domains such as healthcare. However, assessing the fidelity and utility of such data remains challenging. In this study, we evaluate four generative models—CTGAN, TVAE, Gaussian Copula, and CopulaGAN—on a benchmark dataset for stroke prediction. We propose a two-phase generat...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 9ec5ea14-2676-54f2-ae5e-9e17c18e7301
DOI: 10.21203/rs.3.rs-7287372/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Evaluating Fidelity and Machine Learning Utility of Synthetic Tabular Data Generated Using Generative ModelsDOI 10.21203/rs.3.rs-7287372/v1Read

A Multidimensional Evaluation of Privacy-Preserving Generative Models for Neonatal Clinical Tabular Data: Fidelity, Utility, and Realism Trade-offsSemantic proximity Read

The Synthetic Fidelity–Stability Framework (SFSF): A Systematic Multi-Dimensional Benchmark of Synthetic Clinical Laboratory Data GeneratorsSemantic proximity Read

Synthesising artificial patient-level data for Open Science - an evaluation of five methodsSemantic proximity Read

Exploring the Role of Synthetic Data in the Future of AI in Healthcare: A Scoping Review of Frameworks, Challenges, and ImplicationsSemantic proximity Read

A Multidimensional Benchmark of Generative Models for Neonatal Clinical Tabular Data: Trade-offs in Fidelity, Utility, and RealismSemantic proximity Read

Revolutionizing Personalized Medicine with Generative AI: A Systematic ReviewSemantic proximity Read

Generating synthetic electronic health record data: a methodological scoping review with benchmarking on phenotype data and open-source software.Semantic proximity Read

Mending Synthetic Healthcare Data with MAPS: Model Agnostic Post-hoc Synthetic Data Refinement FrameworkSemantic proximity Read

TabGraphSyn: Graph-Guided Latent Diffusion for High-Fidelity and Privacy-Conscious Clinical Data GenerationSemantic proximity Read

Utility is all you need: fidelity-agnostic synthetic data generationSemantic proximity Read

Synthetic Longitudinal Tabular Data Generation via CopulaSemantic proximity Read

Generating virtual patient data for in silico clinical trials of medical devices during extracorporeal membrane oxygenation treatmentSemantic proximity Read