STNG (Synthetic Tabular Neural Generator): A Novel and Fully Automated Platform for Synthetic Tabular Data Generation and Validation

Abstract Healthcare data accessibility for machine learning (ML) is encumbered by a range of stringent regulations and limitations. Using synthetic data that mirrors the underlying properties in the real data is emerging as a promising solution to overcome these barriers. To address this, we introduce a novel approach: a fully automated Synthetic Tabular Neural Generator (STNG). This innovative tool not only generates synthetic data that closely mirrors the characteristics of actual data but also incorporates an Auto-ML module for rigorous validation and comparison of datasets synthesized using various methodologies. To showcase STNG's efficacy, we conducted an extensive empirical study across twelve distinct datasets. The results highlight STNG's robustness and its pivotal role in enhancing the accessibility of validated synthetic healthcare data, thereby offering a promising solution to a critical barrier in ML applications in healthcare.