CTGAN-driven synthetic data generation: A multidisciplinary, expert-guided approach (TIMA)
Computer Methods and Programs in Biomedicine · 2025-02 · 259 · 108523
DOI: 10.1016/j.cmpb.2024.108523 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Methods and Programs in Biomedicine, 2025-02. Verfasst von Orlando Parise und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Cardiac Surgery, Universitair Ziekenhuis Brussel, Laarbeeklaan 101, Brussels 1090, Belgium; Cardiovascular Research Institute Maastrich…. Hauptthemen laut MEDLINE: COVID-19. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 26 Literaturangaben.
Abstract (Originalsprache)
OBJECTIVE: We generated synthetic data starting from a population of two hundred thirty-eight adults SARS-CoV-2 positive patients admitted to the University Hospital of Brussels, Belgium, in 2020, utilizing a Conditional Tabular Generative Adversarial Network (CTGAN)-based technique with the aim of testing the performance, representativeness, realism, novelty, and diversity of synthetic data generated from a small patient sample. A Multidisciplinary Approach (TIMA) incorporates active participation from a medical team throughout the various stages of this process. METHODS: The TIMA committee scrutinized data for inconsistencies, implementing stringent rules for variables unlearned by the system. A sensitivity analysis determined 100,000 epochs, leading to the generation of 10,000 synthetic data. The model's performance was tested using a general-purpose dataset, comparing real and synthetic data. RESULTS: Outcomes indicate the robustness of our model, with an average contingency score of 0.94 across variable pairs in synthetic and real data. Continuous variables exhibited a median correlation similarity score of 0.97. Novelty received a top score of 1. Principal Component Analysis (PCA) on synthetic values demonstrated diversity, as no patient pair displayed a zero or close-to-zero value distance. Remarkably, the TIMA committee's evaluation revealed that synthetic data was recognized as authentic by nearly 100%. CONCLUSIONS: Our trained model exhibited commendable performance, yielding high representativeness in the synthetic dataset compared to the original. The synthetic dataset proved realistic, boasting elevated levels of novelty and diversity.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Cardiac Surgery, Universitair Ziekenhuis Brussel, Laarbeeklaan 101, Brussels 1090, Belgium; Cardiovascular Research Institute Maastricht (CARIM), Maastricht University, Universiteitssingel 50, Maastricht 6…
- Department of Cardiac Surgery, Universitair Ziekenhuis Brussel, Laarbeeklaan 101, Brussels 1090, Belgium.
- Cardiovascular Research Institute Maastricht (CARIM), Maastricht University, Universiteitssingel 50, Maastricht 6229 ER, the Netherlands.
- Heart Rhythm Management Centre, Postgraduate in Cardiac Electrophysiology and Pacing, Universitair Ziekenhuis Brussel, Laarbeeklaan 101, Brussels 1090, Belgium.
Zitieren
APA
Parise, O., Kronenberger, R., Parise, G., de Asmundis, C., Gelsomino, S., & La Meir, M. (2025). CTGAN-driven synthetic data generation: A multidisciplinary, expert-guided approach (TIMA). Computer Methods and Programs in Biomedicine, 259, 108523. https://doi.org/10.1016/j.cmpb.2024.108523
Vancouver
Parise O, Kronenberger R, Parise G, de Asmundis C, Gelsomino S, La Meir M. CTGAN-driven synthetic data generation: A multidisciplinary, expert-guided approach (TIMA). Computer Methods and Programs in Biomedicine. 2025;259:108523. doi:10.1016/j.cmpb.2024.108523
BibTeX
@article{Parise2025,
author = {Parise, Orlando and Kronenberger, Rani and Parise, Gianmarco and de Asmundis, Carlo and Gelsomino, Sandro and La Meir, Mark},
title = {CTGAN-driven synthetic data generation: A multidisciplinary, expert-guided approach (TIMA)},
journal = {Computer Methods and Programs in Biomedicine},
year = {2025},
volume = {259},
pages = {108523},
doi = {10.1016/j.cmpb.2024.108523}
}
EUVIMED