EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Generative AI mitigates representation bias and improves model fairness through synthetic health data

Raffaele Marchesi iD, Nicolo Micheletti, Nicholas I-Hsien Kuo, Sebastiano Barbieri iD, Giuseppe Jurman iD, Venet Osmani iD

PLOS Computational Biology · 19.05.2025 · 21 (5) · e1013080

DOI: 10.1371/journal.pcbi.1013080 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 19.05.2025. Verfasst von Raffaele Marchesi und 5 weiteren Autor:innen. Beteiligte Einrichtung: Data Science for Health (DSH), Fondazione Bruno Kessler, Trento, Italy. Hauptthemen laut MEDLINE: Artificial Intelligence. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Representation bias in health data can lead to unfair decisions and compromise the generalisability of research findings. As a consequence, underrepresented subpopulations, such as those from specific ethnic backgrounds or genders, do not benefit equally from clinical discoveries. Several approaches have been developed to mitigate representation bias, ranging from simple resampling methods, such as SMOTE, to recent approaches based on generative adversarial networks (GAN). However, generating high-dimensional time-series synthetic health data remains a significant challenge. In response, we devised a novel architecture (CA-GAN) that synthesises authentic, high-dimensional time series data. CA-GAN outperforms state-of-the-art methods in a qualitative and a quantitative evaluation while avoiding mode collapse, a serious GAN failure. We perform evaluation using 7535 patients with hypotension and sepsis from two diverse, real-world clinical datasets. We show that synthetic data generated by our CA-GAN improves model fairness in Black patients as well as female patients when evaluated separately for each subpopulation. Furthermore, CA-GAN generates authentic data of the minority class while faithfully maintaining the original distribution of data, resulting in improved performance in a downstream predictive task.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceHumansFemaleComputational BiologyMaleSepsisBias

Autor:innen und Institutionen

  • Data Science for Health (DSH), Fondazione Bruno Kessler, Trento, Italy.
  • Department of Mathematics, University of Pavia, Pavia, Italy.
  • Department of Computer Science, University of Manchester, Manchester, United Kingdom.
  • Centre for Big Data Research in Health, University of New South Wales, Sydney, New South Wales, Australia.
  • Queensland Digital Health Centre, University of Queensland, Brisbane, Queensland, Australia.
  • Department of Biomedical Sciences, Humanitas University, Milan, Italy.

ORCID-Profile: Raffaele Marchesi, Sebastiano Barbieri, Giuseppe Jurman, Venet Osmani

Zitieren

APA

Marchesi, R., Micheletti, N., I-Hsien Kuo, N., Barbieri, S., Jurman, G., & Osmani, V. (2025). Generative AI mitigates representation bias and improves model fairness through synthetic health data. PLOS Computational Biology, 21(5), e1013080. https://doi.org/10.1371/journal.pcbi.1013080

Vancouver

Marchesi R, Micheletti N, I-Hsien Kuo N, Barbieri S, Jurman G, Osmani V. Generative AI mitigates representation bias and improves model fairness through synthetic health data. PLOS Computational Biology. 2025;21(5):e1013080. doi:10.1371/journal.pcbi.1013080

BibTeX
@article{Marchesi2025,
  author = {Marchesi, Raffaele and Micheletti, Nicolo and I-Hsien Kuo, Nicholas and Barbieri, Sebastiano and Jurman, Giuseppe and Osmani, Venet},
  title = {Generative AI mitigates representation bias and improves model fairness through synthetic health data},
  journal = {PLOS Computational Biology},
  year = {2025},
  volume = {21},
  number = {5},
  pages = {e1013080},
  doi = {10.1371/journal.pcbi.1013080}
}
Kostenlos starten →