Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; the references it cites are not checked yet.

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

Open access
Marchesi, Raffaele, Micheletti, Nicolo, I-Hsien Kuo, Nicholas, Barbieri, Sebastiano, Jurman, Giuseppe, Osmani, Venet · 2025 · PLOS Computational Biology

Published version of a preprint

Abstract

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.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1371/journal.pcbi.1013080

Cites

Statistics

Figures

Fig 1 Two-dimensional representations of the acute hypotension dataset for Black patients, including marginal distributions of the principal components. Top panels: PCA two-dimensional representation of real (red) and synthetic (blue) data, where CA-GAN provides the best overall coverage of real data distribution, while SMOTE and WGAN-GP* show evidence of reduced coverage and mode collapse. Bottom panels: t-SNE two-dimensional representation of real data (red) and synthetic data (blue) for the three methods SMOTE, WGAN-GP, and CA-GAN. It can be seen that CA-GAN more uniformly covers the real distribution, while SMOTE does not cover a significant part of it (top right in the panel) and WGAN-GP* coverage is almost completely separated from the real data.
Fig 1 Two-dimensional representations of the acute hypotension dataset for Black patients, including marginal distributions of the principal components. Top panels: PCA two-dimensional representation of real (red) and synthetic (blue) data, where CA-GAN provides the best overall coverage of real data distribution, while SMOTE and WGAN-GP* show evidence of reduced coverage and mode collapse. Bottom panels: t-SNE two-dimensional representation of real data (red) and synthetic data (blue) for the three methods SMOTE, WGAN-GP, and CA-GAN. It can be seen that CA-GAN more uniformly covers the real distribution, while SMOTE does not cover a significant part of it (top right in the panel) and WGAN-GP* coverage is almost completely separated from the real data.CC BY · PubMed Central
Fig 2 Two-dimensional representations of the sepsis dataset for Black patients, including marginal distributions of the principal components. Top panels: PCA two-dimensional representation of real (red) and synthetic (blue) data, where CA-GAN provides more coverage than SMOTE (especially in the top right and bottom left part of the panel), while WGAN-GP* provides the lowest coverage. Bottom panels: t-SNE two-dimensional representation of real data (red) and synthetic data (blue) for the three methods SMOTE, WGAN-GP, and CA-GAN. It can be seen that SMOTE follows an interpolation pattern, while CA-GAN expands into latent space, generating authentic data points while remaining within the clusters identified by t-SNE. Data generated by WGAN-GP* fall outside of the real data.
Fig 2 Two-dimensional representations of the sepsis dataset for Black patients, including marginal distributions of the principal components. Top panels: PCA two-dimensional representation of real (red) and synthetic (blue) data, where CA-GAN provides more coverage than SMOTE (especially in the top right and bottom left part of the panel), while WGAN-GP* provides the lowest coverage. Bottom panels: t-SNE two-dimensional representation of real data (red) and synthetic data (blue) for the three methods SMOTE, WGAN-GP, and CA-GAN. It can be seen that SMOTE follows an interpolation pattern, while CA-GAN expands into latent space, generating authentic data points while remaining within the clusters identified by t-SNE. Data generated by WGAN-GP* fall outside of the real data.CC BY · PubMed Central
Fig 3 Distribution plots[0mm][-3mm]AQ1[4mm][-3mm]AQ2 of each variable, overlaying real and synthetic data for acute hypotension dataset. Distribution of variables related to blood pressure (MAP, diastolic and systolic) is captured well by our method in comparison to WGAN-GP* and SMOTE. CA-GAN performs better also for categorical variables, while all the three methods struggle with variables with long tail, non-normal distributions. Top panel: CA-GAN. Middle panel: WGAN-GP. Bottom panel: SMOTE
Fig 3 Distribution plots[0mm][-3mm]AQ1[4mm][-3mm]AQ2 of each variable, overlaying real and synthetic data for acute hypotension dataset. Distribution of variables related to blood pressure (MAP, diastolic and systolic) is captured well by our method in comparison to WGAN-GP* and SMOTE. CA-GAN performs better also for categorical variables, while all the three methods struggle with variables with long tail, non-normal distributions. Top panel: CA-GAN. Middle panel: WGAN-GP. Bottom panel: SMOTECC BY · PubMed Central
Fig 4 Kendall’s rank correlation coefficients for the real data and the data generated with CA-GAN, WGAN-GP*, and SMOTE. Top panel: Acute hypotension data. Bottom panel: Sepsis data
Fig 4 Kendall’s rank correlation coefficients for the real data and the data generated with CA-GAN, WGAN-GP*, and SMOTE. Top panel: Acute hypotension data. Bottom panel: Sepsis dataCC BY · PubMed Central
Fig 5 Proposed architecture of our CA-GAN. The Generator and the Discriminator are two deep networks with similar structure and number of parameters. Both employ three stacked Bidirectional LSTMs (BILSTMs) to capture the temporal relationships of longitudinal data. They are trained together adversarially, with a minimax game. Conditioning is achieved with static labels, passed as input to both networks. The Generator also takes Gaussian noise as input and generates time-series data (synthetic patients). The discriminator evaluates the plausibility of the output of the Generator, compared with the real data.
Fig 5 Proposed architecture of our CA-GAN. The Generator and the Discriminator are two deep networks with similar structure and number of parameters. Both employ three stacked Bidirectional LSTMs (BILSTMs) to capture the temporal relationships of longitudinal data. They are trained together adversarially, with a minimax game. Conditioning is achieved with static labels, passed as input to both networks. The Generator also takes Gaussian noise as input and generates time-series data (synthetic patients). The discriminator evaluates the plausibility of the output of the Generator, compared with the real data.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

The citation lists are queued

They are fetched later and appear here then.

References 71 · Cited by 29

Research works printed but not linked: 5

  1. Alaa A, Van Breugel B, Saveliev ES, van der Schaar M. How faithful is your synthetic data? Sample-level metrics for evaluating and auditing generative models. In: Proceedings of the International Conference on Machine Learning. PMLR. p. 290–306.
  2. Ghosheh G, Li J, Zhu T. A review of generative adversarial networks for electronic health records: applications, evaluation measures and data sources. arXiv preprint 2022. https://arxiv.org/abs/2203.07018 · arXiv
  3. Gulrajani I, Ahmed F, Arjovsky M, Dumoulin V, Courville A. Improved training of wasserstein gans. Adv Neural Inf Process Syst. 2017.
  4. Snell J, Swersky K, Zemel R. Prototypical networks for few-shot learning. Adv Neural Inf Process Syst. 2017.
  5. Yoon J, Jarrett D, VanderSchaar M. Time-series generative adversarial networks. Adv Neural Inf Process Syst. 2019.

Metadata

Authors
Marchesi, R., Micheletti, N., I-Hsien Kuo, N., Barbieri, S., Jurman, G., & Osmani, V.
Affiliations
  • Fondazione Bruno Kessler (IT)
  • The University of Queensland (AU)
  • Humanitas University (IT)
  • Queen Mary University of London (GB)
Corresponding author
Osmani, Venet
Venue
PLOS Computational Biology
Published
2025-05-19
Volume
21
Issue
5
Pages
e1013080
ISSN
  • 1553-734X (ISSN-L)
  • 1553-7358
OpenAlex
W4410491430
Cited by
29
References
71
Citations by year
2026: 15 · 2025: 12
FWCI
10.74
Type
journal article
Language
en
Open access
Locations
  • PLoS Computational Biology (publishedVersion, cc-by)
  • medRxiv (acceptedVersion, cc-by-nd)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • RePEc: Research Papers in Economics (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Physical Sciences › Computer Science › Artificial Intelligence › Imbalanced Data Classification Techniques
Keywords
generative adversarial networks, synthetic health data, representation bias, model fairness, mode collapse, hypotension, sepsis, Black patients, female patients, clinical decision support
MeSH terms
Artificial Intelligence, Female, Humans, Male, Bias, Sepsis, Computational Biology

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Generative AI mitigates representation bias and improves model fairness through synthetic health data. https://app.cochat.ai/papers/10.1371/journal.pcbi.1013080
The paper
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. https://doi.org/10.1371/journal.pcbi.1013080

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.