The Problem of Fairness in Synthetic Healthcare Data
Open accessThe DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Abstract
Access to healthcare data such as electronic health records (EHR) is often restricted by laws established to protect patient privacy. These restrictions hinder the reproducibility of existing results based on private healthcare data and also limit new research. Synthetically-generated healthcare data solve this problem by preserving privacy and enabling researchers and policymakers to drive decisions and methods based on realistic data. Healthcare data can include information about multiple in- and out- patient visits of patients, making it a time-series dataset which is often influenced by protected attributes like age, gender, race etc. The COVID-19 pandemic has exacerbated health inequities, with certain subgroups experiencing poorer outcomes and less access to healthcare. To combat these inequities, synthetic data must “fairly” represent diverse minority subgroups such that the conclusions drawn on synthetic data are correct and the results can be generalized to real data. In this article, we develop two fairness metrics for synthetic data, and analyze all subgroups defined by protected attributes to analyze the bias in three published synthetic research datasets. These covariate-level disparity metrics revealed that synthetic data may not be representative at the univariate and multivariate subgroup-levels and thus, fairness should be addressed when developing data generation methods. We discuss the need for measuring fairness in synthetic healthcare data to enable the development of robust machine learning models to create more equitable synthetic healthcare datasets.
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.
Integrity signals
Registry
Cites
Statistics
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.
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
Cites
Certifying and Removing Disparate Impact
Feldman, M., Friedler, S. A., Moeller, J., Scheidegger, C., & Venkatasubramanian, S. (2015) · Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2783258.2783311 · Cited by 1,827
Bellamy, R. K. E., Dey, K., Hind, M., Hoffman, S. C., Houde, S., Kannan, K., Lohia, P., Martino, J., Mehta, S., Mojsilovic, A., et al. (2018) · arXiv · doi:10.48550/arxiv.1810.01943 · Cited by 1,581
Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting
Yeom, S., Giacomelli, I., Fredrikson, M., & Jha, S. (2018) · 2018 IEEE 31st Computer Security Foundations Symposium (CSF) · doi:10.1109/csf.2018.00027 · Cited by 1,001
Inherent Trade-Offs in the Fair Determination of Risk Scores
Kleinberg, J., Mullainathan, S., & Raghavan, M. (2016) · arXiv · doi:10.48550/arxiv.1609.05807 · Cited by 941
AI Fairness 360: An extensible toolkit for detecting and mitigating algorithmic bias
Bellamy, R. K. E., Dey, K., Hind, M., Hoffman, S. C., Houde, S., Kannan, K., Lohia, P., Martino, J., Mehta, S., Mojsilović, A., et al. (2019) · IBM Journal of Research and Development · doi:10.1147/jrd.2019.2942287 · Cited by 884
Electronic health records to facilitate clinical research
Cowie, M. R., Blomster, J. I., Curtis, L. H., Duclaux, S., Ford, I., Fritz, F., Goldman, S., Janmohamed, S., Kreuzer, J., Leenay, M., et al. (2017) · Clinical Research in Cardiology · doi:10.1007/s00392-016-1025-6 · Cited by 651 · cited 1×
“For example, electronic medical records (EMRs) can enhance patient care, reduce costs, identify eligible patients easily and improve research efficiency [1].”
BackgroundThe Measure and Mismeasure of Fairness
Corbett-Davies, S., Gaebler, J. D., Nilforoshan, H., Shroff, R., & Goel, S. (2018) · arXiv · doi:10.48550/arxiv.1808.00023 · Cited by 444
Big Data in Public Health: Terminology, Machine Learning, and Privacy
Mooney, S. J., & Pejaver, V. (2018) · Annual Review of Public Health · doi:10.1146/annurev-publhealth-040617-014208 · Cited by 325 · cited 1×
“Use of supervised and unsupervised machine learning on public health data has been used for outbreak detection, hospital readmission, feature association with outcomes and more [4].”
Background50 Years of Test (Un)fairness: Lessons for Machine Learning
Hutchinson, B., & Mitchell, M. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287600 · Cited by 297
Fairness GAN: Generating datasets with fairness properties using a generative adversarial network
Sattigeri, P., Hoffman, S. C., Chenthamarakshan, V., & Varshney, K. R. (2019) · IBM Journal of Research and Development · doi:10.1147/jrd.2019.2945519 · Cited by 134
Differentially Private Fair Learning
Jagielski, M., Kearns, M., Mao, J., Oprea, A., Roth, A., Sharifi-Malvajerdi, S., & Ullman, J. (2018) · arXiv · doi:10.48550/arxiv.1812.02696 · Cited by 62
Vargason, T., Frye, R. E., McGuinness, D. L., & Hahn, J. (2019) · Autism Research · doi:10.1002/aur.2128 · Cited by 59 · cited 2×
“The ASD claims data include records of children having multiple diagnosis across a 5-year period used in [42] with synthetic data generated using HealthGAN [20].”
BackgroundMethodQuantifying representativeness in randomized clinical trials using machine learning fairness metrics
Qi, M., Cahan, O., Foreman, M. A., Gruen, D. M., Das, A. K., & Bennett, K. P. (2021) · JAMIA Open · doi:10.1093/jamiaopen/ooab077 · Cited by 27
Self-citation
Cited by
AI-powered therapeutic target discovery
Pun, F. W., Ozerov, I. V., & Zhavoronkov, A. (2023) · Trends in Pharmacological Sciences · doi:10.1016/j.tips.2023.06.010 · Cited by 341
AI Fairness in Data Management and Analytics: A Review on Challenges, Methodologies and Applications
Chen, P., Wu, L., & Wang, L. (2023) · Applied Sciences · doi:10.3390/app131810258 · Cited by 155
Algorithmic fairness of machine learning models for Alzheimer disease progression
Yuan, C., Linn, K. A., & Hubbard, R. A. (2023) · JAMA Network Open · doi:10.1001/jamanetworkopen.2023.42203 · Cited by 49
Bias Mitigation in Primary Health Care Artificial Intelligence Models: Scoping Review
Sasseville, M., Ouellet, S., Rhéaume, C., Sahlia, M., Couture, V., Després, P., Paquette, J.-S., Darmon, D., Bergeron, F., & Gagnon, M.-P. (2025) · Journal of Medical Internet Research · doi:10.2196/60269 · Cited by 38
“The studies collectively address a wide range of protected attributes [1,8], including race or ethnicity [19,26,28-37], sex [19,20,26-31,36, 39] , age [ 19, 26, 27,29-31 These empirical findings reinforce theoretical insights that emphasize the importance of health equity between protected and…”
InfluentialFair Machine Learning in Healthcare: A Survey
Feng, Q., Du, M., Zou, N., & Hu, X. (2025) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2024.3361836 · Cited by 12
Metadata
- Authors
- Bhanot, K., Qi, M., Erickson, J. S., Guyon, I., & Bennett, K. P.
- Venue
- Entropy
- Publisher
- MDPI AG
- Published
- 2021-09-04
- Volume
- 23
- Issue
- 9
- Pages
- 1165
- ISSN
- 1099-4300 (ISSN-L)
- OpenAlex
- W3197418972
- Cited by
- 91
- References
- 13
- FWCI
- 16.99
- Type
- journal article
- Language
- en
- Open access
- gold
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
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.