CoChat
Sign Up
Cited by 63Privacy-Preserving Technologies in DataEthics and Social Impacts of AIMachine Learning in Healthcare

Improving Fairness in AI Models on Electronic Health Records: The Case for Federated Learning Methods

Open access
Poulain, Raphael, Bin Tarek, Mirza Farhan, Beheshti, Rahmatollah·2023·2023 ACM Conference on Fairness Accountability and Transparency
DOI 10.1145/3593013.3594102PMC PMC10661580
Open this paper in CoChat — free accountOpen PDF

Abstract

Developing AI tools that preserve fairness is of critical importance, specifically in high-stakes applications such as those in healthcare. However, health AI models' overall prediction performance is often prioritized over the possible biases such models could have. In this study, we show one possible approach to mitigate bias concerns by having healthcare institutions collaborate through a federated learning paradigm (FL; which is a popular choice in healthcare settings). While FL methods with an emphasis on fairness have been previously proposed, their underlying model and local implementation techniques, as well as their possible applications to the healthcare domain remain widely underinvestigated. Therefore, we propose a comprehensive FL approach with adversarial debiasing and a fair aggregation method, suitable to various fairness metrics, in the healthcare domain where electronic health records are used. Not only our approach explicitly mitigates bias as part of the optimization process, but an FL-based paradigm would also implicitly help with addressing data imbalance and increasing the data size, offering a practical solution for healthcare applications. We empirically demonstrate our method's superior performance on multiple experiments simulating large-scale real-world scenarios and compare it to several baselines. Our method has achieved promising fairness performance with the lowest impact on overall discrimination performance (accuracy). Our code is available at https://github.com/healthylaife/FairFedAvg.

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

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Integrity signals

Registry

Crossref · 10.1145/3593013.3594102

Cites

Statistics

Claims the paper makes

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

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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?

  • Integrating multi-level fairness techniques can achieve substantial improvements in fairness between groups with only minimal trade-offs in model accuracy.

    “Other research similarly indicates that integrating multi-level fairness techniques can achieve substantial improvements in fairness between groups with only minimal trade-offs in model accuracy [14,15].”

    From Advancing Health Equity through Multi-Level Fairness in Health Informatics (2026) · cites this paper as [14]

Self-check

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

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

The citation lists haven’t been fetched yet

References 36 · Cited by 63

Research works printed but not linked: 41

  1. Annie Abay, Yi Zhou, Nathalie Baracaldo, Shashank Rajamoni, Ebube Chuba, and Heiko Ludwig. 2020. Mitigating Bias in Federated Learning. https://doi.org/ 10.48550/ARXIV.2012.02447 · DOI
  2. Alekh Agarwal, Miroslav Dudik, and Zhiwei Steven Wu. 2019. Fair Regression: Quantitative Definitions and Reduction-Based Algorithms. In Proceedings of the 36th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 97), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, 120-129. https://proceedings.mlr.press/v97/agarwal19d.html
  3. Muhammad Aurangzeb Ahmad, Arpit Patel, Carly Eckert, Vikas Kumar, and Ankur Teredesai. 2020. Fairness in Machine Learning for Healthcare. https: //doi.org/10.1145/3394486.3406461 · DOI
  4. Daniel J Beutel, Taner Topal, Akhil Mathur, Xinchi Qiu, Titouan Parcollet, and Nicholas D Lane. 2020. Flower: A Friendly Federated Learning Research Frame- work. arXiv preprint arXiv:2007.14390 (2020). · arXiv
  5. Trenton Chang, Michael W. Sjoding, and Jenna Wiens. 2022. Disparate Censorship & Undertesting: A Source of Label Bias in Clinical Machine Learning. https: //doi.org/10.48550/ARXIV.2208.01127 · DOI
  6. Irene Y. Chen, Fredrik D. Johansson, and David Sontag. 2018. Why is My Classifier Discriminatory?. In Proceedings of the 32nd International Conference on Neural Information Processing Systems (Montréal, Canada) (NIPS'18).
  7. Richard J. Chen, Tiffany Y. Chen, Jana Lipková, Judy J. Wang, Drew F. K. Williamson, Ming Y. Lu, Sharifa Sahai, and Faisal Mahmood. 2021. Algo- rithm Fairness in AI for Medicine and Healthcare. CoRR abs/2110.00603 (2021). arXiv:2110.00603 https://arxiv.org/abs/2110.00603 · arXiv
  8. Ramon Correa, Jiwoong Jason Jeong, Bhavik Patel, Hari Trivedi, Judy W. Gichoya, and Imon Banerjee. 2021. Two-step adversarial debiasing with partial learning - medical image case-studies. https://doi.org/10.48550/ARXIV.2111.08711 · DOI
  9. Trung Kien Dang, Xiang Lan, Jianshu Weng, and Mengling Feng. 2022. Federated Learning for Electronic Health Records. ACM Transactions on Intelligent Systems and Technology (TIST) (2022).
  10. Emily Diana, Wesley Gill, Michael Kearns, Krishnaram Kenthapadi, and Aaron Roth. 2020. Minimax Group Fairness: Algorithms and Experiments. https: //doi.org/10.48550/ARXIV.2011.03108 · DOI
  11. Yanai Elazar and Yoav Goldberg. 2018. Adversarial Removal of Demographic Attributes from Text Data. In Proceedings of the 2018 Conference on Empirical Meth- ods in Natural Language Processing. Association for Computational Linguistics, Brussels, Belgium, 11-21. https://doi.org/10.18653/v1/D18-1002 · DOI
  12. Yahya H Ezzeldin, Shen Yan, Chaoyang He, Emilio Ferrara, and Salman Aves- timehr. 2021. Fairfed: Enabling group fairness in federated learning. arXiv preprint arXiv:2110.00857 (2021). · arXiv
  13. Qizhang Feng, Mengnan Du, Na Zou, and Xia Hu. 2022. Fair Machine Learning in Healthcare: A Review. https://doi.org/10.48550/ARXIV.2206.14397 · DOI · Paper page
  14. Hrayr Harutyunyan, Hrant Khachatrian, David C. Kale, Greg Ver Steeg, and Aram Galstyan. 2019. Multitask learning and benchmarking with clinical time series data. Scientific Data 6, 1 (2019). https://doi.org/10.1038/s41597-019-0103-9 · DOI · Paper page
  15. Junyuan Hong, Zhuangdi Zhu, Shuyang Yu, Zhangyang Wang, Hiroko H. Dodge, and Jiayu Zhou. 2021. Federated Adversarial Debiasing for Fair and Transferable Representations. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (Virtual Event, Singapore) (KDD '21). Association for Computing Machinery, New York, NY, USA, 617-627. https://doi.org/10.1145/ 3447548.3467281 · DOI
  16. Junyuan Hong, Zhuangdi Zhu, Shuyang Yu, Zhangyang Wang, Hiroko H Dodge, and Jiayu Zhou. 2021. Federated adversarial debiasing for fair and transferable representations. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 617-627.
  17. Tzu-Ming Harry Hsu, Hang Qi, and Matthew Brown. 2019. Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification. arXiv:1909.06335 [cs.LG] · arXiv
  18. Shengyuan Hu, Zhiwei Steven Wu, and Virginia Smith. 2022. Fair Federated Learning via Bounded Group Loss. https://doi.org/10.48550/ARXIV.2203.10190 · DOI
  19. Alistair E.W. Johnson, Tom J. Pollard, Lu Shen, Li-Wei H. Lehman, Mengling Feng, Mohammad Ghassemi, Benjamin Moody, Peter Szolovits, Leo Anthony Celi, Roger G. Mark, and et al. 2016. MIMIC-III, a freely accessible critical care database. Scientific Data 3, 1 (2016), 160035. https://doi.org/10.1038/sdata.2016.35 · DOI · Paper page
  20. Jian Kang, Tiankai Xie, Xintao Wu, Ross Maciejewski, and Hanghang Tong. 2021. InfoFair: Information-Theoretic Intersectional Fairness. https://doi.org/10.48550/ ARXIV.2105.11069 · DOI
  21. Tian Li, Shengyuan Hu, Ahmad Beirami, and Virginia Smith. 2021. Ditto: Fair and Robust Federated Learning Through Personalization. In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 6357-6368. https://proceedings.mlr.press/v139/li21h.html
  22. Tian Li, Maziar Sanjabi, and Virginia Smith. 2019. Fair Resource Allocation in Federated Learning. CoRR abs/1905.10497 (2019). arXiv:1905.10497 http: //arxiv.org/abs/1905.10497 · arXiv
  23. Fenglong Ma, Radha Chitta, Jing Zhou, Quanzeng You, Tong Sun, and Jing Gao. 2017. Dipole: Diagnosis Prediction in Healthcare via Attention-Based Bidirec- tional Recurrent Neural Networks. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (Halifax, NS, Canada) (KDD '17). Association for Computing Machinery, New York, NY, USA, 1903-1911.
  24. Ričards Marcinkevičs, Ece Ozkan, and Julia E. Vogt. 2022. Debiasing Deep Chest X-Ray Classifiers using Intra-and Post-processing Methods. https://doi.org/10. 48550/ARXIV.2208.00781 · DOI
  25. Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Aguera y Arcas. 2017. Communication-efficient learning of deep net- works from decentralized data. In Artificial intelligence and statistics. PMLR, 1273-1282.
  26. Ninareh Mehrabi, Fred Morstatter, Nripsuta Saxena, Kristina Lerman, and Aram Galstyan. 2019. A Survey on Bias and Fairness in Machine Learning. https: //doi.org/10.48550/ARXIV.1908.09635 · DOI · Paper page
  27. Mehryar Mohri, Gary Sivek, and Ananda Theertha Suresh. 2019. Agnostic Federated Learning. https://doi.org/10.48550/ARXIV.1902.00146 · DOI
  28. Dinh C Nguyen, Quoc-Viet Pham, Pubudu N Pathirana, Ming Ding, Aruna Senevi- ratne, Zihuai Lin, Octavia Dobre, and Won-Joo Hwang. 2022. Federated learning for smart healthcare: A survey. ACM Computing Surveys (CSUR) 55, 3 (2022), 1-37.
  29. Afroditi Papadaki, Natalia Martinez, Martin Bertran, Guillermo Sapiro, and Miguel Rodrigues. 2022. Minimax Demographic Group Fairness in Federated Learning. https://doi.org/10.1145/3531146.3533081 · DOI
  30. Stephen Pfohl, Ben Marafino, Adrien Coulet, Fatima Rodriguez, Latha Palaniap- pan, and Nigam H. Shah. 2019. Creating Fair Models of Atherosclerotic Cardiovas- cular Disease Risk. https://doi.org/10.1145/3306618.3314278 · DOI
  31. Stephen R. Pfohl, Andrew M. Dai, and Katherine Heller. 2019. Federated and Differentially Private Learning for Electronic Health Records. https://doi.org/10. 48550/ARXIV.1911.05861 · DOI · Paper page
  32. Stephen R. Pfohl, Tony Duan, Daisy Yi Ding, and Nigam H. Shah. 2019. Coun- terfactual Reasoning for Fair Clinical Risk Prediction. In Proceedings of the 4th Machine Learning for Healthcare Conference (Proceedings of Machine Learn- ing Research, Vol. 106), Finale Doshi-Velez, Jim Fackler, Ken Jung, David Kale, Rajesh Ranganath, Byron Wallace, and Jenna Wiens (Eds.). PMLR, 325-358. https://proceedings.mlr.press/v106/pfohl19a.html
  33. Tom J. Pollard, Alistair E. W. Johnson, Jesse D. Raffa, Leo A. Celi, Roger G. Mark, and Omar Badawi. 2018. The eICU Collaborative Research Database, a freely available multi-center database for critical care research. Scientific Data 5, 1 (2018), 180178. https://doi.org/10.1038/sdata.2018.178 · DOI · Paper page
  34. Alvin Rajkomar, Michaela Hardt, Michael D. Howell, Greg Corrado, and Mar- shall H. Chin. 2018. Ensuring Fairness in Machine Learning to Advance Health Eq- uity. Annals of Internal Medicine 169, 12 (2018), 866. https://doi.org/10.7326/m18- 1990 · DOI · Paper page
  35. Yuji Roh, Kangwook Lee, Steven Euijong Whang, and Changho Suh. 2020. Fair- Batch: Batch Selection for Model Fairness. https://doi.org/10.48550/ARXIV.2012. 01696 · DOI
  36. Pulkit Sharma, Farah E Shamout, and David A Clifton. 2019. Preserving patient privacy while training a predictive model of in-hospital mortality. arXiv preprint arXiv:1912.00354 (2019). · arXiv
  37. Jason Walonoski, Mark Kramer, Joseph Nichols, Andre Quina, Chris Moesel, Dylan Hall, Carlton Duffett, Kudakwashe Dube, Thomas Gallagher, and Scott McLachlan. 2017. Synthea: An approach, method, and software mechanism for generating synthetic patients and the synthetic electronic health care record. Journal of the American Medical Informatics Association 25, 3 (08 2017), 230-238.
  38. Mingyang Wan, Daochen Zha, Ninghao Liu, and Na Zou. 2021. Modeling Tech- niques for Machine Learning Fairness: A Survey. https://doi.org/10.48550/ARXIV. 2111.03015 · DOI
  39. Zheng Wang, Xiaoliang Fan, Jianzhong Qi, Chenglu Wen, Cheng Wang, and Rongshan Yu. 2021. Federated Learning with Fair Averaging. https://doi.org/10. 48550/ARXIV.2104.14937 · DOI
  40. C. Xiao, E. Choi, and J. Sun. 2018. Opportunities and challenges in developing deep learning models using electronic health records data: a systematic review. J Am Med Inform Assoc 25, 10 (Oct 2018), 1419-1428.
  41. Yuchen Zeng, Hongxu Chen, and Kangwook Lee. 2021. Improving Fairness via Federated Learning. https://doi.org/10.48550/ARXIV.2110.15545 · DOI

Authors
Poulain, R., Bin Tarek, M. F., & Beheshti, R.
Affiliations
  • University of Delaware (US)
  • University of Delaware, USA
ORCID
Venue
2023 ACM Conference on Fairness Accountability and Transparency
Publisher
ACM
Published
2023-06-12
Volume
2023
Pages
1599-1608
DOI
10.1145/3593013.3594102
PMC
PMC10661580
OpenAlex
W4380365787
Cited by
63
References
36
Citations by year
2026: 7 · 2025: 17 · 2024: 18 · 2023: 10 · 2022: 5 · 2021: 4 · 2020: 2
FWCI
9.21
Type
conference paper
Language
en
Open access
Licence
www.acm.org/publications/policies/copyright_policy#Background (vor)
Locations
  • ACM Conference on Fairness, Accountability, and Transparency (FAccT) (publishedVersion)
  • PubMed (publishedVersion)
  • PubMed Central (acceptedVersion)
  • arXiv (Cornell University) (submittedVersion, cc-by)
  • arXiv (Cornell University) (cc-by)
Funders
NIH (National Institutes of Health) (5P20GM113125,3P20GM103446)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
  • Social Sciences › Safety Research › Ethics and Social Impacts of AI
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
Keywords
federated learning, algorithmic fairness, electronic health records, adversarial debiasing, artificial intelligence in healthcare, class imbalance, inter-institutional collaboration, discrimination

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