FairFML: Fair Federated Machine Learning with a Case Study on Reducing Gender Disparities in Cardiac Arrest Outcome Prediction
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908488682176512 |
|---|---|
| author | Li, Siqi Wu, Qiming Li, Xin Miao, Di Hong, Chuan Gu, Wenjun Shang, Yuqing Okada, Yohei Chen, Michael Hao Yan, Mengying Ning, Yilin Ong, Marcus Eng Hock Liu, Nan |
| author_facet | Li, Siqi Wu, Qiming Li, Xin Miao, Di Hong, Chuan Gu, Wenjun Shang, Yuqing Okada, Yohei Chen, Michael Hao Yan, Mengying Ning, Yilin Ong, Marcus Eng Hock Liu, Nan |
| contents | Objective: Mitigating algorithmic disparities is a critical challenge in healthcare research, where ensuring equity and fairness is paramount. While large-scale healthcare data exist across multiple institutions, cross-institutional collaborations often face privacy constraints, highlighting the need for privacy-preserving solutions that also promote fairness.
Materials and Methods: In this study, we present Fair Federated Machine Learning (FairFML), a model-agnostic solution designed to reduce algorithmic bias in cross-institutional healthcare collaborations while preserving patient privacy. As a proof of concept, we validated FairFML using a real-world clinical case study focused on reducing gender disparities in cardiac arrest outcome prediction.
Results: We demonstrate that the proposed FairFML framework enhances fairness in federated learning (FL) models without compromising predictive performance. Our findings show that FairFML improves model fairness by up to 65% compared to the centralized model, while maintaining performance comparable to both local and centralized models, as measured by receiver operating characteristic analysis.
Discussion and Conclusion: FairFML offers a promising and flexible solution for FL collaborations, with its adaptability allowing seamless integration with various FL frameworks and models, from traditional statistical methods to deep learning techniques. This makes FairFML a robust approach for developing fairer FL models across diverse clinical and biomedical applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_17269 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FairFML: Fair Federated Machine Learning with a Case Study on Reducing Gender Disparities in Cardiac Arrest Outcome Prediction Li, Siqi Wu, Qiming Li, Xin Miao, Di Hong, Chuan Gu, Wenjun Shang, Yuqing Okada, Yohei Chen, Michael Hao Yan, Mengying Ning, Yilin Ong, Marcus Eng Hock Liu, Nan Computers and Society Artificial Intelligence Machine Learning Objective: Mitigating algorithmic disparities is a critical challenge in healthcare research, where ensuring equity and fairness is paramount. While large-scale healthcare data exist across multiple institutions, cross-institutional collaborations often face privacy constraints, highlighting the need for privacy-preserving solutions that also promote fairness. Materials and Methods: In this study, we present Fair Federated Machine Learning (FairFML), a model-agnostic solution designed to reduce algorithmic bias in cross-institutional healthcare collaborations while preserving patient privacy. As a proof of concept, we validated FairFML using a real-world clinical case study focused on reducing gender disparities in cardiac arrest outcome prediction. Results: We demonstrate that the proposed FairFML framework enhances fairness in federated learning (FL) models without compromising predictive performance. Our findings show that FairFML improves model fairness by up to 65% compared to the centralized model, while maintaining performance comparable to both local and centralized models, as measured by receiver operating characteristic analysis. Discussion and Conclusion: FairFML offers a promising and flexible solution for FL collaborations, with its adaptability allowing seamless integration with various FL frameworks and models, from traditional statistical methods to deep learning techniques. This makes FairFML a robust approach for developing fairer FL models across diverse clinical and biomedical applications. |
| title | FairFML: Fair Federated Machine Learning with a Case Study on Reducing Gender Disparities in Cardiac Arrest Outcome Prediction |
| topic | Computers and Society Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2410.17269 |