Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
August 9, 2025

FairFML: A Unified Approach to Algorithmic Fair Federated Learning with Applications to Reducing Gender Disparities in Cardiac Arrest Outcomes.

View Full Paper
Ask AI
Bookmark
Share

Authors

SLSiqi LiQWQiming WuXLXin Li

Discussion

Loading...

Member takes

Overview

Fair Federated Learning improves fairness by up to 65% in cardiac arrest outcomes, indicating a unified approach to addressing algorithmic bias in healthcare.

Key Points

  • FAIRFML reduces algorithmic bias in healthcare settings using federated learning techniques.
  • The framework is designed to improve fairness without needing to share sensitive patient data.
  • In a real-world study, fair federated learning showed a 65% improvement in fairness for gender disparities.
  • This approach enhances equity in patient outcomes, particularly in cross-institutional collaborations.

Cite This Study

Li et al. (2025) studied this question.

synapsesocial.com/papers/689dfe97d61984b91e13bfbdhttps://doi.org/10.3233/shti251245
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Toward Fair Federated Learning under Demographic Disparities and Data Imbalance2025
  2. 2Fairness Regularization in Federated Learning2025
  3. 3Federated Learning in Healthcare: From Research to Real-World Deployment2026 · 8 citations
  4. 4Federated Learning at the Forefront of Fairness: A Multifaceted Perspective2025 · 4 citations
  5. 5Federated Learning in Healthcare: A Privacy-Preserving Approach to Medical AI2025