Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 25, 2025Journal of Medical and Health StudiesOpen Access

Bias Mitigation in Federated Healthcare Cloud Models

View Full Paper
Ask AI
Bookmark
Share

Authors

VJV. Jagadeesan

Discussion

Loading...

Member takes

Overview

This research identifies bias mitigation strategies in federated learning, highlighting fairness measures and auditing methods.

Key Points

  • Including bias mitigation measures significantly enhances fairness in predictive models used in healthcare.
  • Demographic parity and equalized odds were key fairness measures employed to assess bias across institutions.
  • Mitigation techniques like reweighting data and applying fairness constraints improved model outcomes without sacrificing utility.
  • Secure aggregation methods were analyzed to ensure privacy while enabling collaborative fairness audits in federated systems.

Cite This Study

V. Jagadeesan (2025) studied this question.

synapsesocial.com/papers/68d5bd69dc445aa9033b0668https://doi.org/10.32996/jmhs.2025.6.4.12
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. 1Federated Learning for Secure and Privacy-Preserving Medical Collaboration Across Multi-Cloud Healthcare Systems2024 · 2 citations
  2. 2Toward Fair Federated Learning under Demographic Disparities and Data Imbalance2025
  3. 3FairFML: A Unified Approach to Algorithmic Fair Federated Learning with Applications to Reducing Gender Disparities in Cardiac Arrest Outcomes.2025 · 1 citations
  4. 4Federated Machine Learning Across Hybrid Clouds: Balancing Security and Privacy2023
  5. 5Toward Real-World Deployment of Federated Learning in Healthcare: A Comprehensive Review of Hybrid Models and Data Simulation Tools2025 · 1 citations