Article

FedWeight: Mitigating Covariate Shift of Federated Learning on Electronic Health Records Data through Patients Re-weighting

2025-04-14

Abstract excerpt

<title>Abstract</title> <p>Federated learning (FL) enables collaborative analysis of decentralized medical data while preserving patient privacy. However, the covariate shift from demographic and clinical differences can reduce model generalizability. We propose FedWeight, a novel FL framework that mitigates covariate shift by reweighting patient data from the source sites using density estimators, allowing the t...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 10aa9f5b-66b5-546d-a245-fe55fa415389
DOI: 10.21203/rs.3.rs-6099872/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

FedWeight: Mitigating Covariate Shift of Federated Learning on Electronic Health Records Data through Patients Re-weightingDOI 10.21203/rs.3.rs-6099872/v1Read

FedWeight: Mitigating Covariate Shift of Federated Learning on Electronic Health Records Data through Patients Re-weightingSemantic proximity Read

Ten Quick Tips for Biomedical Federated LearningSemantic proximity Read

Federated Target Trial Emulation using Distributed Observational Data for Treatment Effect EstimationSemantic proximity Read

A Heterogeneity-Aware Privacy-Preserving Federated Learning Framework Using Ensemble Clustering for Healthcare ApplicationsSemantic proximity Read

Hierarchical Personalized Continual Federated Learning for Real Time Risk Prediction of Chronic DiseasesSemantic proximity Read

Efficacy of federated learning on genomic data: a study on the UK Biobank and the 1000 Genomes ProjectSemantic proximity Read

Privacy-first health research with federated learningSemantic proximity Read

Toward Real-World Deployment of Federated Learning in Healthcare: A Comprehensive Review of Hybrid Models and Data Simulation ToolsSemantic proximity Read

Multi-Hospital Electronic Health Record Foundation Models Without Data Sharing: A Comparison of Federated Learning and Inference-Time EnsemblingSemantic proximity Read

Federated Learning for ICU Mortality Prediction: Balancing Accuracy and Privacy in a Multi-Hospital SettingSemantic proximity Read

Data Heterogeneity in Federated Learning with Electronic Health Records: Case Studies of Risk Prediction for Acute Kidney Injury and Sepsis Diseases in Critical CareSemantic proximity Read

Distributed Learning for Heart Disease Risk Prediction Based on Key Clinical Parameters with Evaluation Metrics AnalysisSemantic proximity Read