FedWeight: mitigating covariate shift of federated learning on electronic health records data through patients re-weighting
Abstract 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 covariat...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-05-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-025-01661-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849326863953952768 |
|---|---|
| author | He Zhu Jun Bai Na Li Xiaoxiao Li Dianbo Liu David L. Buckeridge Yue Li |
| author_facet | He Zhu Jun Bai Na Li Xiaoxiao Li Dianbo Liu David L. Buckeridge Yue Li |
| author_sort | He Zhu |
| collection | DOAJ |
| description | Abstract 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 trained model to better align with the distribution of the target site. To support unsupervised applications, we introduce FedWeight ETM, a federated embedded topic model. We evaluated FedWeight in cross-site FL on the eICU dataset and cross-dataset FL between eICU and MIMIC III. FedWeight consistently outperforms standard FL baselines in predicting ICU mortality, ventilator use, sepsis diagnosis, and length of stay. SHAP-based interpretation and ETM-based topic modeling reveal improved identification of clinically relevant characteristics and disease topics associated with ICU readmission. |
| format | Article |
| id | doaj-art-b17a38412bc644dfa7cf9ea06ac72fa8 |
| institution | Kabale University |
| issn | 2398-6352 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj-art-b17a38412bc644dfa7cf9ea06ac72fa82025-08-20T03:48:02ZengNature Portfolionpj Digital Medicine2398-63522025-05-018111910.1038/s41746-025-01661-8FedWeight: mitigating covariate shift of federated learning on electronic health records data through patients re-weightingHe Zhu0Jun Bai1Na Li2Xiaoxiao Li3Dianbo Liu4David L. Buckeridge5Yue Li6School of Computer Science, McGill UniversitySchool of Computer Science, McGill UniversityCommunity Health Sciences, Cumming School of Medicine, University of CalgaryElectrical and Computer Engineering, University of British ColumbiaSchool of Medicine, National University of SingaporeMila—Quebec AI InstituteSchool of Computer Science, McGill UniversityAbstract 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 trained model to better align with the distribution of the target site. To support unsupervised applications, we introduce FedWeight ETM, a federated embedded topic model. We evaluated FedWeight in cross-site FL on the eICU dataset and cross-dataset FL between eICU and MIMIC III. FedWeight consistently outperforms standard FL baselines in predicting ICU mortality, ventilator use, sepsis diagnosis, and length of stay. SHAP-based interpretation and ETM-based topic modeling reveal improved identification of clinically relevant characteristics and disease topics associated with ICU readmission.https://doi.org/10.1038/s41746-025-01661-8 |
| spellingShingle | He Zhu Jun Bai Na Li Xiaoxiao Li Dianbo Liu David L. Buckeridge Yue Li FedWeight: mitigating covariate shift of federated learning on electronic health records data through patients re-weighting npj Digital Medicine |
| title | FedWeight: mitigating covariate shift of federated learning on electronic health records data through patients re-weighting |
| title_full | FedWeight: mitigating covariate shift of federated learning on electronic health records data through patients re-weighting |
| title_fullStr | FedWeight: mitigating covariate shift of federated learning on electronic health records data through patients re-weighting |
| title_full_unstemmed | FedWeight: mitigating covariate shift of federated learning on electronic health records data through patients re-weighting |
| title_short | FedWeight: mitigating covariate shift of federated learning on electronic health records data through patients re-weighting |
| title_sort | fedweight mitigating covariate shift of federated learning on electronic health records data through patients re weighting |
| url | https://doi.org/10.1038/s41746-025-01661-8 |
| work_keys_str_mv | AT hezhu fedweightmitigatingcovariateshiftoffederatedlearningonelectronichealthrecordsdatathroughpatientsreweighting AT junbai fedweightmitigatingcovariateshiftoffederatedlearningonelectronichealthrecordsdatathroughpatientsreweighting AT nali fedweightmitigatingcovariateshiftoffederatedlearningonelectronichealthrecordsdatathroughpatientsreweighting AT xiaoxiaoli fedweightmitigatingcovariateshiftoffederatedlearningonelectronichealthrecordsdatathroughpatientsreweighting AT dianboliu fedweightmitigatingcovariateshiftoffederatedlearningonelectronichealthrecordsdatathroughpatientsreweighting AT davidlbuckeridge fedweightmitigatingcovariateshiftoffederatedlearningonelectronichealthrecordsdatathroughpatientsreweighting AT yueli fedweightmitigatingcovariateshiftoffederatedlearningonelectronichealthrecordsdatathroughpatientsreweighting |