A personalized federated learning approach to enhance joint modeling for heterogeneous medical institutions
Background Federated Learning (FL) offers a privacy-preserving solution for multi-party data collaboration in smart healthcare. However, the data heterogeneity among hospitals and among patients often results in suboptimal performance for some hospitals when applying a global FL model. Current clust...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2025-07-01
|
| Series: | Digital Health |
| Online Access: | https://doi.org/10.1177/20552076251360861 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850075929197412352 |
|---|---|
| author | Hong Ye Xiangzhou Zhang Kang Liu Ziyuan Liu Weiqi Chen Bo Liu Eric WT Ngai Yong Hu |
| author_facet | Hong Ye Xiangzhou Zhang Kang Liu Ziyuan Liu Weiqi Chen Bo Liu Eric WT Ngai Yong Hu |
| author_sort | Hong Ye |
| collection | DOAJ |
| description | Background Federated Learning (FL) offers a privacy-preserving solution for multi-party data collaboration in smart healthcare. However, the data heterogeneity among hospitals and among patients often results in suboptimal performance for some hospitals when applying a global FL model. Current clustering-based FL methods struggle to adapt to complex and diverse data distributions, negatively impacting model performance. Methods We propose a novel framework, Federated Gaussian Mixture Clustering (FedGMC), which leverages Gaussian Mixture Clustering to train personalized FL models. FedGMC determines the optimal number of clusters prior to the FL process, reducing the time and computational cost associated with traversing multiple clustering configurations in existing approaches. Results The FedGMC framework was evaluated using real-world eICU datasets with various classifiers and performance metrics. Experimental results show that FedGMC outperforms other baseline methods in terms of the overall performance of combining two classifiers and two performance metrics. Moreover, it mitigates the risk of performance degraded for participating hospitals following FL. Conclusions The FedGMC framework effectively addresses clinical heterogeneity, enhancing predictive performance and ensuring fairness among participating medical institutions. These improvements increase the willingness of data owners to engage in the collaboration FL initiatives. |
| format | Article |
| id | doaj-art-d93dbca0374048ffb616fde186bf3157 |
| institution | DOAJ |
| issn | 2055-2076 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | Digital Health |
| spelling | doaj-art-d93dbca0374048ffb616fde186bf31572025-08-20T02:46:08ZengSAGE PublishingDigital Health2055-20762025-07-011110.1177/20552076251360861A personalized federated learning approach to enhance joint modeling for heterogeneous medical institutionsHong Ye0Xiangzhou Zhang1Kang Liu2Ziyuan Liu3Weiqi Chen4Bo Liu5Eric WT Ngai6Yong Hu7 School of Management, , Guangzhou, China School of Medicine, , Guangzhou, China School of Management, , Guangzhou, China College of Information Science and Technology, , Guangzhou, China School of Computer Science, , Guangzhou, China School of Management, , Guangzhou, China Faculty of Business, , Hong Kong, China School of Medicine, , Guangzhou, ChinaBackground Federated Learning (FL) offers a privacy-preserving solution for multi-party data collaboration in smart healthcare. However, the data heterogeneity among hospitals and among patients often results in suboptimal performance for some hospitals when applying a global FL model. Current clustering-based FL methods struggle to adapt to complex and diverse data distributions, negatively impacting model performance. Methods We propose a novel framework, Federated Gaussian Mixture Clustering (FedGMC), which leverages Gaussian Mixture Clustering to train personalized FL models. FedGMC determines the optimal number of clusters prior to the FL process, reducing the time and computational cost associated with traversing multiple clustering configurations in existing approaches. Results The FedGMC framework was evaluated using real-world eICU datasets with various classifiers and performance metrics. Experimental results show that FedGMC outperforms other baseline methods in terms of the overall performance of combining two classifiers and two performance metrics. Moreover, it mitigates the risk of performance degraded for participating hospitals following FL. Conclusions The FedGMC framework effectively addresses clinical heterogeneity, enhancing predictive performance and ensuring fairness among participating medical institutions. These improvements increase the willingness of data owners to engage in the collaboration FL initiatives.https://doi.org/10.1177/20552076251360861 |
| spellingShingle | Hong Ye Xiangzhou Zhang Kang Liu Ziyuan Liu Weiqi Chen Bo Liu Eric WT Ngai Yong Hu A personalized federated learning approach to enhance joint modeling for heterogeneous medical institutions Digital Health |
| title | A personalized federated learning approach to enhance joint modeling for heterogeneous medical institutions |
| title_full | A personalized federated learning approach to enhance joint modeling for heterogeneous medical institutions |
| title_fullStr | A personalized federated learning approach to enhance joint modeling for heterogeneous medical institutions |
| title_full_unstemmed | A personalized federated learning approach to enhance joint modeling for heterogeneous medical institutions |
| title_short | A personalized federated learning approach to enhance joint modeling for heterogeneous medical institutions |
| title_sort | personalized federated learning approach to enhance joint modeling for heterogeneous medical institutions |
| url | https://doi.org/10.1177/20552076251360861 |
| work_keys_str_mv | AT hongye apersonalizedfederatedlearningapproachtoenhancejointmodelingforheterogeneousmedicalinstitutions AT xiangzhouzhang apersonalizedfederatedlearningapproachtoenhancejointmodelingforheterogeneousmedicalinstitutions AT kangliu apersonalizedfederatedlearningapproachtoenhancejointmodelingforheterogeneousmedicalinstitutions AT ziyuanliu apersonalizedfederatedlearningapproachtoenhancejointmodelingforheterogeneousmedicalinstitutions AT weiqichen apersonalizedfederatedlearningapproachtoenhancejointmodelingforheterogeneousmedicalinstitutions AT boliu apersonalizedfederatedlearningapproachtoenhancejointmodelingforheterogeneousmedicalinstitutions AT ericwtngai apersonalizedfederatedlearningapproachtoenhancejointmodelingforheterogeneousmedicalinstitutions AT yonghu apersonalizedfederatedlearningapproachtoenhancejointmodelingforheterogeneousmedicalinstitutions AT hongye personalizedfederatedlearningapproachtoenhancejointmodelingforheterogeneousmedicalinstitutions AT xiangzhouzhang personalizedfederatedlearningapproachtoenhancejointmodelingforheterogeneousmedicalinstitutions AT kangliu personalizedfederatedlearningapproachtoenhancejointmodelingforheterogeneousmedicalinstitutions AT ziyuanliu personalizedfederatedlearningapproachtoenhancejointmodelingforheterogeneousmedicalinstitutions AT weiqichen personalizedfederatedlearningapproachtoenhancejointmodelingforheterogeneousmedicalinstitutions AT boliu personalizedfederatedlearningapproachtoenhancejointmodelingforheterogeneousmedicalinstitutions AT ericwtngai personalizedfederatedlearningapproachtoenhancejointmodelingforheterogeneousmedicalinstitutions AT yonghu personalizedfederatedlearningapproachtoenhancejointmodelingforheterogeneousmedicalinstitutions |