Continual learning across population cohorts with distribution shift: insights from multi-cohort metabolic syndrome identification
The proposed CL model effectively mitigates catastrophic forgetting, enhancing the overall performance of DL models. Our results underscore the prospect of CL methods in developing medical DL models and maintaining scalability across diverse healthcare settings.
Authors
- C. S. Steve Cai (ORCID: https://orcid.org/0000-0002-0740-3713)
- Zhangdaihong Liu (ORCID: https://orcid.org/0000-0003-2142-477X)
- Jingjing Liu (ORCID: https://orcid.org/0009-0005-3076-0603)
- Chang Liu (ORCID: https://orcid.org/0000-0002-0059-1408)
- Yang Yang (ORCID: https://orcid.org/0000-0002-5432-1489)
- Hui Wang
- David A. Clifton
Institutions
- Shanghai Jiao Tong University (CN)
- University of Oxford (GB)
- Suzhou Research Institute (CN)
- Software (Spain) (ES)
Publication Details
- Journal
- Journal of the American Medical Informatics Association
- Published
- 2025-06-11
- DOI
- https://doi.org/10.1093/jamia/ocaf070
- Citations
- 1
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 2.48