Machine learning algorithms to predict frailty in older adults in China: a cross-sectional study
ML algorithms can effectively predict the occurrence of frailty in Chinese elderly and identify significant factors associated with frailty. For datasets with complex feature interactions, LightGBM is preferable, while Random Forest offers improved stability and variance control. These findings support ML-based frailty screening and intervention strategies for aging populations.
Authors
- Yue Liu (ORCID: https://orcid.org/0000-0001-9428-9615)
- Yanliqing Song (ORCID: https://orcid.org/0009-0000-3725-714X)
Institutions
- Nanjing Tech University (CN)
- Shanghai University of Sport (CN)
Publication Details
- Journal
- BMC Geriatrics
- Published
- 2025-12-08
- DOI
- https://doi.org/10.1186/s12877-025-06738-3
- Citations
- 1
- Primary Topic
- Frailty in Older Adults
- Type
- article
- Field-Weighted Citation Impact
- 1.22
Funders
- Peking University
- Social Science Foundation of Jiangsu Province