Machine Learning Approach for Frailty Detection in Long-Term Care Using Accelerometer-Measured Gait and Daily Physical Activity: Model Development and Validation Study
Our findings suggest that dynamic gait outcomes may serve as more sensitive indicators of frailty than spatial-temporal gait outcomes (eg, gait speed) in LTC settings, offering valuable insights for enhancing frailty detection and management.
Authors
- Xiaoping Zheng (ORCID: https://orcid.org/0000-0002-7556-130X)
- Kimberley S. van Schooten (ORCID: https://orcid.org/0000-0003-0902-8440)
- Ziwei Zeng (ORCID: https://orcid.org/0000-0001-8541-1842)
- Yijian Yang (ORCID: https://orcid.org/0000-0002-5831-186X)
Institutions
- Chinese University of Hong Kong (HK)
- UNSW Sydney (AU)
- Hong Kong Jockey Club (HK)
- Neuroscience Research Australia (AU)
Publication Details
- Journal
- JMIR Aging
- Published
- 2025-08-08
- DOI
- https://doi.org/10.2196/77140
- Citations
- 4
- Primary Topic
- Frailty in Older Adults
- Type
- article
- Field-Weighted Citation Impact
- 4.90