Explainable Machine Learning for Early Detection of Mild Cognitive Impairment, Fall Risk, and Frailty Using Sensor-Based Motor Function Data
This work introduces a novel ML framework using multimodal sensor-based motor assessments to predict MCI, fall risk, and frailty individually and within a unified model. By combining explainable ML with motor-function data, the framework supports transparent early screening of multidomain cognitive and physical decline in aging.
Authors
- Trent M. Guess (ORCID: https://orcid.org/0000-0003-4923-2489)
- Andrew M. Kiselica (ORCID: https://orcid.org/0000-0002-9514-0668)
- Sonia Akter (ORCID: https://orcid.org/0000-0002-9109-3307)
- Shraboni Sarker (ORCID: https://orcid.org/0009-0009-1513-7521)
- Jamie B. Hall (ORCID: https://orcid.org/0000-0003-3443-7107)
- Praveen Rao
- Samuel A. Hocket
Institutions
- University of Georgia (US)
- University of Missouri (US)
Publication Details
- Journal
- medRxiv
- Published
- 2025-12-27
- DOI
- https://doi.org/10.64898/2025.12.23.25342943
- Primary Topic
- Balance, Gait, and Falls Prevention
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- University of Missouri
- National Institutes of Health