Development and Internal Validation of an Explainable Machine Learning Model for Physical Activity Adherence Among Community-Dwelling Patients with Type 2 Diabetes Mellitus
Yiming Zhao, Mo Zhou, Feng Sun, Chuning Lin, Huimin Niu, Xinyi Zhang, Feng Jiang, Chuyan Wu · 2026
Read Development and Internal Validation of an Explainable Machine Learning Model for Physical Activity Adherence Among Community-Dwelling Patients with Type 2 Diabetes Mellitus by Yiming Zhao, Mo Zhou, Feng Sun, Chuning Lin, Huimin Niu, Xinyi Zhang, Feng Jiang, Chuyan Wu (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13571637.txt.
Description
Knowing which diabetes patients will stick with exercise could help clinics spend support where it counts. Yiming Zhao and co-authors build a model for that call in this 2026 study of 207 community patients in China. Just over half the group kept up high activity levels. The team sifted candidate factors, then compared several learning methods on a training split.
Five factors made the final model, mixing a self-care score, a kidney measure, family history, an activity score, and a blood protein. A support vector machine read them best, with an accuracy score of 0.787 on held-out patients. Explanation plots show how each factor pushes a given patient's score. The authors say outside testing must come before any clinic use.
Catalog record
| CREATOR | Yiming Zhao, Mo Zhou, Feng Sun, Chuning Lin, Huimin Niu, Xinyi Zhang, Feng Jiang, Chuyan Wu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 43 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |