Interpretable multimodal machine learning for injury risk stratification in adolescent athletes: integrating kinematic, physiological, and load data with SHAP/LIME explainability
Linzhen Zhou, Meng Zheng, Hongbing Wang, Linjun Liu, Tianshi Wei · 2026
Read Interpretable multimodal machine learning for injury risk stratification in adolescent athletes: integrating kinematic, physiological, and load data with SHAP/LIME explainability by Linzhen Zhou, Meng Zheng, Hongbing Wang, Linjun Liu, Tianshi Wei (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/PMC13472085.txt.
Description
Zhou and colleagues published a 2026 study on predicting injury risk in teenage athletes with explainable AI. Teen athletes injure lower limbs more often than adults, partly from immature control. The team combined movement, body, and training-load data for 320 athletes aged 13 to 18. Ten learning models competed at sorting athletes into risk groups.
A plain logistic model beat the fancier deep learning entries overall. It reached about 87 percent accuracy with a strong discrimination score. Two explanation tools agreed on the top risk signals behind predictions. Hip inward angle during movement led, then ankle flexibility range. Knee inward collapse angle ranked third among the warning signs. Data came from motion cameras, force plates, and GPS trackers combined.
Catalog record
| CREATOR | Linzhen Zhou, Meng Zheng, Hongbing Wang, Linjun Liu, Tianshi Wei |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 78 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |