Explainable machine learning for predicting activities of daily living at discharge in stroke patients: A retrospective study using SHAP interpretability
Qian Ye, Guilin Fang, Liping Li, Qinggui Li, Yun Yang, Lingling Liu · 2026
Read Explainable machine learning for predicting activities of daily living at discharge in stroke patients: A retrospective study using SHAP interpretability by Qian Ye, Guilin Fang, Liping Li, Qinggui Li, Yun Yang, Lingling Liu (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/plos-pone-0351468.txt.
Description
Qian Ye and five colleagues present this 2026 PLOS One study building a machine learning tool to predict how independently stroke patients will manage daily life by discharge. Records from nearly six hundred inpatients treated between 2019 and 2024 were used to train ten algorithms, after statistical screening narrowed forty-one candidate measures down to six.
A random forest model performed best, separating patients headed for good versus poor daily-living independence with high accuracy. An explanation technique ranked the strongest drivers: how independent the patient already was at admission, standing balance, recovery stages of the arm and leg, and the ability to dress and groom. The authors say the transparent model can help rehabilitation teams set realistic goals and plan support earlier.
Catalog record
| CREATOR | Qian Ye, Guilin Fang, Liping Li, Qinggui Li, Yun Yang, Lingling Liu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 24072 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |