Prediction of Risk of Unplanned Readmission or Death in Elderly Heart Failure Patients During the Vulnerable Phase: Machine Learning With SHAP Interpretation
Hao Luo, Qi Wu, Zaiyong Zheng, Xuefeng Wang, Na Lai, Yixuan Li, Xiang Zheng, Yihang Li, Deqiang Li, Kai Guo, Ji Li · 2026
Read Prediction of Risk of Unplanned Readmission or Death in Elderly Heart Failure Patients During the Vulnerable Phase: Machine Learning With SHAP Interpretation by Hao Luo, Qi Wu, Zaiyong Zheng, Xuefeng Wang, Na Lai, Yixuan Li, Xiang Zheng, Yihang Li, Deqiang Li, Kai Guo, Ji Li (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/PMC13254217.txt.
Description
Hao Luo and co-authors build a risk model for older heart failure patients in a 2026 study. The vulnerable phase after hospital care brings frequent readmission and death. The team trained 18 machine learning models with six algorithms and used SHAP, a method that shows how each factor shapes a prediction.
Eleven models scored above 0.8 on a key accuracy curve measure. The best, Boruta-XGBoost, reached 0.873, with sensitivity of 0.839 and accuracy of 0.769. The top five factors were hemoglobin, a thyroid hormone measure, age, diabetes, and blood potassium. The authors stress the model's clear reasoning as a strength.
Catalog record
| CREATOR | Hao Luo, Qi Wu, Zaiyong Zheng, Xuefeng Wang, Na Lai, Yixuan Li, Xiang Zheng, Yihang Li, Deqiang Li, Kai Guo, Ji Li |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 40376 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |