Development and Interpretability Analysis of a Stacking Ensemble Model for Early Prediction of Nutritional Risk in Intensive Care Unit Patients: Retrospective Cohort Study
Xu Zhang, An Fang, Pei Lou, Kuanda Yao, Tianci Huang, Jiahui Hu · 2026
Read Development and Interpretability Analysis of a Stacking Ensemble Model for Early Prediction of Nutritional Risk in Intensive Care Unit Patients: Retrospective Cohort Study by Xu Zhang, An Fang, Pei Lou, Kuanda Yao, Tianci Huang, Jiahui Hu (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-13232782.txt.
Description
Xu Zhang and colleagues build in 2026 a stacked machine learning model that flags malnutrition risk within a day of intensive care arrival. Standard scores rely on slow or judgment-based inputs, which delays feeding support for the sickest patients. Records from a large public intensive care database covered more than fifty thousand stays with first-day vitals and labs.
Four learning methods fed their outputs into a final combining model, a design called stacking. The stack sorted future malnutrition cases far better than the standard score and slightly better than its best single member. About one patient in twelve in the cohort carried the risk label. Explanation tools showed which inputs drove each call, keeping the model open to clinical judgment.
Catalog record
| CREATOR | Xu Zhang, An Fang, Pei Lou, Kuanda Yao, Tianci Huang, Jiahui Hu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 51 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |