Time-Series modeling for predicting mortality risk in intensive care unit patients with pulmonary inflammation
Yihai Zhai, Ruixin Xu, Haisu Lu, Siying Lv, Liqin Mo · 2026
Read Time-Series modeling for predicting mortality risk in intensive care unit patients with pulmonary inflammation by Yihai Zhai, Ruixin Xu, Haisu Lu, Siying Lv, Liqin Mo (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-13581569.txt.
Description
Yihai Zhai and co-authors (2026) build models that forecast death risk for intensive care patients with pneumonia, using the way their condition evolves over time. A single snapshot at admission misses deterioration or recovery. The team drew records from two large critical care databases, MIMIC-IV and eICU. One cohort was split into training and test sets; the other served as an outside check. Gaps in the data were filled by carrying values forward and by statistical imputation.
A long short-term memory network first extracted patterns from each patient's time series. Those patterns then fed five standard classifiers, from logistic regression to gradient boosting and a small neural net. Tuning used cross-validation and grid search. The authors scored the models on accuracy, recall, and other measures, aiming for a tool that is both strong and readable enough for clinicians to trust at the bedside.
Catalog record
| CREATOR | Yihai Zhai, Ruixin Xu, Haisu Lu, Siying Lv, Liqin Mo |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 50 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |