The prognostic value of the early neutrophil-to-lymphocyte ratio for 28-day mortality in sepsis patients: A machine learning-based investigation of the MIMIC database
Jiyang Liao, Qianwen Xiang, Xingwang Chen, Long Wu, Houwang Chen, Zhijun Yao, Huachu Wu, Jianbo Lai · 2026
Read The prognostic value of the early neutrophil-to-lymphocyte ratio for 28-day mortality in sepsis patients: A machine learning-based investigation of the MIMIC database by Jiyang Liao, Qianwen Xiang, Xingwang Chen, Long Wu, Houwang Chen, Zhijun Yao, Huachu Wu, Jianbo Lai (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-0348676.txt.
Description
Jiyang Liao and colleagues used machine learning on a large intensive care database in 2026 to test a simple inflammation ratio as a death predictor in sepsis. The ratio of neutrophils to lymphocytes had given mixed answers in smaller studies.
More than four thousand sepsis patients were grouped by the ratio, and models adjusted step by step for clinical factors. Twenty-eight day death ran near one in five overall. The learned model beat standard severity scores at prediction, and the ratio kept independent value. A free number from a routine blood count may help intensive care teams rank risk sooner.
Catalog record
| CREATOR | Jiyang Liao, Qianwen Xiang, Xingwang Chen, Long Wu, Houwang Chen, Zhijun Yao, Huachu Wu, Jianbo Lai |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 57238 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |