Prediction models for the occurrence and mortality of sepsis-associated lung injury: a systematic review and meta-analysis
Chen Liu, Jian Huo, Yan-Song Li, An-Min Hu, Ting-Ting Ao · 2026
Read Prediction models for the occurrence and mortality of sepsis-associated lung injury: a systematic review and meta-analysis by Chen Liu, Jian Huo, Yan-Song Li, An-Min Hu, Ting-Ting Ao (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/PMC13286850.txt.
Description
Chen Liu and colleagues appraise published models that predict lung injury or early death in sepsis patients whose lungs fail. Their 2026 systematic review found nine studies, eight from China, reporting dozens of model versions. Sepsis often strikes the lungs first, and failing lungs carry poor survival, so prediction tools have multiplied without much scrutiny.
Formal appraisal flagged high or unclear bias risk in most studies, and certainty rated low across the board. Pooled accuracy was moderate for both predicting injury and predicting death. Fancy machine learning did not reliably beat plain logistic regression. Results also varied widely between studies. The authors demand transparent designs and outside validation before any model enters care.
Catalog record
| CREATOR | Chen Liu, Jian Huo, Yan-Song Li, An-Min Hu, Ting-Ting Ao |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 49361 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |