Development and Validation of an Interpretable Machine Learning Model to Predict Mortality in Patients With Sepsis-Induced Coagulopathy: Multicenter Cohort Study

Jiaxuan Sun, Jingyuan Wang, Yuxin Dong, Jieyu Liu, Yiyun Ding, Shilin Fan, Dongyue Chen, Songtao Shou, Arriel Benis · 2026

Read Development and Validation of an Interpretable Machine Learning Model to Predict Mortality in Patients With Sepsis-Induced Coagulopathy: Multicenter Cohort Study by Jiaxuan Sun, Jingyuan Wang, Yuxin Dong, Jieyu Liu, Yiyun Ding, Shilin Fan, Dongyue Chen, Songtao Shou, Arriel Benis (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/PMC13592666.txt.

Description

Jiaxuan Sun leads a team building a machine learning tool that predicts early death in sepsis patients whose blood clotting has gone wrong. Standard severity scores miss tangled, nonlinear patterns in such patients. Records came from three intensive care databases in the United States and China, totaling about twelve thousand cases. Twelve learning methods were trained on ten chosen predictors and judged against four classic scores, with explanation tools exposing what drove each call.

One boosted tree model won clearly, scoring near 0.90 on accuracy curves inside its home data and holding up in both outside sets. It beat every classic score and promised more clinical benefit. Anion gap, red cell spread, lactate, bilirubin, and age topped the driver list. Sun and the team shipped a free web tool so clinicians can run the model at the bedside.

Catalog record

CREATORJiaxuan Sun, Jingyuan Wang, Yuxin Dong, Jieyu Liu, Yiyun Ding, Shilin Fan, Dongyue Chen, Songtao Shou, Arriel Benis
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE39 KB
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13592666

Browse the full library · About the Tower of Babel