Machine learning for the prediction of acute kidney injury in patients with sepsis.

Yue S, Li S, Huang X, Liu J, Hou X, Zhao Y, Niu D, Wang Y, Tan W, Wu J. · 2022

Read Machine learning for the prediction of acute kidney injury in patients with sepsis. by Yue S, Li S, Huang X, Liu J, Hou X, Zhao Y, Niu D, Wang Y, Tan W, Wu J. (2022) 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/europmc-pmc9101823.txt.

Description

Yue and co-authors build machine learning models that predict acute kidney injury in patients with sepsis. Kidney injury is the most common grave problem of sepsis and raises the risk of death. Early warning would let doctors act in time to help. The team drew patient data from the MIMIC-III intensive care database.

In all, 3,176 patients were studied, and 2,397 of them developed kidney injury in hospital. The team selected 36 variables and trained seven types of model. The XGBoost model scored best, with an area under the curve of 0.821. It beat standard severity scores on the same data. The authors say such models can help flag high-risk patients for early care.

Catalog record

CREATORYue S, Li S, Huang X, Liu J, Hou X, Zhao Y, Niu D, Wang Y, Tan W, Wu J.
YEAR2022
COLLECTIONPAPERS
FORMATTXT
FILE SIZE43 KB
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC9101823

Browse the full library · About the Tower of Babel