Development and validation of interpretable machine learning models for postoperative pneumonia prediction

Bingbing Xiang, Yiran Liu, Shulan Jiao, Wensheng Zhang, Shun Wang, Mingliang Yi · 2024

Read Development and validation of interpretable machine learning models for postoperative pneumonia prediction by Bingbing Xiang, Yiran Liu, Shulan Jiao, Wensheng Zhang, Shun Wang, Mingliang Yi (2024) 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-11670315.txt.

Description

Bingbing Xiang and co-authors train nine learning algorithms to flag surgery patients headed for pneumonia. Lung infection after an operation stretches stays, fills intensive care beds, and kills. From records of over seventeen thousand surgical patients, the team built a matched set of five hundred twenty-eight, half with pneumonia and half without. They then sifted forty-seven candidate clues down to five strong ones.

All nine models learned to sort the groups, and a plain general linear model did it best overall. The team plotted which factors drove each call so clinicians can see the reasoning rather than trust a black box. They frame the tool as an early-warning aid for wards, prompting closer watching and preventive care for flagged patients.

Catalog record

CREATORBingbing Xiang, Yiran Liu, Shulan Jiao, Wensheng Zhang, Shun Wang, Mingliang Yi
YEAR2024
COLLECTIONPAPERS
FORMATTXT
FILE SIZE31 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11670315

Browse the full library · About the Tower of Babel