Explainable machine learning for the early differentiation of pediatric bronchopneumonia using routine laboratory parameters

Jinxing Dai, Hao Qiu, Liran Shen, Qianjin Shi, Kang Shen, Qingkai Wang, Weibing Qiu · 2026

Read Explainable machine learning for the early differentiation of pediatric bronchopneumonia using routine laboratory parameters by Jinxing Dai, Hao Qiu, Liran Shen, Qianjin Shi, Kang Shen, Qingkai Wang, Weibing Qiu (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-0351509.txt.

Description

Jinxing Dai and six colleagues present this 2026 PLOS One study on telling two childhood lung conditions apart using ordinary blood tests. Bronchopneumonia and simple upper respiratory infections look alike at a first visit, which leads to unneeded antibiotics and scans. The team studied more than five hundred children with mild breathing symptoms and trained seven machine learning models on routine laboratory results.

A support vector machine model performed best, separating the two conditions with high accuracy on held-out cases, and its risk estimates were well calibrated. An explanation method then showed which lab values drove each prediction and at what levels they mattered most. The authors propose the tool as a cheap, noninvasive triage aid for busy clinics deciding which children need closer attention.

Catalog record

CREATORJinxing Dai, Hao Qiu, Liran Shen, Qianjin Shi, Kang Shen, Qingkai Wang, Weibing Qiu
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE40504
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0351509

Browse the full library · About the Tower of Babel