Machine learning model based on clinical and imaging features for predicting fungal infections in children with leukemia

Peng Ge, Xu-sheng Qian, Yu He, Ya-kang Dai, Wan-liang Guo · 2026

Read Machine learning model based on clinical and imaging features for predicting fungal infections in children with leukemia by Peng Ge, Xu-sheng Qian, Yu He, Ya-kang Dai, Wan-liang Guo (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/PMC13629111.txt.

Description

Peng Ge and four colleagues built machine learning models to predict dangerous fungal infections in children being treated for leukaemia, published in 2026. These children face high infection risk because their disease and chemotherapy suppress immunity, and early prediction could speed up protective treatment.

Working from 247 young patients, the team trained five algorithms on clinical data, imaging features, or both, then checked the winner in a fresh group of sixty-one children. A support vector machine fed both data types performed best by a clear margin, outscoring three radiologists of differing experience. Chest findings such as pleural thickening, low white cell counts, and hormone treatment carried the most predictive weight. The authors present the model as decision support, not a replacement for clinicians.

Catalog record

CREATORPeng Ge, Xu-sheng Qian, Yu He, Ya-kang Dai, Wan-liang Guo
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE33338
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13629111

Browse the full library · About the Tower of Babel