An interpretable radiomics–machine learning model for early risk stratification of invasive fungal infections in community-acquired pneumonia: a dual-center study
Wenzhang He, Yulin Xiong, Xuan Huang, Haoran Luo, Shaoquan Zhou, Yongbo Tu, Tie Deng, Min Gu · 2026
Read An interpretable radiomics–machine learning model for early risk stratification of invasive fungal infections in community-acquired pneumonia: a dual-center study by Wenzhang He, Yulin Xiong, Xuan Huang, Haoran Luo, Shaoquan Zhou, Yongbo Tu, Tie Deng, Min Gu (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/PMC13526825.txt.
Description
Wenzhang He and others build, in a 2026 study, a machine learning model that shows its reasoning, to flag serious fungal infection early in pneumonia caught outside hospital. Such infections are risky and hard to confirm quickly. The model mines hundreds of texture features from chest CT, set beside usual medical factors.
The study took in 570 pneumonia patients from two hospitals, scanned between July 2022 and August 2024, split into training, internal test, and external test sets. Software outlined the infected lung regions on its own. The joint model reached areas under the curve near 0.81 on the inside set and 0.79 on the outside set. It beat versions that used medical factors alone or image features alone, and it gave better net benefit when weighed for real-world use. Age swayed the model's calls most, followed by fine texture details. Explanation tools made each single call open to checks by doctors.
Catalog record
| CREATOR | Wenzhang He, Yulin Xiong, Xuan Huang, Haoran Luo, Shaoquan Zhou, Yongbo Tu, Tie Deng, Min Gu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 47194 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |