Staged identification of CAP in fever patients across epidemic environments: modeling & validation
Ziheng Gao, Tengfei Chen, Yanxiang Ha, Yifan Shi, Xiaolong Xu, Bo Li, Qingquan Liu · 2025
Read Staged identification of CAP in fever patients across epidemic environments: modeling & validation by Ziheng Gao, Tengfei Chen, Yanxiang Ha, Yifan Shi, Xiaolong Xu, Bo Li, Qingquan Liu (2025) 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-12770393.txt.
Description
Ziheng Gao and co-authors built a staged model in 2025 that flags community-acquired pneumonia in fever patients without leaning on costly imaging. Diagnosis usually needs a scan, which strains low-resource clinics. Older tools also serve clinicians, not patients, and a traditional Chinese medicine subtype split lacked clear criteria.
Their fusion model learns from basic facts, records, and lab tests to score pneumonia risk, joining top models in an ensemble. Training used more than two thousand fever clinic visits in Beijing from late 2021 to late 2022, with a later set of three hundred for validation. Unsupervised learning sorted the traditional subtypes. Readers get a triage tool built for the setting where the scan is the bottleneck.
Catalog record
| CREATOR | Ziheng Gao, Tengfei Chen, Yanxiang Ha, Yifan Shi, Xiaolong Xu, Bo Li, Qingquan Liu |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 50 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |