Early prediction of severe Omicron pneumonia using a multimodal a.i. model integrating delta CT radiomics and laboratory indicators
Xiaoxian Ye, Xuhao Dai, Shengping Gong, Yingying Zhou, Ting Zhu, Binbin Song, Jiming Yang, Xiaoqin Ge, Jiangping Ren, Cong Shi, Yijian Cao · 2026
Read Early prediction of severe Omicron pneumonia using a multimodal a.i. model integrating delta CT radiomics and laboratory indicators by Xiaoxian Ye, Xuhao Dai, Shengping Gong, Yingying Zhou, Ting Zhu, Binbin Song, Jiming Yang, Xiaoqin Ge, Jiangping Ren, Cong Shi, Yijian Cao (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/PMC13562556.txt.
Description
Xiaoxian Ye and ten colleagues build a model that flags, early, which Omicron COVID-19 patients in hospital are heading for severe pneumonia. Fast triage saves beds and lives when wards fill. The 2026 model mixes two data streams: measurements drawn from repeat chest scans, capturing how lung images change over time, and laboratory results that include blood chemistry and immune cell counts. Three learning methods were tried, and the results were shaped into a scoring chart for individual risk.
Training used 91 patients from one centre, with 23 held back for internal checks and 32 from a second centre for an outside test. The combined model separated severe from milder cases well, scoring 0.885 on internal checks and 0.875 on the outside test by the standard curve measure. Scan-change features proved steady across settings. The authors want larger forward-looking studies before the tool guides real triage.
Catalog record
| CREATOR | Xiaoxian Ye, Xuhao Dai, Shengping Gong, Yingying Zhou, Ting Zhu, Binbin Song, Jiming Yang, Xiaoqin Ge, Jiangping Ren, Cong Shi, Yijian Cao |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 48090 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |