A multimodal deep learning model predicting hyperprogressive disease for PD-1 blockade in advanced hepatocellular carcinoma
Yan Li, Xin Li, Xiaoqi Lin, Ziming Xu, Rui Li, Feng Duan, Chao An, Huijun Chen · 2026
Read A multimodal deep learning model predicting hyperprogressive disease for PD-1 blockade in advanced hepatocellular carcinoma by Yan Li, Xin Li, Xiaoqi Lin, Ziming Xu, Rui Li, Feng Duan, Chao An, Huijun Chen (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/pmc-13542075.txt.
Description
Yan Li and colleagues built a scan-plus-clinic model that flags rapid decline on liver cancer immune therapy. Published in 2026, the multi-clinic look-back study covered 665 patients with advanced liver cancer on PD-1 triple therapy. Hyperprogressive disease, a swift surge after PD-1 drugs, can kill and shut the door on later treatments, yet pre-treatment warnings were lacking.
The HOPE model fused two-phase CT scans with clinic factors and scored 0.801 inside its home data and 0.687 on outside data, beating clinic-only and scan-only rivals. Knock-out checks backed the fusion, and heat maps showed where the model looked. Subgroup and outcome checks further backed its risk sorting. The authors pitch HOPE as a clear pre-treatment aid for closer watch and risk-tuned care of high-risk patients.
Catalog record
| CREATOR | Yan Li, Xin Li, Xiaoqi Lin, Ziming Xu, Rui Li, Feng Duan, Chao An, Huijun Chen |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 77 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |