Machine learning based hepatic safety score predicts decompensation in hepatocellular carcinoma systemic therapy
Ji Won Han, Jaejun Lee, Keungmo Yang, Kwon Yong Tak, Hyun Yang, Si Hyun Bae, Hee Sun Cho, Heechul Nam, Chang Wook Kim, Hae Lim Lee, Hee Yeon Kim, Sung Won Lee, Ahlim Lee, Do Seon Song, Seok Hwan Kim, Myeong Jun Song, Soon Woo Nam, Soon Kyu Lee, Jung Hyun Kwon, Pil Soo Sung, Jeong Won Jang · 2026
Read Machine learning based hepatic safety score predicts decompensation in hepatocellular carcinoma systemic therapy by Ji Won Han, Jaejun Lee, Keungmo Yang, Kwon Yong Tak, Hyun Yang, Si Hyun Bae, Hee Sun Cho, Heechul Nam, Chang Wook Kim, Hae Lim Lee, Hee Yeon Kim, Sung Won Lee, Ahlim Lee, Do Seon Song, Seok Hwan Kim, Myeong Jun Song, Soon Woo Nam, Soon Kyu Lee, Jung Hyun Kwon, Pil Soo Sung, Jeong Won Jang (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-13470065.txt.
Description
Ji Won Han and colleagues built a machine learning liver safety score in 2026 to predict decompensation during systemic therapy for unresectable liver cancer. Portal hypertension raises bleeding and liver failure risk on therapy, yet treatment choice rarely weighs it formally. A random forest model trained on 1,262 patients and validated on 764 predicted significant portal hypertension and prognosis.
The score reached 0.840 area under the curve, and high-score patients faced decompensation risk 3.25-fold, bleeding risk 4.90-fold, and death risk 2.21-fold higher. Atezolizumab-bevacizumab helped low-score patients but brought bleeding without survival gain in high-score patients. Simulated score-guided choice cut decompensation 24%, bleeding 40%, and mortality 26%, backing personalised regimen selection.
Catalog record
| CREATOR | Ji Won Han, Jaejun Lee, Keungmo Yang, Kwon Yong Tak, Hyun Yang, Si Hyun Bae, Hee Sun Cho, Heechul Nam, Chang Wook Kim, Hae Lim Lee, Hee Yeon Kim, Sung Won Lee, Ahlim Lee, Do Seon Song, Seok Hwan Kim, Myeong Jun Song, Soon Woo Nam, Soon Kyu Lee, Jung Hyun Kwon, Pil Soo Sung, Jeong Won Jang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 41 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |