Machine learning outperforms large language models for survival prediction in advanced hepatocellular carcinoma: a multicenter study
Jiacheng Tan, Yangyang Li, Fengtao Zhang, Kai Sun, Qingkang Zheng, Huanzhang Niu · 2026
Read Machine learning outperforms large language models for survival prediction in advanced hepatocellular carcinoma: a multicenter study by Jiacheng Tan, Yangyang Li, Fengtao Zhang, Kai Sun, Qingkang Zheng, Huanzhang Niu (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-13324143.txt.
Description
Jiacheng Tan and co-authors compare machine learning models with large language models for predicting survival in advanced liver cancer, published in 2026. Exact prognosis in this disease remains an unmet need. Machine learning has shown value for such prediction, but whether chat-style models can do structured clinical forecasting was unclear.
In a multicenter retrospective study, over a thousand patients who had interventional plus targeted therapy were split into training and test cohorts. Six machine learning algorithms were built and compared with two large language models. A small set of clinical variables was picked as key predictors. In the test cohort, the best machine learning model scored highest, while both language models showed limited power. Machine learning also split patients into risk groups with clearly different one-year survival.
Catalog record
| CREATOR | Jiacheng Tan, Yangyang Li, Fengtao Zhang, Kai Sun, Qingkang Zheng, Huanzhang Niu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 31 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |