Survival prediction in colorectal cancer liver metastases using machine learning with SHAP-based interpretation
Nan Li, Baoxin Dong, Yu Liang, Likun Liu, Xixing Wang, Ce Zhang, Shulan Hao · 2026
Read Survival prediction in colorectal cancer liver metastases using machine learning with SHAP-based interpretation by Nan Li, Baoxin Dong, Yu Liang, Likun Liu, Xixing Wang, Ce Zhang, Shulan Hao (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/PMC13290457.txt.
Description
Predicting how long patients with colorectal cancer spread to the liver will live is the aim of a 2026 machine-learning study by Nan Li and colleagues. Standard statistics struggle with the tangled, nonlinear links among clinical variables, so the team built and checked six algorithms.
From a retrospective cohort of 861 patients, the models learned to forecast survival at 36 and 60 months, with traditional Chinese medicine exposure among the inputs. An optimized XGBoost model performed best and held up on a later, temporal validation set. Explanation analysis ranked TNM stage, liver metastasis burden, and the intensity of Chinese medicine treatment as the strongest factors, with heavier treatment linked to better survival in a dose-like pattern. The group deployed the model as a web tool that returns personal risk estimates with visible reasoning.
Catalog record
| CREATOR | Nan Li, Baoxin Dong, Yu Liang, Likun Liu, Xixing Wang, Ce Zhang, Shulan Hao |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 43802 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |