Machine learning predicts early recurrence risk in cholangiocarcinoma

A novel machine learning model effectively predicts very early recurrence (VER) of perihilar cholangiocarcinoma (PCCA) post-surgery. In a study of 434 patients, 15% experienced VER, significantly reducing median overall survival to 8.4 months compared to 38.5 months for those without recurrence (p<0.001). The XGBoost model's stratification capabilities enhance surgical decision-making and patient counseling, identifying high-risk individuals who may benefit most from treatment.