Interpretable machine learning-based clinical prediction model for predicting lymph node metastasis in patients with intrahepatic cholangiocarcinoma

Researchers developed and validated machine learning-based predictive models for lymph node metastasis (LNM) in intrahepatic cholangiocarcinoma (ICC) using clinicopathological data from 345 patients. The study used six machine learning algorithms, identifying the Extreme Gradient Boosting (XGB) model as the best, with an average area under the curve (AUC) of 0.908. Factors such as alcoholic liver disease, smoking, boundary, tumor diameter, and white blood cell count were identified as significant predictors. A web calculator based on the XGB model was created to help clinicians predict LNM and tailor treatment plans.