Machine learning-based prognostic prediction and surgical guidance for intrahepatic cholangiocarcinoma

Abstract

The prognosis following radical surgery for intrahepatic cholangiocarcinoma (ICC) is poor, and optimal follow-up strategies remain unclear, with ongoing debates regarding anatomic resection (AR) versus non-anatomic resection (NAR). This study included 680 patients from five hospitals, comparing a combination of eight feature screening methods and 11 machine learning algorithms to predict prognosis and construct integrated models. These models were assessed using nested cross-validation and various datasets, benchmarked against TNM stage and performance status. Evaluation metrics such as area under the curve (AUC) were applied. Prognostic models incorporating screened features showed superior performance compared to unselected models, with AR emerging as a key variable. Treatment recommendation models for surgical approaches, including DeepSurv, neural network multitask logistic regression (N-MTLR), and Kernel support vector machine (SVM), indicated that N-MTLR's recommendations were associated with survival benefits. Additionally, some patients identified as suitable for NAR were within groups previously considered for AR. In conclusion, three robust clinical models were developed to predict ICC prognosis and optimize surgical decisions, improving patient outcomes and supporting shared decision-making for patients and surgeons.