Identification of key factors and explainability analysis for surgical decision-making in hepatic alveolar echinococcosis assisted by machine learning.

Abstract

Background: Echinococcosis, caused by Echinococcus parasites, includes alveolar echinococcosis (AE), the most lethal form, primarily affecting the liver with a 90% mortality rate without prompt treatment. While radical surgery combined with antiparasitic therapy is ideal, many patients present late, missing hepatectomy opportunities. Ex vivo liver resection and autotransplantation (ELRA) offers hope for such patients. Traditional surgical decision-making, relying on clinical experience, is prone to bias. Machine learning can enhance decision-making by identifying key factors influencing surgical choices. This study innovatively employs multiple machine learning methods by integrating various feature selection techniques and SHapley Additive exPlanations (SHAP) interpretive analysis to deeply explore the key decision factors influencing surgical strategies.

Aim: To determine the key preoperative factors influencing surgical decision-making in hepatic AE (HAE) using machine learning.

Methods: This was a retrospective cohort study at the First Affiliated Hospital of Xinjiang Medical University (July 2010 to August 2024). There were 710 HAE patients (545 hepatectomy and 165 ELRA) with complete clinical data. Data included demographics, laboratory indicators, imaging, and pathology. Feature selection was performed using recursive feature elimination, minimum redundancy maximum relevance, and least absolute shrinkage and selection operator regression, with the intersection of these methods yielding 10 critical features. Eleven machine-learning algorithms were compared, with eXtreme Gradient Boosting (XGBoost) optimized using Bayesian optimization. Model interpretability was assessed using SHAP analysis.

Results: The XGBoost model achieved an area under the curve of 0.935 in the training set and 0.734 in the validation set. The optimal threshold (0.28) yielded sensitivity of 93.6% and specificity of 90.9%. SHAP analysis identified type of vascular invasion as the most important feature, followed by platelet count and prothrombin time. Lesions invading the hepatic vein, inferior vena cava, or multiple vessels significantly increased the likelihood of ELRA. Calibration curves showed good agreement between predicted and observed probabilities (0.2-0.7 range). The model demonstrated high net clinical benefit in Decision Curve Analysis, with accuracy of 0.837, recall of 0.745, and F1 score of 0.788.

Conclusion: Vascular invasion is the dominant factor influencing the choice of surgical approach in HAE. Machine-learning models, particularly XGBoost, can provide transparent and data-driven support for personalized decision-making.