Work

Enhancing explainability of random survival forests in predicting stent patency risk for malignant colonic obstruction

Year: 2025

Type: article

Abstract: λ In this study, we found that the Random Survival Forest (RSF) model outperformed the Cox Proportional Hazards (CPH) model in predicting stent patency, with higher AUC and lower Brier scores, effectively capturing complex clinical relationships. λ Critical variables like Length of Obstruction, CA199, and Diabetes were identified using Lasso and RSF methods. Advanced techniques like SurvSHAP(t) and SurvLIME provided clear insights into the time-varying importance of key four features. λ To interpret the RSF and CPH models, we quantitatively compared global and local explanation methods. The RSF model was rigorously validated, ensuring reliability and clinical relevance, with explainability assessments demonstrating its utility for personalized treatment planning. This study aims to enhance the explainability and predictive accuracy of the Random Survival Forest (RSF) algorithm in predicting stent patency risk for patients with malignant colonic obstruction. The RSF algorithm was applied to clinical prognostic data of 109 patients with malignant colonic obstruction who underwent self-expandable metallic stent (SEMS) procedures between September 2014 and October 2023. We combined the RSF variable importance and Least Absolute Shrinkage and Selection Operator (Lasso) regression to identify the final predictive variables. And the performance of the RSF model was compared with the Cox Proportional Hazards (CPH) model using both global and local explanation methods. The RSF model demonstrated superior predictive performance, with higher time-dependent AUCs and lower Brier scores compared to the CPH model across various time points. Significant predictors of stent patency identified by the RSF and Lasso models included Diabetes, CA199, Pre-Chemotherapy and Length of obstruction. The partial dependence plots highlighted CA199 and Length of obstruction as critical variables, with SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations) analyses further revealing the dynamic, time-varying impact of these variables on individual patient outcomes. The RSF algorithm, supplemented with comprehensive feature importance analyses and advanced interpretability techniques, offers a robust and reliable framework for predicting stent patency risk in patients with malignant colonic obstruction.

Source: BMC Gastroenterology

DOI: 10.1186/s12876-025-04373-1