Interpretable Machine Learning Model for Survival Prediction in Pediatric Adrenocortical Tumors

Purpose Pediatric adrenocortical tumors (pACTs) are rare and clinically heterogeneous. Existing risk stratification systems rely on fixed thresholds and linear assumptions, which may limit their prognostic accuracy—particularly for non-metastatic, locally advanced cases. We aimed to develop an interpretable machine learning (ML) model for individualized survival prediction using only routine clinical features. Methods We retrospectively analyzed 97 patients with pACT from the German GPOH-MET registry (1997–2024). An XGBoost Cox proportional hazards model was trained using four features—tumor volume, distant metastases, pathologic T stage, and resection status—identified via systematic feature evaluation across 11,737 model combinations. Performance was assessed using a stratified 80/20 train-test-split, 500 bootstrap iterations, and Harrell’s concordance index (C-index). SHapley Additive exPlanations (SHAP) were used for interpretability. Results The model achieved strong prognostic performance (test-set C-index: 0.925; bootstrap mean: 0.891, 95% CI: 0.817–0.946). SHAP analysis confirmed the dominant influence of metastatic status, followed by tumor volume, T stage, and resection status. The model uncovered non-linear and additive effects, including a SHAP- and bootstrap-guided tumor volume cut-off (190 mL, 95% percentile interval 127–910 mL) that differed from conventional thresholds. Stratification remained robust in subgroups, including non-metastatic patients with advanced local disease. Conclusions This interpretable ML model enables individualized survival prediction in pACT using only routine clinical data. It offers a clinically accessible and clinically meaningful complement to existing scoring systems, particularly in patients with ambiguous risk profiles who may benefit from more personalized management.