Machine Learning Prediction of Recurrence in Pediatric Thyroid Cancer: Malignant Endocrine Tumors Cohort Analysis Using XGBoost and SHAP.

Abstract

Pediatric differentiated thyroid carcinoma (DTC) often presents with advanced disease but generally has excellent long-term survival. However, recurrence or failure to achieve remission remains relatively frequent, underscoring the need for improved early risk stratification. To develop and evaluate an interpretable machine learning model for predicting recurrence or nonremission in pediatric DTC using routine clinical and biochemical variables. Retrospective analysis of 250 pediatric patients (aged <18 years) enrolled in the German Pediatric Oncology Hematology-Malignant Endocrine Tumors Registry (1997-2023). Inclusion required known age at diagnosis and ≥24 months of follow-up. The composite study endpoint was structural recurrence or failure to achieve remission within 24 months of initial therapy. An extreme gradient boosting classifier was trained on 80% of the data, with the remaining 20% used as an independent test set. Model generalizability was assessed via 50 randomized stratified train-validation splits of the training dataset. SHapley Additive exPlanations (SHAP) were used to interpret feature contributions. The final model achieved an area under the receiver operating characteristic curve (AUROC) of 0.86 on the independent test set. Across 50 validation splits, the mean AUROC was 0.82 (SD ± 0.05), sensitivity 0.81 (SD ± 0.09), and specificity 0.64 (SD ± 0.06). SHAP analysis identified younger age at diagnosis (<10 years), elevated postoperative thyroglobulin levels, and distant metastases as the most influential predictors. This interpretable machine learning model reliably predicts early recurrence or nonremission in pediatric DTC and may complement current risk stratification systems to support personalized, risk-adapted treatment decisions.