Explaining Risk Stratification in Differentiated Thyroid Cancer Using SHAP and Machine Learning Approaches

<b>Background/Objectives</b>: Differentiated thyroid cancer (DTC) represents over 90% of all hyroid malignancies and typically has a favorable prognosis. However, approximately 30% of patients experience recurrence within 10 years after initial treatment. Conventional risk classification frameworks such as the American Thyroid Association (ATA) and AJCC TNM systems rely heavily on pathological interpretation, which may introduce observer variability and incomplete documentation. This study aimed to develop an interpretable machine-learning framework for risk stratification in DTC and to identify major clinical predictors using SHapley Additive exPlanations (SHAP). <b>Methods</b>: A retrospective dataset of 345 patients was obtained from the UCI Machine Learning Repository. Thirteen clinicopathological features were analyzed, including Age, Gender, T, N, M, Hx Radiotherapy, Focality, Adenopathy, Pathology, and Response. Statistical analysis and feature selection (ReliefF and mRMR) were applied to identify the most influential variables. Two modeling scenarios were tested using an optimizable neural network classifier: (1) all 10 core features and (2) reduced features selected from machine learning criteria. SHAP analysis was used to explain model predictions and determine feature impact for each risk category. <b>Results</b>: Reducing the input features from 10 to 6 led to improved performance in the explainable neural network model (AUC = 0.94, accuracy = 92%), confirming that T, N, Response, Age, M, and Hx Radiotherapy were the most informative predictors. SHAP analysis highlighted N and T as the dominant drivers of high-risk classification, while Response enhanced postoperative biological interpretation. Notably, when Response was excluded (Scenario III), the optimizable tree model still achieved strong predictive performance (AUC = 0.93-0.96), demonstrating that accurate preoperative risk estimation can be achieved using only clinical baseline features. <b>Conclusions</b>: The proposed interpretable neural network model effectively stratifies recurrence risk in DTC while reducing dependence on subjective pathological interpretation. SHAP-based feature attribution enhances clinical transparency, supporting integration of explainable machine learning into thyroid cancer follow-up and personalized management.