Classification of Thyroid Disease Risk Using the XGBoost Method

Thyroid disease is one of the essential health threats and requires early detection to enable more effective medical intervention. This study aims to develop a classification model using the XGBoost algorithm to categorize patient clinical data from the Kaggle platform into three levels of thyroid cancer risk: low, moderate, and high. The data processing process follows the stages of the SEMMA (Sample, Explore, Modify, Model, Assess) methodology, with main techniques such as label coding, stratified 5-fold cross-validation, and hyperparameter tuning being applied. Performance evaluation was conducted using accuracy metrics, including F1-score and AUC-ROC. The results show that the model exhibits excellent performance in detecting low-risk cases (AUC = 1.00), but it still faces challenges in classifying moderate and high-risk categories. After adjusting the hyperparameters, the validation accuracy increased to 96.24%, although the final accuracy on the test data remained at 69.85%. These findings suggest that XGBoost is a promising approach for the early assessment of thyroid disease risk, particularly in detecting low-risk cases. However, further model development is needed to enhance generalizability across risk levels and support informed clinical decision-making.