Ensemble Machine Learning Algor ithms for Predicting Thyroid Disorders in Diabetic Patients: A Comparative Analysis

Thyroid diseases represent a significant health challenge due to their high prevalence and complex interactions with other diseases, negatively impacting quality of life and increasing the cost and complexity of treatment. Machine learning techniques have proven effective in medical applications, particularly in enhancing diagnostic accuracy and predictive performance. This study aims to develop an early prediction application for thyroid disorders in diabetic patients by comparing individual machine learning models—Decision Tree (DT), K-Nearest Neighbors (KNN), Gaussian Naïve Bayes (GNB), Support Vector Machine (SVM), and Logistic Regression (LR)—with ensemble learning models, including Random Forest (RF), Voting, Bagging, AdaBoost, Gradient Boosting, and Stacking. The results demonstrated that the Support Vector Machine (SVM) model outperformed other base models, achieving an accuracy of 97%, a precision of 93%, and sensitivity and specificity of 85% each. The K-Nearest Neighbors (KNN) model achieved an accuracy of 97%, a precision of 91%, and sensitivity and specificity of 83% each. Similarly, the Logistic Regression (LR) model achieved an accuracy of 97%, a precision of 90%, and sensitivity and specificity of 84% each. Among the ensemble methods, the Gradient Boosting method achieved the highest performance, with an accuracy of 97%, a precision of 92%, and sensitivity and specificity of 88% each. The Voting model achieved an accuracy of 97%, a precision of 92%, and sensitivity and specificity of 87% each. The Random Forest (RF) model achieved an accuracy of 97%, a precision of 89%, and sensitivity and specificity of 88% each. The significance of this study lies in early prediction of thyroid disorders in diabetic patients. We recommend the use of ensemble learning models due to their effectiveness in early diagnosis and prediction of pathological conditions as part of a computer-based medical diagnostic system.