Enhanced Thyroid Disease Prediction Using Ensemble Machine Learning Techniques

Abstract

There is an urgent need for precise and effective diagnosis techniques since thyroid diseases are becoming more common and have a major negative influence on public health. Conventional diagnostic methods frequently lack speed and accuracy, which causes therapy delays and unfavorable patient outcomes. The purpose of this study is to improve the predicted accuracy of thyroid illness detection by utilizing ensemble machine learning techniques. The dataset was preprocessed to ensure cleanliness and format compatibility with machine learning algorithms. Four classifiers were used to evaluate their predictive capabilities: Bagging Classifier, Support Vector Machine (SVM), AdaBoost, and Gaussian Naive Bayes. Bagging Classifier, utilizing 50 Decision Tree estimators, emerged as the most effective model. Bagging achieved the highest accuracy (99.87%), followed closely by AdaBoost (98.87%). SVM and Naïve Bayes performed comparatively lower, with accuracy scores of 94.58% and 93.69%, respectively. These findings highlight the effectiveness of ensemble methods for accurate and reliable thyroid disease prediction. These advancements could play a crucial role in developing automated tools for early detection and monitoring of thyroid disorders, ultimately improving patient outcomes and streamlining healthcare processes.