Computer Aided Diagnosis of Thyroid Disease Using Machine Learning Algorithms

This paper presents a comprehensive study of investigating the performance of different machine learning algorithms in the diagnosis of thyroid disease. Detecting thyroid disease at an early stage is a task of utmost significance because fatal thyroid diseases like thyroid cancer can be fully cured with proper treatment. Therefore, machine learning (ML) has made its way up to be a reliable component to predict thyroid diseases. A dataset from the University of California, Irvine (UCI) repository has been trained and tested to build the model classifier. Several classifying machine learning algorithms were implemented on the dataset and their corresponding confusion matrices were presented. Subsequently, a detailed comparative analysis was carried out in terms of accuracy, precision, sensitivity, F1 score, ROC-AUC which provided conclusive evidence that Multilayer Perceptron (MLPC) was the most proficient algorithm among these algorithms with an accuracy of 99.70% after hyperparameter optimization.