Abstract: The health sector is one of the most important sectors; because it affects people’s lives. The thyroid gland is located at the front of the neck. It is one of the most important glands; that is because it is responsibility on the metabolism. Thyroid Gland releases hormones that affect the human lifestyle, activity, and health. The thyroid diseases are hyperthyroidism, hypothyroidism, and thyroid cancer. The early detection of these diseases gives the patient better opportunity to get faster recovery. Machine learning (ML)--based models are used widely these days to predict several types of disease. However, the performance from one ML to another differs throughout different applications. This study performs several prediction models based on the most common ML algorithms including support vector machine (SVM), naïve Bayes (NB), artificial neural network (ANN), NB network, and Logistic classifiers. The models’ performances were assessed in predicting Thyroid disease using several evaluation metrics including accuracy, precision, recall, F-measure, ROC, and PRC. The results show that different classifiers could provide remarkable performance in detecting Thyroid disease, and the maximum accuracy is obtained at 97.664% by using the Logistic classifier.

Keywords: Thyroid, Health Data, Machine Learning, hyperthyroidism, hypothyroidism, NB- Network, Prediction

Pages: 275-283