This research was carried out to compare the applicability of machine learning techniques in a way to support decision making in Thyroid disease diagnosis. In this research work, two types of machine learning algorithms; Multilayer perceptron Neural Network with Back-propagation and Random Forest were used, and a comparison of their performance was done to identify the most suitable machine learning algorithm which can be used to assist the diagnostic process of Thyroid diseases. Each of the models developed under the two machine learning techniques were trained and tested using two thyroid datasets from the UCI machine learning repository. The performance of the models was evaluated using the performance measures, Accuracy (%), Mean Absolute Error, Root Mean Squared Error, True Positive rate, False Positive rate, Precision and Recall.
W.K.D. Jayamini, K.G.H.D. Weerasinghe (2021); Decision Support for Diagnosing Thyroid Diseases using Machine Learning; International Journal of Scientific and Research Publications (IJSRP)
11(6) (ISSN: 2250-3153), DOI: http://dx.doi.org/10.29322/IJSRP.11.06.2021.p11402