DSpace Arşivi :: by Yazar "Salman, Khalid Abdalsatar" değerine göre listeleniyor

Listeleniyor 1 - 1 / 1

THE EFFICIENCY OF CLASSIFICATION TECHNIQUES IN PREDICTING THYROID DISEASE
(2021-07) Salman, Khalid Abdalsatar
Diagnostics and prediction of diseases are among the most important applications of machine learning techniques. Recently, machine learning algorithms have had an essential and convincing role in diagnosing and classifying diseases. Among these diseases, thyroid disease is a concern for human health, as the thyroid gland plays a critical role in regulating human health because it regulates human metabolism. This study used eight machine learning techniques (Support Vector Machines, Random Forest, Decision Tree, Naive Bayes, Logistic Regression, K-Nearest Neighbors, Multi-layer Perceptron (MLP), Linear Discriminant Analysis) to diagnose thyroid disease. Thyroid disease is classified in this study into three categories: hyperthyroidism, hypothyroidism, and normal. The data used in this study were collected from the laboratories of a hospital in Iraq, which consisted of 1250 records. Machine learning algorithms have achieved promising results in diagnosing thyroid diseases, helping clinicians and health workers to diagnose the disease early, and increase the chances of treatment. The Random Forest algorithm got the highest accuracy of 98.93% with all the features, and the MLP algorithm got the highest accuracy of 95.73% with the deletion of three properties which are (query_thyroxine, query_hypothyorid and query_hyperthyroid).