Abstract:In medical science, automatic disease diagnosis is an invaluable tool because of restricted observation of the specialist and uncertainties in medical knowledge. Advances in medical information technology have enabled healthcare industries to automatically collect huge amount of data through clinical laboratory examinations. To explore these data, the past few years have envisaged the use of Computer Aided Diagnosis (CAD) systems in many screening sites and hospitals. While using CAD, thyroid function diagnosis is considered as a classification problem, which can automatically identify the type of thyroid (hyper, hypo or normal). Machine learning techniques are increasingly introduced to construct the CAD systems owing to its strong capability of extracting complex relationships in the biomedical data.
Early and correct detection of thyroid disease is very important for correct and timely treatment. The need to increase the accuracy of detecting and classifying thyroid disease poses a great challenge not only to the research community but also to healthcare industries. Usage of machine learning algorithms for thyroid disease classification is an area of research that is gaining popularity for the past few years. Automatic thyroid disease computer aided system for diagnosing the disease requires sophisticated and effective algorithms to perform classification in an accurate and time efficient manner. As a solution to this demand, hybrid models that combine clustering and classification algorithms along with ensemble technology are proposed. Four category of thyroid disease prediction system are proposed. They are Clustering + Classification models, Classification + Classification Models, Clustering + Clustering Models and Classification + Clustering Models. Two types of ensembles, namely, homogeneous and heterogeneous, are also considered and analyzed. Performance evaluation showed that the Classification + Classification model based on the combination of SVM and heterogeneous KNN + SVM classifier produce highest prediction accuracy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.