Prediction of diabetic obese patients using machine learning techniques / Raghda Essam Abdelrazek Ali ; Supervised Hatem Mohamed Elkadi , Soha Safwat Labib , Yasmin Saad Ibrahim

Thesis (M.Sc.) - Cairo University - Faculty of Computers and Artificial Intelligence - Department of Information Systems

computing. This contribution can help in managing and interpreting various types of medical data to support decision-making. Machine learning approaches have demonstrated that it is sufficient for such complicated tasks. Early prediction of diseases in healthcare sector is very important. Diabetes disease is one of the threatening diseases whose occurrence is growing alarmingly and expected to increase more and more by 2035. Obesity is considered to be a massive risk factor of type 2 diabetes, type 2 diabetes has been proposed as a leading cause of fatty liver disease progression, it also probably reflect the quick succession of obesity and resistant to insulin in type 2 diabetes. Machine learning techniques nowadays help in diseases prediction to avoid the probability of its occurrence as much as possible. In this thesis, we explore the use of the machine learning techniques in the design of medical classification predictive models derived from the patient{u2019}s data address the complexities of designing machine learning techniques for promoting clinical decision-taking. Four machine learning classifiers have been used in this study which are; K-Nearest Neighbor, Fuzzy K-Nearest Neighbor, Support Vector Machine and Artificial Neural Network in order to detect non-alcoholic fatty liver disease and predict diabetes mellitus chronic disease.The used techniques are applied on a real dataset from Al-Kasr Al-Aini Hospital in Giza, Egypt

Issued also as CD