Diabetes Prediction Tool under System on Chip Using Machine Learning Method

Extraordinary advances in biotechnology and health sciences have brought significant generation of data, such as genetic data clinical information, generated from huge electronic records. Data analysis is a process studying identifying hidden patterns large amounts drawing conclusions. In care, this analytical carried out using machine learning (ML) algorithms to analyze medical build Machine Learning models transform all available information into valuable knowledge. Nowadays, diabetes has become common disease among young people, elderly even children. According the World Health Organization (WHO) report, by 2025, number expected exceed 380 million. This research work performs comparison 5 classification techniques, namely Naive Bayes (NB), Bagging (J48), Decision Tree (J48, C4.5), K Nearest Neighbors (KNN), Support Vector (SVM), detect at an early stage. The performances five are evaluated compared on various measures like accuracy, precision, recall. experiments were conducted based database, source National Institute Diabetes, Digestive Kidney Diseases, showing effectiveness (DT) technique. led choice method. After obtaining DT model problem, main task facing us hardware implementation model. Indeed, forecasting system can be used other complementary works processing unit cloud, able manage numerous requests. considered solution Field Programmable Gate Array (FPGA) board.