Diabetes mellitus is a group of metabolic diseases showing high blood sugar levels over prolonged periods. It is one of the deadly diseases growing at rapid rates in developing countries. Diabetes has affected over 246 million people worldwide. According to the World Health Organization (WHO) report, this number is expected to rise to over 380 million by 2025. If untreated, diabetes can lead to long-term complications such as heart disease and kidney failure. Therefore, there is a great need for the timely diagnosis of diabetes for people around the world. In particular, diabetes has been identified to be a very serious threat to younger generations and working individuals. Diabetes can be managed if it can be predicted during the early stages with changes in the diet and lifestyle of the patient. Therefore, this paper proposes a model for the early prediction of diabetes by considering major risk factors. An artificial neural network model with the Levenberg-Marquardt training algorithm is built using the PIMA Indian Diabetes dataset. The objective of the study is to predict the occurrence of diabetes mellitus using known risk factors based on feed-forward artificial neural network.
展开▼
