Performance Analysis of Deep Neural Network and Machine Learning Algorithms for Diabetes Prediction

Diabetes mellitus has an issue called chronic hyperglycaemia. It might lead to a lot of problems. According to present rates of morbidity, it is expected to be 642 million diabetic patients worldwide by 2040, or one in every ten individuals. Without a doubt, more attention has to be paid to this alarming statistic. The huge and highly classified data that the healthcare industry produces must be handled with care. One of the numerous fatal diseases that are spreading around the globe is diabetes mellitus. Medical professionals want a reliable diabetes prediction system. Several machine learning techniques are used in a range of areas to do predictive modelling over huge data. Machine learning is presently applied in many fields of medical science due to its rapid progress. Although it is challenging to employ analytics to predict outcomes in healthcare, in the long run, it may assist practitioners in making quick judgements on the treatment and well-being of individuals based on vast volumes of data. Basically, Pima Indians diabetes dataset is considered in this work. The National Institute of Diabetes and Digestive and Kidney Diseases is the original repository for this dataset. In this work, seven distinct machine learning algorithms are employed and compared with deep neural network model to address the diabetes prediction. The deep neural net model gives better accuracy score as compared to conventional machine learning models.