A Survey on Using Machine Learning to Predict Diabetes Early on

Abstract

Diabetes is a category of metabolic disease caused by a prolonged high blood sugar level. It is sometimes referred to as a chronic disease. If accurate early prediction is achievable, it can considerably lower the risk factor and severity of diabetes. Combining data mining methods with machine learning, a subsection of artificial intelligence, offers promise in the field of prediction. Data is widely available in the healthcare industry, and in order to improve prognosis, diagnosis, therapy, medication development, and healthcare in general, information must be extracted from it. Based on the World Health Organisation's 2014 report, diabetes is a type of chronic disease with the fastest global growth rates. To illustrate the widely used techniques for early diabetes detection—which are based on cutting-edge technologies including machine learning, cloud computing, etc.—we have reviewed a few significant pieces of literature in this study. The findings suggested that artificial intelligence-based methods are more effective in the early detection of diabetes in patients. Here, we used the Random Forest model to conduct an experiment using a diabetes dataset. First, the dataset is resampled and then used to train and test the Random Forest model. On all performance criteria, the Random Forest attained values above 96%.