Risk Estimate of Complications in Type 2 Diabetes Using Ensemble Learning and Deep Learning

More than 34.2 million people (one in ten Americans) have diabetes, and 90% of them have type 2 diabetes. Most people with type 2 diabetes are above the age of 45, but it is also becoming more common in children, teenagers, and young adults. Diabetes and related health issues must be prevented by early diagnosis and treatment. The purpose of this study is to evaluate females’ risk of developing diabetes depending on their age, glucose, BMI, and insulin levels. Multiple machine-learning ensemble models and a deep learning model are used to predict the risk of Type 2 diabetes in females, and the model with the best performance is chosen to forecast the risk estimate for complications in people with type 2 diabetes. We also compare and contrast the usage of these models on two different-sized datasets and achieve an accuracy of more than 90% for both the datasets.