Existential Risk Prediction Models for Diabetes Mellitus

Abstract

Diabetes mellitus is a disease of the human body that is caused by high blood sugar levels and inactivity, poor eating habits, being overweight etc. This paper reviewed, and analyzed diabetes mellitus Type 1, Type 2, and Gestational diabetes diverse risk prediction models and algorithms employed. In this study, the methodology adopted is the exploratory descriptive approach, which clearly describes the various deep learning and machine learning risk prediction model used for diabetes mellitus classification and forecasting problems. The Deep Neural Network Model algorithms given in this work have the highest score in terms of accuracy and outperformed machine learning models in terms of performance, there is also the issue of other various algorithms' precision. It is recommended that when conducting a classification and risk prediction survey on the different variants of diabetes mellitus, researchers consider using the algorithms explicitly described while paying close attention to their advantages and disadvantages, as well as their potential outcomes. It is also possible to combine deep learning techniques and machine learning algorithms to create ensemble models, which can improve prediction performance.