Enhancing Diabetic Disease Prediction With Optimized Random Forest Using Machine Learning

Abstract

According to recent increases in morbidity, the number of diabetic patients worldwide is expected to reach 642 million by 2040, or one out of every ten persons. Diabetes is a chronic disease that affects millions of people worldwide. Early diagnosis and management of the disease can significantly improve patient outcomes. In recent years, machine learning techniques, particularly Advanced Decision Ensemble(ADF) Algorithms, have emerged as a promising approach for predicting diabetes. In this paper, we propose a ADF algorithm using Grid Search Method based diabetes prediction model that uses cutting-edge machine learning techniques to achieve high accuracy in predicting diabetes. Our model uses a combination of traditional features such as age, BMI, and blood pressure, as well as newer features such as retinal images and gene expression data. The obtained results showed that our proposed ADF method based on the DNN technique provides promising performances with an accuracy of 97%, Recall 96% and F-Measure 94%.