Machine Learning Algorithms for Early Detection of Diabetes: An Indian Perspective

Worldwide, Diabetes is a chronic disorder that affects millions of people and with early diagnosis and treatment, serious diabetes-related effects like heart disease, stroke, and blindness can be avoided. This study compares the performance of machine learning algorithms for the early identification of diabetes with the perspective of India. These techniques include Gradient Boosting (GB), Extreme Gradient Boosting (EGB), Convolutional Neural Network (CNN), and Extra Decision Tree (EDT), Gaussian Nave Bayes (GNB), Support Vector Machine (SVM), Logistic Regression (LR), Decision Tree (DT), K-Nearest Neighbor (KNN), Random Forest (RF), and SVM. The algorithms were evaluated using the Pima Indians Diabetes dataset, a publicly available dataset of diabetes disease. The experimental findings demonstrate that the CNN algorithm obtains the best level accuracy of 99% for early diagnosis of diabetes.