Earlier Detection of Diabetes Using Random Forest Algorithm

Diabetes is the most deadly and chronic diseases, causes blood sugar levels to increase.. Diabetes can cause a wide range of consequences if it is not properly managed and diagnosed. As a result, a patient is scheduled for a medical consultation. However, the development of machine learning methods overcomes this large problem. This study's objective is to develop a model that can predict someone's risk of developing diabetes. This experiment uses the k-Nearest Neighbors Classification Model, Logistic Regression Model, Decision Tree, Random Forest Classifier, Gradient Boosting Classifier, and SVM as six machine learning classification methods for to early- stage diabetes detection. The Pima Indians Diabetes Database (PIDD), is used in this study. The ratio of cases that were properly and incorrectly categorized serves as a measure of accuracy. The Random Forest Classifier performs better than previous algorithms, with a maximum accuracy of 94%. To display the data, we'll utilize a heatmap, pair plot, and count plot.