Prediction Using SVM and DT

Abstract

Diabetes is recognized as a severe and persistent illness that leads to an elevation in blood sugar levels. Untreated and undetected diabetes can give rise to numerous complications. The laborious process of identification typically involves a patient visiting a diagnostic centre and consulting with a doctor. However, the advancement of machine learning approaches has addressed this critical issue. The objective of this study is to develop a model capable of predicting the likelihood of diabetes in patients with the utmost accuracy. To achieve this goal, three machine learning classification algorithms—Decision Tree, SVM, and Naive Bayes—are employed in this experiment to identify diabetes at an early stage. The experiments are conducted on the Pima Indians Diabetes Database (PIDD), sourced from the UCI machine learning repository. The performance of each algorithm is assessed using various metrics such as Precision, Accuracy, F-Measure, and Recall. Accuracy is gauged based on both correctly and incorrectly classified instances. The results indicate that Naive Bayes outperforms the other algorithms, achieving the highest accuracy of 76.30%. These findings are corroborated through a meticulous examination of Receiver Operating Characteristic (ROC) curves.