Doctors and other healthcare practitioners face enormous problems due to the emergence of new diseases and the growing complexity of current ailments. In order to assess the probability of illness incidence in patients, this research investigates machine learning methods for disease risk prediction using classification algorithms. Finding the best method is our main emphasis; thus, we compare the performance of DT, SVM, and NB classifiers. This work assesses the accuracy of illness risk prediction using Naive Bayes, SVM, and DT algorithms. We evaluate various algorithms on a similar dataset using measures like AUC, accuracy, precision, F1-Score, and recall. There is promising evidence that SVMs can improve clinical decision-making by outperforming competing methods in terms of accuracy and dependability.