There is an abundance of electronic health data as a result of the broad use of digital technologies in healthcare. Due to the overwhelming amount of data, medical practitioners are finding it difficult to diagnose various diseases early on and analyze symptoms promptly and effectively. Efficient and precise examination of health-related issues is essential for both prophylaxis and management. When it comes to complicated problems and serious illnesses, traditional diagnostic techniques might not be sufficient. Compared to existing techniques, developing a medical diagnosis system based on machine learning algorithms for disease prediction may provide a more accurate diagnostic approach. Numerous algorithms have been taken into consideration, including K-nearest neighbor (KNN), decision trees, and naive Bayes. Using these various machine learning approaches, we have developed a disease prediction system for diagnosing medical problems. This chapter’s goal is to conduct a thorough analysis of the performance measures of several supervised machine learning models in the context of disease identification.