The increasing prevalence of electronic health data has prompted a shift towards supervised machine learning (ML) algorithms for enhanced disease detection in healthcare. This study investigates the performance trends of these algorithms, highlighting the proficiency of Support Vector Machine (SVM) in detecting kidney diseases and Parkinson’s disease. Logistic Regression (LR) excels in predicting heart diseases, while Random Forest (RF) and Convolutional Neural Networks (CNN) show promise in forecasting breast diseases and common ailments, respectively. This research contributes valuable insights for leveraging ML models in disease diagnosis, signifying a potential paradigm shift in healthcare methodologies