A Comparative Study of Machine Learning Algorithms for EarlyStage and Rare Disease Diagnosis Using Highly Imbalanced Datasets

The implementation of accurate, reliable, and interpretable diagnostic tools is a pressing needin modern healthcare. This study addresses this challenge through a comprehensivecomparative analysis of machine learning algorithms—including Support Vector Machines(SVM), Random Forest, Neural Networks, and Logistic Regression—for medical diagnosisprediction. Based on systematic experimentation across multiple datasets, our resultsdemonstrate the superior performance of ensemble methods, with Random Forest excelling inaccuracy, sensitivity, and specificity. The findings provide valuable insights for healthcarepractitioners and contribute significantly to the advancement of clinical decision supportsystems.Keywords: Machine Learning, Medical Diagnosis, Healthcare Analytics, PredictiveModeling, Clinical Decision Support