Chronic diseases like diabetes and heart disease have become more and more routine, thus, the major obstacle in the public health sector all over the world. Machine learning methods have become incredibly useful in the medical field of study, providing effective and reliable solutions to complicated problems. This study is directed toward the healthcare sector, which aims to determine the most appropriate machine learning techniques to predict these diseases. Two different datasets were used to gather knowledge collected from various sources. To identify heart disease and diabetes, we used supervised machine learning algorithms, such as Decision Tree, Random Forest, Logistic Regression, KNN, and SVM. We also evaluated the algorithms’ accuracy and illness detection efficiency. Random Forest performs the best in both datasets after hyperparameter tuning with 99% accuracy for both heart disease prediction and diabetes prediction. Furthermore, we incorporated model explainability techniques such as SHAP and LIME to ensure transparency and interpretability of the predictions, providing valuable insights into how the models make their decisions and which features are most influential in determining disease risk.