Machine learning serves a crucial role in modern healthcare, aiding in the identification, diagnosis, and prediction of diseases. This paper provides a comprehensive and detailed review of recent research studies that explore various machine learning techniques, methods, and frameworks for disease prediction. These studies investigate different ways to predict health issues: some use wear- able devices to track data and make predictions, while others focus on predicting chronic diseases or the risk of creation of non-communicable diseases like dia- betes or chronic conditions such as cardiac infractions or certain types of cancers. The algorithms discussed range from models like DT (Decision Tree), SVM (Support Vector Machine), RF (Random Forest), KNN (K-Nearest Neighbors), and more. This paper offers an elaborate review of potential applications, meth- ods used, and results, presenting a dynamic perspective on how ML is shaping the future of healthcare diagnostics.