In current era of technology, accurate classification of heart disease, kidney disease, and diabetes is essential for effective treatment, planning and patient management. This chapter focuses on studying various Machine Learning (ML) algorithms to predict the risk of such chronic diseases by employing historical patient data. In this connection, we have employed K-Nearest Neighbors (KNN) and Logistic Regression (LR) to create the concerned predictive models for disease prediction and we have the dataset that comprises of distinct key medical indicators such as blood pressure, glucose levels, age, Body Mass Index (BMI), and other relevant health metrics. Further, the data undergoes preprocessing, including normalization and feature selection, to enhance the model performance. KNN is selected for its simplicity and ability to handle multiclass problems, while Logistic Regression is chosen for its interpretability and efficiency in linear relationships. The models are evaluated using metrics like accuracy, precision, recall, and F1 score, demonstrating their effectiveness in disease prediction. Besides, a web-based application is used that provides an accessible and user-friendly interface for users to input their health data and receive immediate risk assessments, facilitating proactive health management.