This research paper explores the utilization of Machine Learning (ML) techniques in disease prediction, specifically targeting diabetes, heart disease and lung cancer. As healthcare increasingly adopts data-driven decision-making through advanced data analysis and predictive modeling, our study employs established ML algorithms - Logistic Regression, Naive Bayes, K-Nearest Neighbors (KNN), and Support Vector Machines (SVM) - to accurately predict these diseases. Our primary aim is to showcase the efficacy of these algorithms, facilitating timely intervention and improved patient care by healthcare professionals. We discuss the methodology, data preprocessing, feature selection, and model evaluation for each disease prediction task, emphasizing data quality and ethical concerns. Through comprehensive experimentation, we offer insights into algorithm strengths and weaknesses, highlighting their relevance in disease prediction. This research contributes to medical informatics, highlighting ML's potential to enhance disease diagnosis and prognosis, making it a valuable resource for researchers, practitioners, and policymakers embracing ML for healthcare advancement.

Keywords : Machine Learning, Disease Prediction, Logistic Regression, Naive Bayes, K-Nearest Neighbors, and Support Vector Machines.