This paper focuses on revolutionizing health insurance eligibility assessments by deploying advanced machine learning algorithms. Through the analysis of extensive medical records, including historical diagnoses, symptoms, and health indicators, our automated system predicts the likelihood of heart disease, diabetes, liver disease, lung cancer and abnormal RBC counts. Using classification and clustering approaches together improves disease profiling's precision and effectiveness. This data-driven approach aims to streamline the eligibility process, significantly reducing administrative burdens for both applicants and insurance providers. The system provides an objective and personalized evaluation of an individual's health status, contributing to a fair and sustainable health insurance market. This paper model not only aids in predicting specific diseases but also serves as a tool to mitigate adverse selection risks, ensuring a more equitable distribution of insurance coverage. By fostering a comprehensive understanding of an individual's health profile. This paper significantly contributes to improving healthcare accessibility and providing financial security.