Diabetic retinopathy is a leading cause of vision impairment and blindness worldwide, affecting millions annually. Arising from prolonged hyperglycaemia, it damages the retina's blood vessels, leading to retinal ischaemia, microaneurysms, and haemorrhages, which may result in vision loss or blindness. In 2020, 103.12 million adults globally were affected by DR, with projections reaching 160.50 million by 2045. Timely detection is crucial for preventing vision loss and improving quality of life, while also reducing the societal burden of blindness. The rise of deep learning, particularly convolutional neural networks (CNNs), has revolutionized automated DR detection, offering a promising path for early intervention. Technologies such as fundus photography, optical coherence tomography (OCT), and AI-driven screening systems complement these advancements. This project proposes a Health Monitoring System that uses CNNs to automate DR detection and grading. By incorporating personalized patient data, the system enhances diagnostic accuracy and provides tailored recommendations to patients and doctors. This personalized approach aims to prevent vision loss and improve patient outcome.