Integrated Machine Learning Framework for Multi-Disease Prediction and Geolocation-Based Healthcare Recommendations

Non-communicable diseases account for a growing proportion of global morbidity and mortality. Diabetes and cardiovascular diseases are among the leading causes of long-term complications, while breast cancer remains a primary contributor to cancer-related deaths in women. Diabetic retinopathy, although preventable, is a major cause of avoidable blindness when early detection is missed.Machine learning techniques have been widely applied to individual disease prediction tasks. However, most deployed systems are disease-specific and operate in isolation. Moreover, prediction outputs are often binary labels without contextual guidance, leaving patients uncertain about subsequent actions.This work addresses two gaps. First, it integrates multiple disease prediction models into a single web application. Second, it extends prediction results with geolocation-based hospital and doctor recommendations. The primary contributions of this paper are:• A unified architecture supporting four disease prediction models.• Algorithm selection tailored to dataset characteristics.• Integration of prediction outputs with healthcare recommendation logic.• Experimental evaluation using standard accuracy metrics.