This study presents an original empirical machine learning analysis examining the relationship between climatic variability and vector-borne disease incidence under climate change conditions. India’s climatic diversity results in region-specific disease patterns, particularly in states such as Kerala and Maharashtra. This study presents an original empirical analysis examining the relationship between climatic variables and vector-borne disease incidence using machine learning techniques. Epidemiological and climatic data from 2000 to 2015 were analysed to identify patterns linking temperature, rainfall, humidity, and vegetation to disease occurrence in the two states. Random Forest and Gradient Boosting models were developed to assess outbreak risk and evaluate predictor importance. The results indicate strong regional differences in climate sensitivity, with humidity and rainfall dominating disease risk in Kerala, while temperature and urbanization exert greater influence in Maharashtra. The study demonstrates the applicability of machine learning for climate-sensitive disease forecasting and provides evidence-based insights to support early warning systems and targeted public health interventions under changing climatic conditions.