GIS-Enhanced Bayesian Reinforcement Learning for Vector-Borne Infectious Disease Transmission

Vector-borne infectious diseases has continue to pose a significant challenge to global public health, and accurate and timely transmission prediction are crucial for effective intervention and control. The development of accurate and efficient vector-borne infectious disease predictive models has been the current trend in disease modeling. Modeling transmission, however, has assumed a discrete transmission space, which is not always ideal in the real world, and little attention has been paid to overestimation biases in predictions. The effectiveness of a predictive model is also determined by its capability to capture a significant number of data characteristics to enhance robust and accurate prediction of cases. The study proposed the application of a GIS-enhanced Bayesian Reinforcement learning model for the transmission of vector-borne infectious diseases, and model performance assessment was determined. The Bayesian quantifies the uncertainty in the parameters of models, and min-max ensemble Q-value estimation minimizes overestimation bias in the model. Simulation study was used to evaluate model performance, success rate, and interaction rate. The findings show that vector and human can avoid interaction with a success rate of 96.2% when human select combined intervention actions spray repellent, insecticide treated nets, larval management, and vaccination. Other variables such as education, wealth index, community participation, and gender empowerment significantly influence the transmission of the disease in the area. The model demonstrates a better performance in describing the transmission of the disease, therefore setting the stage for future research in predictive modeling within sub-Saharan disease-prone regions. The model can be used to determine the appropriate actions that the human should adopt to reduce human-vector interaction.