A Novel Framework to Explore the Spatiotemporal Dynamics of Respiratory Syncytial Virus

Respiratory syncytial virus (RSV) poses a substantial burden of disease globally among children under five and elders. Given the importance of identifying the spatiotemporal traits of RSV epidemics to provide insights for region-specific public health prevention strategies, we proposed a novel framework to investigate the spatiotemporal dynamics of RSV transmission and the meteorological factors that drive RSV epidemics. We used Japan as our pilot research area, considering it has a heavy disease burden of RSV and has varying climate regions. Our preliminary results show that average temperature, relative humidity, and visibility have significant impacts on RSV epidemics, varying by climate region throughout Japan. Additionally, deep learning techniques could better simulate and forecast RSV trends based on the data features. By applying the proposed research framework, this study deepened the understanding of spatiotemporal patterns of RSV epidemics in Japan and revealed how meteorological variables were associated with RSV epidemics in varying climate conditions.