Seasonal shift in epidemics of respiratory syncytial virus infection in Japan

Abstract

In Japan, respiratory syncytial virus (RSV) infection generally has occurred during autumn and winter. However, a possible change in the seasonal trend of RSV infection has been observed recently. The current study was conducted to determine whether the epidemic season of RSV infection in Japan has indeed changed significantly. We used expectation-based Poisson scan statistics to detect periods with high weekly reported RSV cases (epidemic cluster), and the epidemic clusters were detected between September and December in the 2012-2016 seasons while those were detected between July and October in the 2017-2019 seasons. Non-linear and linear ordinary least squares regression models were built to evaluate whether there is a difference in year trend in the epidemic seasonality, and the epidemic season was shifted to earlier in the year in 2017-2019 compared to that in 2012-2016. Although the reason for the shift is unclear, this information may help in clinical practice and public health.

Keywords: Epidemics; respiratory syncytial virus infections; seasonal shift.

Fig. 1.

Weeks of disease clusters per year detected by the scan statistics, and the predictions of year effect on the weeks of the clusters in 2012–2019, as obtained from the non-linear OLS regression models. (a) The number of weekly reported RSV infection cases from paediatric sentinel sites (solid lines) and the weeks of detected disease clusters (dots and grey areas). The dates in the plot are the cluster-start/end-points. (b) The prediction (solid line) from the non-linear OLS regression model for the weeks of the clusters (dots).