Effects of Absolute Humidity, Relative Humidity, Temperature, and Wind Speed on Influenza Activity in Toronto, Ontario, Canada

Abstract

The occurrence of influenza in different climates has been shown to be associated with multiple meteorological factors. The incidence of influenza has been reported to increase during rainy seasons in tropical climates and during the dry, cold months of winter in temperate climates. This study was designed to explore the role of absolute humidity (AH), relative humidity (RH), temperature, and wind speed (WS) on influenza activity in the Toronto, ON, Canada, area. Environmental data obtained from four meteorological stations in the Toronto area over the period from 1 January 2010 to 31 December 2015 were linked to patient influenza data obtained for the same locality and period. Data were analyzed using correlation, negative binomial regressions with linear predictors, and splines to capture the nonlinear relationship between exposure and outcomes. Our study found a negative association of both AH and temperature with influenza A and B virus infections. The effect of RH on influenza A and B viruses was controversial. Temperature fluctuation was associated with increased numbers of influenza B virus infections. Influenza virus was less likely to be detected from community patients than from patients tested as part of an institutional outbreak investigation. This could be more indicative of nosocomial transmission rather than climactic factors. The nonlinear nature of the relationship of influenza A virus with temperature and of influenza B virus with AH, RH, and temperature could explain the complexity and variation between influenza A and B virus infections. Predicting influenza activity is important for the timing of implementation of disease prevention and control measures as well as for resource allocation.IMPORTANCE This study examined the relationship between environmental factors and the occurrence of influenza in general. Since the seasonality of influenza A and B viruses is different in most temperate climates, we also examined each influenza virus separately. This study reports a negative association of both absolute humidity and temperature with influenza A and B viruses and tries to understand the controversial effect of RH on influenza A and B viruses. This study reports a nonlinear relation between influenza A and B viruses with temperature and influenza B virus with absolute and relative humidity. The nonlinear nature of these relations could explain the complexity and difference in seasonality between influenza A and B viruses, with the latter predominating later in the season. Separating community-based specimens from those obtained during outbreaks was also a novel approach in this research. These findings provide a further understanding of influenza virus transmission in temperate climates.

Keywords: absolute humidity; environmental factors; influenza; relative humidity; temperature; wind speed.

FIG 1

Epidemic curve of influenza A and B virus activity by month of exposure, Toronto area, January 2010 to December 2015. Influenza A virus activity peaked during the December to January period, while influenza B virus activity peaked later in the season (March to April).

FIG 2

Absolute humidity, relative humidity, temperature, and wind speed in the Toronto area, January 2010 to December 2015. AH and temperature were the highest in the summer and the lowest in the winter, whereas RH and WS did not vary considerably between months.

FIG 3

Adjusted nonlinear negative regression model examining the relationship of AH, RH, and temperature with overall influenza virus and influenza A and B virus detection. The dark gray shading represents the 95% confidence interval band. Nonlinearity was significant only for absolute and relative humidity with influenza B virus and for temperature with both influenza A and B viruses.