Longitudinal surveillance of influenza in Japan, 2006-2016

Abstract

We analysed 2006-2016 national influenza surveillance data in Japan with regards to age-, sex-, and predominant virus-related epidemic patterns and the prevalence of serum influenza virus antibodies. We found a significant increase in influenza prevalence in both children (≤ 19 years old) and adults (≥ 20 years old) over time. The influenza prevalence was higher in children (0.33 [95% CI 0.26-0.40]) than in adults (0.09 [95% CI 0.07-0.11]). Additionally, the mean prevalence of antibodies for A(H1N1)pdm09 and A(H3N2) was significantly higher in children than in adults, whereas the mean prevalence of antibodies for B lineages was relatively low in both children and adults. There was a biennial cycle of the epidemic peak in children, which was associated with a relatively higher prevalence of B lineages. The female-to-male ratios of the influenza prevalence were significantly different in children (≤ 19 years old; 1.10 [95% CI:1.08-1.13]), adults (20-59 years old; 0.79 [95% CI 0.75-0.82]), and older adults (≥ 60 years old; 1.01 [95% CI 0.97-1.04]). The significant increase in influenza prevalence throughout the study period suggests a change of immunity to influenza infection. Long-term surveillance is important for developing a strategy to monitor, prevent and control for influenza epidemics.

Figure 1

Influenza prevalence rate by age group and predominant virus. (a) Prevalence rate by age group according to reports from national sentinel clinics for each season. The base population was calculated using data from the national census in 2010. The 2005–2006 season comprised only data between January and June 2006 (due to data availability). (b) Prevalence of cases attributable to each epidemic virus subtype and strain (concerning B lineages, the prevalence of unspecified B lineages was distributed for the ratio of the B/Victoria and B/Yamagata lineages in each season).

Figure 2

Linear regression model for seasonal influenza prevalence rate. A single linear regression model for the seasonal influenza prevalence rate in (a) children (≤ 19 years old) and (b) adults (≥ 20 years old). f(x) represents the prevalence rate, and X represents the number of seasons after the 2004–2005 season. For children, the seasons in which A(H1N1)pdm09 emerged (between the 2009–2010 and 2011–2012 seasons) were excluded from the regression model.

Figure 3

Biennial cycle of influenza virus B lineages and influenza prevalence rate in children (≤ 19 years old). (a) Biennial cycle of increased influenza prevalence rates in children and the prevalence of B lineages (the data exclude epidemic seasons during which the novel swine influenza virus emerged [between the 2009–2010 and 2011–2012 seasons], as indicated by the dotted lines). (b) Average influenza prevalence rate in children and average prevalence of B lineages for the low-prevalence period (Season A: 2005–2006, 2007–2008, 2012–2013, and 2014–2015 seasons) and high-prevalence period (Season B: 2006–2007, 2011–2012, 2013–2014, and 2015–2016 seasons).

Figure 4

Yearly prevalence rate of hemagglutination inhibition (HAI) titers (≥ 1:40) for the influenza virus by age group. Prevalence rate of serum antibodies against influenza virus strains by age group presented for titers ≥ 1:40, as measured in approximately 6000 people in Japan each year using the HAI assay. In (a), the prevalence rate of serum antibodies against A(H1N1) is presented for years between 2006 and 2008, and the prevalence rate of serum antibodies against A(H1N1)pdm09 is presented for years between 2009 and 2016, although the subtypes of A(H1N1) and A(H1N1)pdm09 were genetically different.

Figure 5

Sex ratio of the influenza prevalence rate by age group. Average female-to-male ratio in the influenza prevalence rate in each age group.