Association between respiratory syncytial virus activity and pneumococcal disease in infants: a time series analysis of US hospitalization data

Abstract

Background: The importance of bacterial infections following respiratory syncytial virus (RSV) remains unclear. We evaluated whether variations in RSV epidemic timing and magnitude are associated with variations in pneumococcal disease epidemics and whether changes in pneumococcal disease following the introduction of seven-valent pneumococcal conjugate vaccine (PCV7) were associated with changes in the rate of hospitalizations coded as RSV.

Methods and findings: We used data from the State Inpatient Databases (Agency for Healthcare Research and Quality), including >700,000 RSV hospitalizations and >16,000 pneumococcal pneumonia hospitalizations in 36 states (1992/1993-2008/2009). Harmonic regression was used to estimate the timing of the average seasonal peak of RSV, pneumococcal pneumonia, and pneumococcal septicemia. We then estimated the association between the incidence of pneumococcal disease in children and the activity of RSV and influenza (where there is a well-established association) using Poisson regression models that controlled for shared seasonal variations. Finally, we estimated changes in the rate of hospitalizations coded as RSV following the introduction of PCV7. RSV and pneumococcal pneumonia shared a distinctive spatiotemporal pattern (correlation of peak timing: ρ = 0.70, 95% CI: 0.45, 0.84). RSV was associated with a significant increase in the incidence of pneumococcal pneumonia in children aged <1 y (attributable percent [AP]: 20.3%, 95% CI: 17.4%, 25.1%) and among children aged 1-2 y (AP: 10.1%, 95% CI: 7.6%, 13.9%). Influenza was also associated with an increase in pneumococcal pneumonia among children aged 1-2 y (AP: 3.2%, 95% CI: 1.7%, 4.7%). Finally, we observed a significant decline in RSV-coded hospitalizations in children aged <1 y following PCV7 introduction (-18.0%, 95% CI: -22.6%, -13.1%, for 2004/2005-2008/2009 versus 1997/1998-1999/2000). This study used aggregated hospitalization data, and studies with individual-level, laboratory-confirmed data could help to confirm these findings.

Conclusions: These analyses provide evidence for an interaction between RSV and pneumococcal pneumonia. Future work should evaluate whether treatment for secondary bacterial infections could be considered for pneumonia cases even if a child tests positive for RSV. Please see later in the article for the Editors' Summary.

Figure 1. Relationship in the timing of the average seasonal peak of RSV, pneumococcal pneumonia, and pneumococcal septicemia.

Association between the average peak timing (in weeks) of RSV hospitalizations and the average peak timing (in weeks) of (A) pneumococcal pneumonia hospitalizations and (B) pneumococcal septicemia hospitalizations in each state among children aged <2 y, 1992/1993–2008/2009. Smaller values indicate earlier epidemics. The error bars indicate the 95% confidence intervals. The colors differentiate the states; labels for selected states are shown.

Figure 2. Time series of hospitalizations for pneumococcal pneumonia, RSV, and influenza in California.

Incidence rate of pneumococcal pneumonia (red, 3-wk moving average) among children age <2 y in California compared with the incidence of (A) RSV among children aged <2 y (blue) and (B) influenza among all ages (green), 1997/1998–2008/2009. The x-axis shows the year and quarter. Incidence is defined as cases per 100,000 children.

Figure 3. Change in hospitalization rates in each year compared with the average of 1997/1998–1999/2000 among children aged 0–2 and 3–11 mo for RSV, pneumococcal pneumonia, and pneumococcal septicemia.

The y-axis is the IRR and 95% confidence intervals, with values below one representing declines compared with the baseline period.

Figure 4. Variations between states and age groups in the change in rates of hospitalization for RSV or pneumococcal pneumonia after introduction of PCV7.

Decline in the rate of (A) RSV hospitalizations and (B) pneumococcal pneumonia hospitalizations in each state for 2004/2005−2008/2009 compared with the average of 1997/1998−1999/2000 for children aged 0−11, 0−2, 3−11, and 12−23 mo. The IRRs are shown, with values below one indicating a decline compared with the baseline period. The size of the bubbles is proportional to the inverse variance (i.e., more confidence in larger bubbles). Fewer states were available for the analysis of children aged 0−2 and 3−11 mo. The lines demonstrate the difference in IRRs between children aged 0−2 and 3−11 mo. The colors differentiate the states.

Figure 5. Variations between states, age groups, and years in the change in rates of hospitalization for RSV or pneumococcal pneumonia after introduction of PCV7.

Decline in the rate of (A) RSV hospitalizations and (B) pneumococcal pneumonia hospitalizations in each state and each year (July−June) among children aged 0−11 mo compared to the average of 1997/1998−1999/2000 in the same state. The shaded areas indicate the 95% confidence intervals for the IRRs. The red dotted line indicates a rate ratio of one (no change). The colors differentiate the states.