Potential for early warning of viral influenza activity in the community by monitoring clinical diagnoses of influenza in hospital emergency departments

Abstract

Background: Although syndromic surveillance systems are gaining acceptance as useful tools in public health, doubts remain about whether the anticipated early warning benefits exist. Many assessments of this question do not adequately account for the confounding effects of autocorrelation and trend when comparing surveillance time series and few compare the syndromic data stream against a continuous laboratory-based standard. We used time series methods to assess whether monitoring of daily counts of Emergency Department (ED) visits assigned a clinical diagnosis of influenza could offer earlier warning of increased incidence of viral influenza in the population compared with surveillance of daily counts of positive influenza test results from laboratories.

Methods: For the five-year period 2001 to 2005, time series were assembled of ED visits assigned a provisional ED diagnosis of influenza and of laboratory-confirmed influenza cases in New South Wales (NSW), Australia. Poisson regression models were fitted to both time series to minimise the confounding effects of trend and autocorrelation and to control for other calendar influences. To assess the relative timeliness of the two series, cross-correlation analysis was performed on the model residuals. Modelling and cross-correlation analysis were repeated for each individual year.

Results: Using the full five-year time series, short-term changes in the ED time series were estimated to precede changes in the laboratory series by three days. For individual years, the estimate was between three and 18 days. The time advantage estimated for the individual years 2003-2005 was consistently between three and four days.

Conclusion: Monitoring time series of ED visits clinically diagnosed with influenza could potentially provide three days early warning compared with surveillance of laboratory-confirmed influenza. When current laboratory processing and reporting delays are taken into account this time advantage is even greater.

Figure 1

Comparison of daily count of Emergency Department diagnoses of influenza and daily counts of positive laboratory test results for influenza viruses, New South Wales, 2001 to 2005.

Figure 2

Daily counts of Emergency Department ('ED') visits with a provisional diagnosis of influenza and positive laboratory ('Lab') test results for influenza viruses – raw data and fitted models.

Figure 3

Cross-correlation of daily counts of Emergency Department visits with a provisional diagnosis of influenza against daily counts of positive laboratory test results for influenza viruses after removal of trend and seasonality for the five-year period 2001 to 2005. Dashed horizontal lines are 95% confidence limits.

Figure 4

Comparison of unlagged predicted values for the smoothing spline component of the fitted Poisson regression models, representing medium to long-term trends of the Emergency Department ('ED') and laboratory ('Lab') series by year. Y-axis scales are chosen to give a similar range for both ED and laboratory series in each year to allow comparison of trend rather than absolute magnitude of the series over time.

Figure 5

Comparison of 7-day moving averages of the Emergency Department series and 7-day moving averages of the laboratory series during the influenza season from July to September 2003.