A method for estimating from thermometer sales the incidence of diseases that are symptomatically similar to influenza

• We created models to estimate incidence of symptomatically-like-influenza diseases.
• We only use as input to the models thermometer sales data.
• When estimating ED SLI cases at the county level, the mean error was less than 20%.

Early detection and accurate characterization of disease outbreaks are important tasks of public health. Infectious diseases that present symptomatically like influenza (SLI), including influenza itself, constitute an important class of diseases that are monitored by public-health epidemiologists. Monitoring emergency department (ED) visits for presentations of SLI could provide an early indication of the presence, extent, and dynamics of such disease in the population.We investigated the use of daily over-the-counter thermometer-sales data to estimate daily ED SLI counts in Allegheny County (AC), Pennsylvania. We found that a simple linear model fits the data well in predicting daily ED SLI counts from daily counts of thermometer sales in AC. These results raise the possibility that this model could be applied, perhaps with adaptation, in other regions of the country, where commonly thermometer sales data are available, but daily ED SLI counts are not.

We found a linear relationship between thermometer sales (TS) and cases of diseases that are symptomatically like influenza (SLI), which includes influenza itself, as estimated by the Bayesian Case Detection System (which our laboratory developed), in monitored emergency departments (EDs) in Allegheny County (AC), Pennsylvania. Based on this finding, we developed linear models that can estimate SLI cases the present to EDs and the population at the County level with little delay (at most 24 h), across locations in the US.Figure optionsDownload high-quality image (268 K)Download as PowerPoint slide