691. Real-Time Local Influenza Forecasting Using Smartphone-Connected Thermometer Readings

Abstract

Background. Information regarding infuenza activity can inform clinical and public health activities. However, current surveillance approaches induce a delay in infuenza activity reports (typically 1-2 weeks). Recently, we used data from smart-phone connected thermometers to accurately forecast real-time infuenza activity at a national level. Because thermometer readings can be geo-located, we used state-level thermometer data to determine whether these data can improve state-level surveillance estimates. Methods. We used temperature readings collected by the Kinsa smart-thermometer and mobile device app to develop state-level forecasting models to predict real-time infuenza activity (1-2 weeks in advance of surveillance reports). We used state-reported infuenza-like illness (ILI) to represent state infuenza activity for 48 US states with sufcient surveillance data. Counts of temperature readings, fever episodes and reported symptoms were computed by week. We developed autoregressive time-series models and evaluated model performance in an adaptive out-of-sample manner. We compared baseline time-series models containing lagged state-reported ILI activity to models incorporating exogenous thermometer readings. Results. A total of 10,262,212 temperature readings were recorded from October 30, 2015 to March 29, 2018. In nearly all of the 48 states considered, weekly forecasts of ILI activity improved considerably when thermometer readings were incorporated. On average, state-level forecasting accuracy improved by 23.9% compared with baseline time-series models. In many states, such as PA, New Mexico, MA, Virginia, New York and SC, out-of-sample forecast error was reduced by more than 50% when thermometer data were incorporated. In general, forecasts were most accurate in states with the greatest number of device readings. During the 2017-2018 infuenza season, the average improvement in forecast accuracy was 24.4%, and thermometer readings improved forecasting accuracy in 41, out of 48, states. Conclusion. Data from smart thermometers accurately track real-time infuenza activity at a state level. Local surveillance eforts may be improved by incorporating such information. Such data may also be useful for longer-term local forecasts.