Digital Disease Surveillance for Emerging Infectious Diseases: An Early Warning System Using the Internet and Social Media Data for COVID-19 Forecasting in Canada

Abstract

Background: Emerging Infectious Diseases (EID) are a significant threat to population health globally. We aimed to examine the relationship between internet search engine queries and social media data on COVID-19 and determine if they can predict COVID-19 cases in Canada. Methods: We analyzed Google Trends (GT) and Twitter data from 1/1/2020 to 3/31/2020 in Canada and used various signal-processing techniques to remove noise from the data. Data on COVID-19 cases was obtained from the COVID-19 Canada Open Data Working Group. We conducted time-lagged cross-correlation analyses and developed the long short-term memory model for forecasting daily COVID-19 cases. Results: Among symptom keywords, “cough,” “runny nose,” and “anosmia” were strong signals with high cross-correlation coefficients >0.8 ( rCough = 0.825, t - 9; rRunnyNose = 0.816, t - 11; rAnosmia = 0.812, t - 3 ), showing that searching for “cough,” “runny nose,” and “anosmia” on GT correlated with the incidence of COVID-19 and peaked 9, 11, and 3 days earlier than the incidence peak, respectively. For symptoms- and COVID-related Tweet counts, the cross-correlations of Tweet signals and daily cases were rTweetSymptoms = 0.868, t - 11 and tTweetCOVID = 0.840, t - 10, respectively. The LSTM forecasting model achieved the best performance (MSE = 124.78, R2 = 0.88, adjusted R2 = 0.87) using GT signals with cross-correlation coefficients >0.75. Combining GT and Tweet signals did not improve the model performance. Conclusion: Internet search engine queries and social media data can be used as early warning signals for creating a real-time surveillance system for COVID-19 forecasting, but challenges remain in modelling.

Validating part of the social media infodemic listening conceptual framework using structural equation modelling

“… 38 , 39 The SoMeIL conceptual framework can be extended to other areas, such as symptom reports or behavioural patterns, to aid in public health decision-making and resource allocations. 40 By integrating social media platforms such as Twitter into pandemic preparedness, health organizations and government authorities can harness their potential as powerful tools to engage with the public, address health misinformation, and effectively respond to crises, which can ultimately help to mitigate the impact of future pandemics. 38 , 39 Similar to the WHO's EARS platform, 10 the SoMeIL conceptual framework can be implemented as a way to provide real-time monitoring and surveillance.…”

Early Warning and Prediction of Scarlet Fever in China Using the Baidu Search Index and Autoregressive Integrated Moving Average With Explanatory Variable (ARIMAX) Model: Time Series Analysis

“…The models ARIMA(4,0,0)(0,1,1) (12) and ARIMAX(1,0,2)(2,0,0) (12) were constructed according to the auto.arima function and the AIC minimum principle.…”

“…The model was fitted using different values for the parameters ranging from 0 to 2 in a stepwise manner from lower to higher orders [10]. After conducting combination tests, the model ARIMA(4,0,0)(0,1,2) (12) was selected based on the minimum AIC of 1947.03, and the residuals conformed to a white noise sequence (χ 2 =0.145; P=.70).…”

“…The CCF plot considered the mutual relationship within a lag of 12 months, revealing that the CSI at a lag of 0 months exhibited the strongest correlation with scarlet fever (Multimedia Appendix 3). The stationary time series of CSI at a lag of 0 months was used as the input sequence for constructing the ARIMA(4,0,0)(0,1,2) (12) + CSI (Lag=0) and ARIMA(4,0,0)(0,1,1) (12) + CSI (Lag=0) models. All the aforementioned models passed the LSM and the residuals Ljung-Box tests (Table 3).…”

“…An increasing number of individuals are inclined to search for health-related information on the internet before seeking medical services, opening up the potential for early disease surveillance by monitoring fluctuations in the frequency of specific search keywords [11]. Internet-derived data revealed substantial potential in the application of infectious disease surveillance worldwide [12,13]. Google's influenza monitoring data became available 2 weeks before official announcements in the United States [14].…”