Forecasting Zika Incidence in the 2016 Latin America Outbreak Combining Traditional Disease Surveillance with Search, Social Media, and News Report Data

Abstract

Background: Over 400,000 people across the Americas are thought to have been infected with Zika virus as a consequence of the 2015-2016 Latin American outbreak. Official government-led case count data in Latin America are typically delayed by several weeks, making it difficult to track the disease in a timely manner. Thus, timely disease tracking systems are needed to design and assess interventions to mitigate disease transmission.

Methodology/principal findings: We combined information from Zika-related Google searches, Twitter microblogs, and the HealthMap digital surveillance system with historical Zika suspected case counts to track and predict estimates of suspected weekly Zika cases during the 2015-2016 Latin American outbreak, up to three weeks ahead of the publication of official case data. We evaluated the predictive power of these data and used a dynamic multivariable approach to retrospectively produce predictions of weekly suspected cases for five countries: Colombia, El Salvador, Honduras, Venezuela, and Martinique. Models that combined Google (and Twitter data where available) with autoregressive information showed the best out-of-sample predictive accuracy for 1-week ahead predictions, whereas models that used only Google and Twitter typically performed best for 2- and 3-week ahead predictions.

Significance: Given the significant delay in the release of official government-reported Zika case counts, we show that these Internet-based data streams can be used as timely and complementary ways to assess the dynamics of the outbreak.

Fig 1. Prediction results for (a) Colombia and (b) Honduras.

In each country, the weekly estimations of AR (dotted blue), G+T (green), ARGO+T (orange), and ARGO+TH (red) models are compared to the official case counts (black). Models include Twitter data where available (Colombia). The best model performance (lowest relative RMSE) in each time series by country is shown as a bolded line.

Fig 2. Prediction results for (a) Venezuela and (b) Martinique.

In each country, the weekly estimations of AR (dotted blue), G+T (green), ARGO+T (orange), and ARGO+TH (red) models are compared to the official case counts (black). Models include Twitter data where available (Venezuela). The best model performance (lowest relative RMSE) in each time series by country is shown as a bolded line.

Fig 3. Prediction results for El Salvador.

The weekly estimations of AR (dotted blue), G+T (green), ARGO+T (orange), and ARGO+TH (red) models are compared to the official case counts (black). The best model performance (lowest relative RMSE) in each time series is shown as a bolded line.