A combination of incidence data and mobility proxies from social media predicts the intra-urban spread of dengue in Yogyakarta, Indonesia

Only a few studies have investigated the potential of using geotagged social media data for predicting the patterns of spatio-temporal spread of vector-borne diseases. We herein demonstrated the role of human mobility in the intra-urban spread of dengue by weighting local incidence data with geo-tagged Twitter data as a proxy for human mobility across 45 neighborhoods in Yogyakarta city, Indonesia. To estimate the dengue virus importation pressure in each study neighborhood monthly, we developed an algorithm to estimate a dynamic mobility-weighted incidence index (MI), which quantifies the level of exposure to virus importation in any given neighborhood. Using a Bayesian spatio-temporal regression model, we estimated the coefficients and predictiveness of the MI index for lags up to 6 months. Specifically, we used a Poisson regression model with an unstructured spatial covariance matrix. We compared the predictability of the MI index to that of the dengue incidence rate over the preceding months in the same neighborhood (autocorrelation) and that of the mobility information alone. We based our estimates on a volume of 1·302·405 geotagged tweets (from 118·114 unique users) and monthly dengue incidence data for the 45 study neighborhoods in Yogyakarta city over the period from August 2016 to June 2018. The MI index, as a standalone variable, had the highest explanatory power for predicting dengue transmission risk in the study neighborhoods, with the greatest predictive ability at a 3-months lead time. The MI index was a better predictor of the dengue risk in a neighborhood than the recent transmission patterns in the same neighborhood, or just the mobility patterns between neighborhoods. Our results suggest that human mobility is an important driver of the spread of dengue within cities when combined with information on local circulation of the dengue virus. The geotagged Twitter data can provide important information on human mobility patterns to improve our understanding of the direction and the risk of spread of diseases, such as dengue. The proposed MI index together with traditional data sources can provide useful information for the development of more accurate and efficient early warning and response systems.Author summary: Recent studies have shown that Twitter can be utilized as a tool for health research, and aggregated large-scale social media data can indicate the risk of infectious disease in real-time with high accuracy and at low cost. However, most of these studies relied primarily on content analysis or text mining, while only a few analyzed the networks of Twitter users. None has incorporated user geolocation data to explain health outcomes at an intra-urban level. Currently dengue early warning systems rely on syndromic surveillance, which lacks completeness and timeliness. Effective syndromic surveillance is rarely achieved due to its technical complexity and a general lack of capacity. Researchers have assessed vector indices, meteorological factors and environmental variables as predictors of dengue incidence, but have failed to capture the complexity of transmission as it relates to human behaviors and movements. Here we develop an algorithm to estimate a dynamic mobility-weighted incidence index (MI), which quantifies the level of exposure to virus importation in a given neighborhood. The proposed index is based on publicly available social media and routine disease surveillance data, and provides a low-cost source of information for assessing the risk of spread of communicable diseases, such as dengue. This study suggests that the MI index is of utility and significance for dengue surveillance and early warnings systems and can enhance timely decision-making within the public health system.