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

Abstract

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.

Social and environmental risk factors for dengue in Delhi city: A retrospective study

“…By contrast, Wealthy colonies are hubs for daily intra-urban movement [19] and the importance of intra-urban mobility in dengue diffusion may generate the paradoxically high levels of dengue despite adequate associated infra-structure and lower mosquito density. Whilst an increasing number of studies emphasise the important role intra-city people movement plays in diffusion of DENV [18][19][20]36,37], to our knowledge no empirical study has explicitly coupled differing mosquito densities with intra-urban movement to explain observed spatial patterns of dengue. A high level of viral importation from high-risk sources of infection could thus enable a relatively high force of infection despite modest mosquito densities.…”

Untapped Potential: A Qualitative Study of a Hospital-Based Dengue Surveillance System

“…This is a less sensitive topic, and the information can be of value for other stakeholders as well, including the community when they are included in the information loop. 44 Social media has, in addition, been shown to be a promising real-time proxy for disease events 45 and to enhance outbreak predictions compared with the use of routine data alone. 46,47 Second, a high risk of inequalities in the care provided was identified owing to the aforementioned regulatory issues, as well asthe introduction of the new insurance system, BPJS.…”

“…This is a less sensitive topic, and the information can be of value for other stakeholders as well, including the community when they are included in the information loop. 44 Social media has, in addition, been shown to be a promising real-time proxy for disease events 45 and to enhance outbreak predictions compared with the use of routine data alone. 46 , 47 …”

Turn to the Internet First? Using Online Medical Behavioral Data to Forecast COVID-19 Epidemic Trend

“…In addition to search engine data, health-relevant information shared on social media, such as Facebook posts and tweets, are used to monitor disease trends. For instance, some studies tried to anticipate the human trajectory and sustained spread of EIDs using geolocated Twitter activity data ( Rocklöv, Tozan, Ramadona et al., 2019 ; Ramadona, Tozan, Lazuardi et al., 2019 ). Using other digital tools such as online educational tools, which allows parents to monitor the children's fever and influenza-like illness, can also forecast the outbreaks of influenza earlier than the traditional surveillance system ( Hswen, Brownstein, Liu et al., 2017 ).…”