Inferences about spatiotemporal variation in dengue virus transmission are sensitive to assumptions about human mobility: a case study using geolocated tweets from Lahore, Pakistan

Abstract

Billions of users of mobile phones, social media platforms, and other technologies generate an increasingly large volume of data that has the potential to be leveraged towards solving public health challenges. These and other big data resources tend to be most successful in epidemiological applications when utilized within an appropriate conceptual framework. Here, we demonstrate the importance of assumptions about host mobility in a framework for dynamic modeling of infectious disease spread among districts within a large urban area. Our analysis focused on spatial and temporal variation in the transmission of dengue virus (DENV) during a series of large seasonal epidemics in Lahore, Pakistan during 2011-2014. Similar to many directly transmitted diseases, DENV transmission occurs primarily where people spend time during daytime hours, given that DENV is transmitted by a day-biting mosquito. We inferred spatiotemporal variation in DENV transmission under five different assumptions about mobility patterns among ten districts of Lahore: no movement among districts, movement following patterns of geo-located tweets, movement proportional to district population size, and movement following the commonly used gravity and radiation models. Overall, we found that inferences about spatiotemporal variation in DENV transmission were highly sensitive to this range of assumptions about intra-urban human mobility patterns, although the three assumptions that allowed for a modest degree of intra-urban mobility all performed similarly in key respects. Differing inferences about transmission patterns based on our analysis are significant from an epidemiological perspective, as they have different implications for where control efforts should be targeted and whether conditions for transmission became more or less favorable over time.

Electronic supplementary material: The online version of this article (10.1140/epjds/s13688-018-0144-x) contains supplementary material.

Keywords: Big data; Disease dynamics; Geo-located tweets; Gravity model; Human mobility; Radiation model; Spatiotemporal analysis; Twitter data.

Figure 1

Relative proportion of tweets made in the town indicated in the panel label by residents of every other town. Different colors represent different home location of residents

Figure 2

Time series stratified by towns in which cases were assumed to be acquired (colors) under five different assumptions about mobility among towns (rows)

Figure 3

Time series stratified by towns in which cases were assumed to be acquired (rows) under five different assumptions about mobility among towns (line type)

Figure 4

Relationships between predicted (x-axis) and observed (y-axis) log incidence based on models fitted to five different mobility-based incidence time series (panels). The coefficient of determination, $R^2$, associated with each best-fit model is indicated in each panel. Values of observed incidence vary across panels due to the effect of different assumptions about mobility used to transform the residence-based time series to mobility-based time series. For example, log incidence under the assumption of no movement never falls below 0, because there were no fractional cases observed in the raw data. Fractional incidence did occur in the other two time series due to each person’s incidence of disease being partitioned across the towns proportional to assumed mobility patterns. Under the ideal free assumption, the diagonal sets of points are a result of incidence on a given day varying across towns only in proportion to their different population sizes

Figure 5

Predicted values of residence-based incidence in each town (rows) using the best-fit model under each of five different assumptions about mobility (colors). Observed values of residence-based incidence in each town are shown with black dots, and bands show 95% confidence intervals on model predictions

Figure 6

Temporal variation in ${\beta }_i(t)$ for different towns (rows) under three different mobility assumptions (columns): no movement (left), Twitter (center), and ideal free (right). The black line shows the mean of the best-fit model and blue bands show standard error around the mean. The dashed red line indicates where ${\beta }_i(t)=1$

Figure 7

Temporal variation in ${\beta }_i(t)$ for different towns (rows) under three different mobility assumptions (columns): gravity model (left), Twitter (center), and radiation model (right). The black line shows the mean of the best-fit model and blue bands show standard error around the mean. The dashed red line indicates where ${\beta }_i(t)=1$

Figure 8

Geometric means of ${\beta }_i(t)$ stratified by year (x-axis), town (rows), and mobility assumption (columns)

Figure 9

Measures of transmission and incidence across towns (colors) under different mobility assumptions (columns) aggregated over the entire 2011–2014 time period. The upper left y-axis was cut off to permit viewing of the majority of values; the geometric mean of ${\beta }_i(t)$ for Shalimar town is 17.49