Design Choices for Automated Disease Surveillance in the Social Web

Abstract

The social web has emerged as a dominant information architecture accelerating technology innovation on an unprecedented scale. The utility of these developments to public health use cases like disease surveillance, information dissemination, outbreak prediction and so forth has been widely investigated and variously demonstrated in work spanning several published experimental studies and deployed systems. In this paper we provide an overview of automated disease surveillance efforts based on the social web characterized by their different high level design choices regarding functional aspects like user participation and language parsing approaches. We briefly discuss the technical rationale and practical implications of these different choices in addition to the key limitations associated with these systems within the context of operable disease surveillance. We hope this can offer some technical guidance to multi-disciplinary teams on how best to implement, interpret and evaluate disease surveillance programs based on the social web.

Keywords: Crowd sourced Disease surveillance; Data Mining; Knowledge Engineering; Participatory Epidemiology; The social web.

Figure 1

Analytical Pipeline for Disease Surveillance applications on the social web

Figure 2

Activity cycle for textual Analytical pipeline for disease surveillance applications on the Social Web

Figure 3

Disease forecasting, nowcasting and real-time monitoring vs. disease progression timeline

Figure 4

Proportion of worldwide internet users by access mode. Source: gs.statcounter.com [102]

Figure 5

Mobile OS market share for different platforms. Source: Statista.com [103]

Figure 6

Yearly global sales of smart wearables from 2014 to 2017 by category from 2014 to2017. Source: Statista.com [104].

Figure 7

District level epidemic trajectories for the 2014-2015 Ebola outbreak in Sierra Leone. Weekly incidence records for each district are shown as colored ‘x’, solid line in the corresponding color is the approximate average incidence. Dates shown on the x-axis (dd/mm/yy) are endings of epidemic weeks. Source: Yang et al [105]