Assessing the impact of a health intervention via user-generated Internet content

Abstract

Assessing the effect of a health-oriented intervention by traditional epidemiological methods is commonly based only on population segments that use healthcare services. Here we introduce a complementary framework for evaluating the impact of a targeted intervention, such as a vaccination campaign against an infectious disease, through a statistical analysis of user-generated content submitted on web platforms. Using supervised learning, we derive a nonlinear regression model for estimating the prevalence of a health event in a population from Internet data. This model is applied to identify control location groups that correlate historically with the areas, where a specific intervention campaign has taken place. We then determine the impact of the intervention by inferring a projection of the disease rates that could have emerged in the absence of a campaign. Our case study focuses on the influenza vaccination program that was launched in England during the 2013/14 season, and our observations consist of millions of geo-located search queries to the Bing search engine and posts on Twitter. The impact estimates derived from the application of the proposed statistical framework support conventional assessments of the campaign.

Live attenuated influenza vaccine (LAIV): recent effectiveness results from the USA and implications for LAIV programmes elsewhere

“…This was seen in both lower rates of general practitioner influenza-like illness consultations and influenza-confirmed hospitalisations in both 2013/2014 and 2014/2015 in targeted and non-targeted age-groups 23 24. In 2013/2014, there was also evidence of a significantly lower number of primary school absences25 and in influenza-related social media queries26 in primary school pilot areas compared with the non-pilot areas.…”

Multi-Task Learning Improves Disease Models from Web Search

“…We also deploy nonlinear regression models using Gaussian Processes as previous works have shown that the relationship between query frequencies and disease rates is significantly better captured by a nonlinear function [31,33,34,50].…”

“…Existing approaches have routinely used single task models such as regularized regression [17,22,31,43], Gaussian Processes [31,34], and autoregressive frameworks [31,42,47]. Here, we have chosen to apply MTEN [35] and MTGP [11] for the following reasons: (a) EN and GPs have been applied in many text regression [27,44] and disease modeling approaches [31,33,34,55], and (b) the sample sizes we are operating on are limited and no performance gain would have been achieved by deploying neural network structures (such as [16,51,52]). …”

Measuring Global Disease with Wikipedia

“…These traces of disease observations are embedded in search queries [5, 7, 9, 12, 14, 17, 21, 25, 26, 31, 32, 33, 39, 49, 50, 53, 59, 63, 64, 71, 72 73, 77, 78, 81, 85, 87, 90, 97, 103, 104, 109, 119, 126, 127, 131, 132, 141, 142, 144, 146, 157, 158, 162, 163, 166, 168, 169, 170, 173, 177, 179, 180, 182], social media messages [1, 2, 8, 10, 20, 36, 40, 41, 42, 46, 51, 60, 62, 68, 76, 84, 89, 92, 93, 115, 116, 118, 123, 124, 148, 149, 151, 176], web server access logs [57, 79, 101, 105], and combinations thereof [13, 19, 30, 91, 136, 143, 167]. …”

“…The disease surveillance work cited above has been applied to a wide variety of infectious and non-infectious conditions: allergies [87], asthma [136, 176], avian influenza [25], cancer [39], chicken pox [109, 126], chikungunya [109], chlamydia [42, 78, 109], cholera [36, 57], dengue [7, 31, 32, 57, 62, 109], diabetes [42, 60], dysentery [180], Ebola [5, 57], erythromelalgia [63], food poisoning [12], gastroenteritis [45, 50, 71, 126], gonorrhea [77, 78, 109], hand foot and mouth disease [26, 167], heart disease [51, 60], hepatitis [109], HIV/AIDS [57, 76, 177, 180], influenza [1, 2, 8, 9, 10, 13, 19, 20, 21, 30, 33, 40, 41, 43, 46, 48, 53, 57, 59, 68, 72, 73, 79, 81, 84, 85, 89, 90, 91, 92, 93, 97, 101, 103, 104, 105, 109, 115, 116, 118, 123, 124, 126, 131, 132, 141, 14...…”