Digital Immunization Surveillance: Monitoring Flu Vaccination Rates Using Online Social Networks

摘要

Influenza immunizations are critical for preventing deadly and costly outbreaks within the United States, yet flu vaccination coverage has annually remained low. Flu vaccination monitoring is important since early detection of anomalies in flu vaccination rates allows faster communication among public health agencies and local governments thereby facilitating rapid deployment of flu vaccination campaigns. Currently, there is no real-time detection mechanism for monitoring flu vaccination rates. Traditional flu vaccination rate tracking systems suffer information lags due to reliance on reports submitted by medical practices which are updated only once a week. In this paper, we demonstrate the feasibility of a real-time, low-cost and labor-efficient alternative monitoring method to the flu vaccination rate surveillance system used by the United States Department of Health and Human Services (HHS). This alternative is based on social network data and specifically Twitter data. We demonstrate the viability of this approach by measuring the level of correlation between the frequency of "tweets" mentioning flu vaccinations and HHS data on flu vaccination rates.