Using Big Data to Supplement Population Health Surveillance Systems

• Activity Number: 375
• Type: Invited
• Date/Time: Tuesday, August 5, 2014 : 2:00 PM to 3:50 PM
• Sponsor: WNAR
• Author(s): Carol Gotway Crawford+ and Steven Gittleman*
• Companies: CDC and Mktg Inc.
• Keywords: Facebook ; prediction ; behavioral risk factors

Abstract

Facebook Likes may be a source of digital data that can complement traditional public health surveillance systems and provide data at a local level. We used regression analyses to examine the predictive qualities of Facebook Likes with regard to mortality, diseases (diabetes and obesity), and lifestyle behaviors associated with chronic disease in 214 counties across the United States and 61 of the 67 counties in Florida. Predictors were county-specific proportions of users with activity-, interest-, retail- and shopping-related Likes selected for their potential relationship to health. Based on these analyses, we found there was a persistent predictive benefit of Facebook Likes when added to socioeconomic status (SES) compared to the SES alone. With the inclusion of Facebook Likes, effects range from an 11% improvement in variance explained when predicting obesity to a 353% improvement when predicting average duration since last routine checkup. Online data sources such as these may provide more reliable, timely, and cost effective county-level data than those obtainable from traditional public health surveillance systems as well as serve as an adjunct to those systems.