Conjunctivitis can be a disruptive diagnosis, necessitating significant time off of work and school—an epidemic can even impact a local economy. While researchers have traditionally used reported cases to identify a regional outbreak, only about 10% of patients with allergic conjunctivitis seek medical care.¹ One day, you may be able to use the web to predict when you might have an uptick in red eye appointments. At least that’s what researchers in San Francisco are studying.²

The researchers used worldwide Google search data for conjunctivitis-related search terms over a span of five years, in addition to control search terms. After identifying candidate outbreaks using the web searches, they compared them with a collection of reported conjunctivitis outbreaks. The web data identified 135 candidate outbreaks for 77 countries. These candidates correlated with 18 of 26 (69% sensitivity) reported nation-wide outbreaks and nine of 20 (45% sensitivity) reported region or district-wide outbreaks. They revealed far fewer nosocomial and reported smaller outbreaks, the study found.²

The study also noted that 83% of candidate outbreaks started earlier than the reported outbreaks, some by as much as 12 weeks. The researchers conclude that “conjunctivitis outbreaks can be detected using temporal scan analysis of Google search data alone, with over 80% detected prior to an outbreak report’s issuance date.”²

They hope data from smaller regions, social media and more search terms can help hone the sensitivity and possibly provide a “complementarily benefit [to] traditional reporting and detection systems to improve epidemic awareness.”²