The open communication of the World Wide Web can be a cesspool of cat videos, memes, and various other unnecessary information. But for Yom-Tov and his colleagues at University College, it’s a data mine that contains all sorts of interesting medical facts. Based on Bing searches involving the flu, Yom-Tov scoured social networks and websites for flu-related information including how many people complained about their symptoms in direct relation to the city they lived in.
“Based on these data sources alone, we were able to show a 25 to 30 percent reduction in the number of flu cases in cities where the vaccine was distributed, compared to other cities where it was not,” he said according to the Microsoft Research blog posted today.
“Crowdsourcing health” is a term that Yom-Tov uses to identify his technique of finding information online. Aggregated internet data can be generated when individuals interact extensively with online content, searches for data as a result of previously searched data, and through social media that indicates the status of an individual’s well-being, thoughts, or other data in response to other stimuli.
Yom-Tov made sure to note that users’ personal information was not in danger, and the information that was available to him was anonymous and solely used for the process of better understanding patterns in people’s health. Even regarding the study of prescription drugs and their side effects, he found rather concerning deep data indicating that many symptoms were being overlooked.
“We were missing side effects people don’t realize are connected to the drugs because they’re more benign or take a longer time to appear,” he said. “This is due to the fact that traditional methods rely on people reporting such associations.”
While he’s hopeful that the medical community will become more involved with computer scientists, Yom-Tov knows that the search data isn’t the cure-all that it can appear to be. The accuracy is nothing compared to traditional medical research, after all.