Scientists from Microsoft, Stanford, and Columbia University used Web search data gathered from Google, Microsoft, and Yahoo searches and discovered hidden side effects of certain prescription drugs.
Imagine you visit your doctor because you’re feeling depressed for no good reason. Your doctor prescribes an anti-depressant and a few days later you notice, your vision seems blurry.
You may go back to your doctor and report it, but in a connected world, lots of us Google first. If you search for the prescribed drug, and it tells you blurry vision is a known side effect, you might just live with it or you may return to the doctor to try a different treatment.
What if your Web search doesn’t reveal that the drug you’re taking is known to cause blurry vision? You may be more likely to get it checked out, but aside from that, you’re not the only person doing the same search.
There may be hundreds or thousands of people who got the same prescription and are also experiencing blurry vision as a side effect. People searching for the same drug along with the same side effect exposes a signal. Studies of those signals have been especially helpful in discovering side effects caused by the interaction of two different medications combined in unanticipated ways.
Reporting for The New York Times, John Markoff explained the research this way:
“Using automated software tools to examine queries by 6 million Internet users taken from Web search logs in 2010, the researchers looked for searches relating to an antidepressant, paroxetine, and a cholestorol lowering drug, pravastatin. They were able to find evidence that the combination of the two drugs caused high blood sugar.”
Chairman of the Stanford bioengineering department Russ B. Altman published results of the study in the Journal of the American Medical Informatics Association on Wednesday:
“There is a potential public health benefit in listening to such signals, and integrating them with other sources of information.”