By analyzing search data, researchers can now discover the unknown side effects of prescription drugs more quickly than before. Using data from Google, Yahoo, and Microsoft, researchers discovered trends that accurately correlated with the symptoms of drug interactions. The New York Times reports that this new method can alert researchers to side effects before the FDA's warning system would be able to. Google has been tracking the spread and severity of influenza using search data since 2006 — and this new research applies a similar data-mining technology.
The research team — a collaboration between Microsoft, Standford, and Columbia University — found that people who had searched for the drugs paroxetine and pravastatin over the past year were about 10 percent more likely to search for terms related to the side effect hyperglycemia, and 30 percent of those people would search for symptoms relating to both drugs on the same day. That's enough for the research team to consider it a strong correlation.
The project was conceived by Dr. Russ B. Altman of Stanford University, who wanted to see if drug side effects could be determined more quickly and accurately — a difficult task for the FDA because of the massive number of potential drug pairings. The FDA has financed an effort since 2008 to monitor the risks of drugs already on the market, and it looks like this new method should be able to strengthen that work.