Google_Flu_Trends_MapUsing data drawn from queries entered into Google, Microsoft and Yahoo search engines, scientists at Microsoft, Stanford and Columbia University have for the first time been able to detect evidence of unreported prescription drug side effects before they were found by the Food and Drug Administration’s warning system.

The research team 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.

The study, was reported in the Journal of the American Medical Informatics Association and based on data-mining techniques similar to those employed by services like Google Flu Trends.

Note: The F.D.A. asks physicians to report side effects through a system known as the Adverse Event Reporting System. But its scope is limited by the fact that data is generated only when a physician notices something and reports it.