Web-Scale Pharmacovigilance: Listening to Signals from the Crowd

Context: Adverse drug events cause substantial morbidity and mortality and are often discovered after a drug comes to market.1 In the US alone, adverse drug events cause thousands of deaths annually and their associated medical treatment costs billions of dollars.2,3

Objective: Given that a significant use of the Internet is for health searches,4 we hypothesized that Internet users may provide early clues about adverse drug events via their online information-seeking activities.

Design: We conducted a large-scale study of Web search log data gathered during 2010. We pay particular attention to the specific drug pairing of paroxetine and pravastatin, whose interaction to cause hyperglycemia was reported after the time period of the online logs used in the analysis. We also examine sets of drug pairs known to be associated with hyperglycemia and those that have not been associated with hyperglycemia.

Results: Our study shows that signals concerning drug interactions can be mined directly from search logs and confirms the findings of laboratory studies as well as prior known associations.

Conclusions: This is the first study to extract evidence of drug interactions from search log data. Compared to analysis of other sources such as electronic health records (EHR), logs are inexpensive to collect and mine, are not dependent on healthcare utilization, and are not subject to the same latencies. The results demonstrate that logged search activities by populations of computer users captured by Internet services can contribute to drug safety surveillance.