| Summary: | BackgroundAdverse drug reactions (ADRs) can occur any time someone uses a medication. ADRs are systematically tracked and cataloged, with varying degrees of success, in order to better understand their etiology and develop methods of prevention. The US Food and Drug Administration (FDA) has developed the FDA Adverse Event Reporting System (FAERS) for this purpose. FAERS collects information from myriad sources, but the primary reporters have traditionally been medical professionals and pharmacovigilance data from manufacturers. Recent studies suggest that information shared publicly on social media platforms related to medication use could be of benefit in complementing FAERS data in order to have a richer picture of how medications are actually being used and the experiences people are having across large populations.
ObjectiveThe aim of this study is to validate the accuracy and precision of social media methodology and conduct evaluations of Twitter ADR reporting for commonly used pharmaceutical agents.
MethodsADR data from the 10 most prescribed medications according to pharmacy claims data were collected from both FAERS and Twitter. In order to obtain data from FAERS, the SafeRx database, a curated collection of FAERS data, was used to collect data from March 1, 2016, to March 31, 2017. Twitter data were manually scraped during the same time period to extract similar data using an algorithm designed to minimize noise and false signals in social media data.
ResultsA total of 40,539 FAERS ADR reports were obtained via SafeRx and more than 40,000 tweets containing the drug names were obtained from Twitter’s Advanced Search engine. While the FAERS data were specific to ADRs, the Twitter data were more limited. Only hydrocodone/acetaminophen, prednisone, amoxicillin, gabapentin, and metformin had a sufficient volume of ADR content for review and comparison. For metformin, diarrhea was the side effect that resulted in no difference between the two platforms (P=.30). For hydrocodone/acetaminophen, ineffectiveness as an ADR that resulted in no difference (P=.60). For gabapentin, there were no differences in terms of the ADRs ineffectiveness and fatigue (P=.15 and P=.67, respectively). For amoxicillin, hypersensitivity, nausea, and rash shared similar profiles between platforms (P=.35, P=.05, and P=.31, respectively).
ConclusionsFAERS and Twitter shared similarities in types of data reported and a few unique items to each data set as well. The use of Twitter as an ADR pharmacovigilance platform should continue to be studied as a unique and complementary source of information rather than a validation tool of existing ADR databases.
|
|---|
