Evaluation of Facebook and Twitter Monitoring to Detect Safety Signals for Medical Products: An Analysis of Recent FDA Safety Alerts

Abstract

Introduction: The rapid expansion of the Internet and computing power in recent years has opened up the possibility of using social media for pharmacovigilance. While this general concept has been proposed by many, central questions remain as to whether social media can provide earlier warnings for rare and serious events than traditional signal detection from spontaneous report data.

Objective: Our objective was to examine whether specific product-adverse event pairs were reported via social media before being reported to the US FDA Adverse Event Reporting System (FAERS).

Methods: A retrospective analysis of public Facebook and Twitter data was conducted for 10 recent FDA postmarketing safety signals at the drug-event pair level with six negative controls. Social media data corresponding to two years prior to signal detection of each product-event pair were compiled. Automated classifiers were used to identify each 'post with resemblance to an adverse event' (Proto-AE), among English language posts. A custom dictionary was used to translate Internet vernacular into Medical Dictionary for Regulatory Activities (MedDRA^®) Preferred Terms. Drug safety physicians conducted a manual review to determine causality using World Health Organization-Uppsala Monitoring Centre (WHO-UMC) assessment criteria. Cases were also compared with those reported in FAERS.

Findings: A total of 935,246 posts were harvested from Facebook and Twitter, from March 2009 through October 2014. The automated classifier identified 98,252 Proto-AEs. Of these, 13 posts were selected for causality assessment of product-event pairs. Clinical assessment revealed that posts had sufficient information to warrant further investigation for two possible product-event associations: dronedarone-vasculitis and Banana Boat Sunscreen--skin burns. No product-event associations were found among the negative controls. In one of the positive cases, the first report occurred in social media prior to signal detection from FAERS, whereas the other case occurred first in FAERS.

Conclusions: An efficient semi-automated approach to social media monitoring may provide earlier insights into certain adverse events. More work is needed to elaborate additional uses for social media data in pharmacovigilance and to determine how they can be applied by regulatory agencies.

Fig. 1

Data processing results. Public social media data were obtained for Facebook and Twitter, with 935,246 posts identified where each of the 10 products under review were mentioned. An automated classifier was used to remove spam, followed by exclusion of verbatim duplicate posts. Posts with an indicator score of ≥0.65 were considered a ‘post with resemblance to an adverse event’ and manually curated to remove false positives. The resulting 13 posts that mentioned product–event associations from alerts or negative controls were assessed for causality by an independent third party. Six posts contained certain, probable, and possible cases. AE adverse event, Proto-AE post with resemblance to an adverse event

Fig. 2

Volume of mentions of selected products in public Twitter and Facebook social media data. Mentions for the products of interest varied over time, with rapid increases after new product launches, black bars by year, and higher volumes for controlled substances

Fig. 3

Comparison of public Twitter and Facebook data for purposes of medical product safety surveillance. Social media data from public Facebook and Twitter posts were analyzed. A greater volume of posts originated from Twitter than from Facebook