Can social media data lead to earlier detection of drug‐related adverse events?
نویسندگان
چکیده
PURPOSE To compare the patient characteristics and the inter-temporal reporting patterns of adverse events (AEs) for atorvastatin (Lipitor® ) and sibutramine (Meridia® ) in social media (AskaPatient.com) versus the FDA Adverse Event Reporting System (FAERS). METHODS We identified clinically important AEs associated with atorvastatin (muscle pain) and sibutramine (cardiovascular AEs), compared their patterns in social media postings versus FAERS and used Granger causality tests to assess whether social media postings were useful in forecasting FAERS reports. RESULTS We analyzed 998 and 270 social media postings between 2001 and 2014, 69 003 and 7383 FAERS reports between 1997 and 2014 for atorvastatin and sibutramine, respectively. Social media reporters were younger (atorvastatin: 53.9 vs. 64.0 years, p < 0.001; sibutramine: 36.8 vs. 43.8 years, p < 0.001). Social media reviews contained fewer serious AEs (atorvastatin, pain: 2.5% vs. 38.2%; sibutramine, cardiovascular issues: 7.9% vs. 63.0%; p < 0.001 for both) and concentrated on fewer types of AEs (proportion comprising the top 20 AEs: atorvastatin, 88.7% vs. 55.4%; sibutramine, 86.3% vs. 65.4%) compared with FAERS. While social media sibutramine reviews mentioning cardiac issues helped predict those in FAERS 11 months later (p < 0.001), social media atorvastatin reviews did not help predict FAERS reports. CONCLUSIONS Social media AE reporters were younger and focused on less-serious and fewer types of AEs than FAERS reporters. The potential for social media to provide earlier indications of AEs compared with FAERS is uncertain. Our findings highlight some of the promises and limitations of online social media versus conventional pharmacovigilance sources and the need for careful interpretation of the results. © 2016 The Authors. Pharmacoepidemiology and Drug Safety published by John Wiley & Sons Ltd.
منابع مشابه
Evaluation of Facebook and Twitter Monitoring to Detect Safety Signals for Medical Products: An Analysis of Recent FDA Safety Alerts
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. OBJECTIV...
متن کاملIdentifying Adverse Drug Events from Health Social Media Using Distant Supervision
Adverse drug events (ADEs) have been recognized as a significant healthcare problem worldwide. Prior studies have shown that health social media can be used to generate medical hypotheses and identify adverse drug events. Most studies adopted supervised learning approach for ADE detection in health social media, which requires human annotated data and is not scalable to large datasets. In this ...
متن کاملChoosing appropriate theories for understanding hospital reporting of adverse drug events, a theoretical domains framework approach
Adverse drug events (ADEs) may cause serious injuries including death. Spontaneous reporting of ADEs plays a great role in detection and prevention of them, however, underreporting always exists. Although several interventions have been utilized to solve this problem, they are mainly based on experience and the rationale for choosing them has no theoretical base. The vast variety of behavioral ...
متن کاملChoosing appropriate theories for understanding hospital reporting of adverse drug events, a theoretical domains framework approach
Adverse drug events (ADEs) may cause serious injuries including death. Spontaneous reporting of ADEs plays a great role in detection and prevention of them, however, underreporting always exists. Although several interventions have been utilized to solve this problem, they are mainly based on experience and the rationale for choosing them has no theoretical base. The vast variety of behavioral ...
متن کاملDetecting Adverse Drug Reactions Using a Sentiment Classification Framework
Medical blogs and forums are a source of sentiment oriented content that is used in diverse applications including post-marketing drug surveillance, competitive intelligence and the assessment of health-related opinions and sentiments for detecting adverse drug reactions. However applying existing tools for sentiment analysis to health-related datasets provides inadequate classification accurac...
متن کامل