Adverse drug reactions come at a considerable cost on society. Social media is a potentially invaluable reservoir of information for pharmacovigilance, yet its true value remains to be fully understood. In order to realise the benefits social media holds, a number of technical, regulatory and ethical challenges remain to be addressed. We outline these key challenges identifying relevant current research and present possible solutions. This article is protected by copyright. All rights reserved. This article is protected by copyright. All rights reserved.
Introduction: Adverse drug reactions (ADRs) are a signiﬁcant cause of mor-bidity and mortality worldwide. Approximately 6.5% of UKhospital admissions are caused by ADRs at considerable coston health, ﬁnance and manpower . Even though the num-ber of Yellow Card reports is increasing year-on-year withover 26 000 reports in 2012 , the vast majority of ADRs stillremain unreported . It has thus been suggested that socialmedia may be a method by which pharmacovigilance couldbe strengthened given that approximately 72% of internetusers search for health information online .Social media have signiﬁcantly expanded recently withTwitter and Facebook now registering over 300 million and1.4 billion active users, respectively [4–7]. Social mediahave already been utilized in different domains illustratingtheir potential application to pharmacovigilance. Forinstance, Twitter data were analyzed to determineepicentres of earthquakes in Japan  and following thedevastating 2010 earthquake in Haiti, Twitter was shownto map trends of the cholera outbreak weeks before tradi-tional reporting methods . The quantity and near-instantaneous nature of social media provides potentialopportunities for real-time monitoring of ADRs, greatercapture of ADR reports and expedited signal detection ifutilised correctly.The role of social media in pharmacovigilance has beengaining in interest with various social media sources [10–31]used for detecting ADRs, including general purpose socialnetworking sites such as Twitter , and health and supportnetworks including PatientsLikeMe , DailyStrength and MedHelp  (Figure 1). Previous reviews in this areahave focused on the approaches that have been taken toanalyze social media , and the analysis of variouspharmacovigilance text sources including biomedical litera-ture, clinical narratives and social media . To complementthese existing reviews, we take a broad view to incorporatethe technical, industrial, legislative and ethical perspectivesof using social media for pharmacovigilance in order to high-light current challenges and potential opportunities. Wordsin italics are described in the ‘Glossary of terms’section.
Post-marketing Drug Safety Surveillance Post-market drug safety surveillance is required to identify potential adverse reactions in the larger population Spontaneous reporting systems (SRS) Submitted to national agencies E.g. US FDA’s MedWatch program UK MHRA’s Yellow Card Scheme Reflects less than 10% of the adverse effect occurrences (Inman & Pearce, 1993; Yang et al., 2012)
Social Media for Drug Safety Surveillance A relatively new resource that can augment the current surveillance systems is the user posts in: social health networks microblogs (e.g. Twitter) disease specific communities, and etc. Millions of health-related messages can reveal important public health issues
Extraction Challenges Consumers do not always use terms in medical lexicons. They use creative phrases, descriptive symptom explanations, and idiomatic expressions. “messed up my sleeping patterns” was used to report “sleep disturbance”. Semantic type classification E.g.: ADR vs. Indications This drug prevents anxiety symptoms [Indication] User postings are informal, and deviate from grammatical rules: Contains misspellings, abbreviations, and phrase construction irregularities Extraction is more difficult compared to other corpora
Extraction of post-marketing drug safety information (Related Work ) Various resources: electronic health records, biomedical literature, SRS Online user posts (initially proposed by Leaman et al. in DIEGO lab) health social networking sites: DailyStrength, PatientsLikeMe, and MedHelp; Twitter; users’ web search logs. Most prior studies focused on exploring existing or customized ADR lexicons to find ADR mentions in user posts. Limited progress on automated medical concept extraction approaches, and advanced machine learning based NLP techniques. Less effort in addressing the introduced challenges.