Utilizing social media data for pharmacovigilance: A review

Abstract

Objective Automatic monitoring of Adverse Drug Reactions (ADRs), defined as adverse patient outcomes caused by medications, is a challenging research problem that is currently receiving significant attention from the medical informatics community. In recent years, user-posted data on social media, primarily due to its sheer volume, has become a useful resource for ADR monitoring. Research using social media data has progressed using various data sources and techniques, making it difficult to compare distinct systems and their performances. In this paper, we perform a methodical review to characterize the different approaches to ADR detection/extraction from social media, and their applicability to pharmacovigilance. In addition, we present a potential systematic pathway to ADR monitoring from social media. Methods We identified studies, describing approaches for ADR detection from social media from the Medline, Embase, Scopus and Web of Science databases, and the Google Scholar search engine. Studies that met our inclusion criteria were those that attempted to utilize ADR information posted by users on any publicly available social media platform. We categorized the studies into various dimensions such as primary ADR detection approach, size of data, source(s), availability, evaluation criteria, and so on. Results Twenty-two studies met our inclusion criteria, with fifteen (68.2%) published within the last two years. The survey revealed a clear trend towards the usage of annotated data with eleven of the fifteen (73.3%) studies published in the last two years relying on expert annotations. However, publicly available annotated data is still scarce, and we found only six (27.3%) studies that made the annotations used publicly available, making system performance comparisons difficult. In terms of algorithms, supervised classification techniques to detect posts containing ADR mentions, and lexicon-based approaches for extraction of ADR mentions from texts have been the most popular. Conclusion Our review suggests that interest in the utilization of the vast amounts of available social media data for ADR monitoring is increasing with time. In terms of sources, both health-related and general social media data have been used for ADR detection— while health-related sources tend to contain higher proportions of relevant data, the volume of data from general social media websites is significantly higher. There is still very limited publicly available annotated data available, and, as indicated by the promising results obtained by recent supervised learning approaches, there is a strong need to make such data available to the research community.

21st Century Patient Registries, Ebook Addendum to Registries for Evaluating Patient Outcomes: A User's Guide, 3rd Edition

“…2 PCORnet is the National Patient-Centered Clinical Research Network that integrates health data for studies and catalyzes research partnerships among two types of networks: (1) Clinical Data Research Networks (CDRNs), which are mainly based in healthcare systems such as hospitals and health centers, and (2) PPRNs, which are run by groups of patients and their partners who are focused on one or more specific conditions or communities, and who are interested in sharing health information and participating in research. 39 The PCORnet networks have developed multi-dimensional methods and approaches for engaging patients to provide input into their networks and studies. For example, networks have a variety of structures for engaging patients, caregivers, and patient advocates in the governance of their networks to help make critical decisions with respect to planning and operationalizing the network and their respective research priorities.…”

“…In addition, evidence for COAs must include data to demonstrate that the clinical outcome is linked to survival or how patients feel or function in daily life. 39 While these guidelines are not directly applicable to registry research, both patient-reported and clinical outcome measures used in registries should likewise show evidence of importance to the patient population through patient review and testing of the measure for relevance of content and cognitive and linguistic understanding.…”

“…[36][37][38][39] Much of the data captured from digital technologies are often available in real-time, allowing researchers and healthcare providers to quickly grasp epidemiological insights such as disease prevalence, as well as impact of medical interventions. 40 …”

“…For example, social listening, the manual or automated collection of patient-generated data that is unsolicited and available publicly or with permission, enables a stakeholder to capture a large amount of patient-generated data. 39 Digital health apps and social listening sites have been used to determine where to host a clinical trial or launch a product. 41 In spite of the early uptake of social listening by some, many are unaware of social media's ability to reduce the burden of data collection on all parties, and how to attenuate and mitigate their associated risks.…”

Does "Hotboxing?" Get You High and Can You Test Positive? - A Brief Review of Second-Hand Cannabis Exposure, Intoxication and Urine Drug Screens

“…Use of such information is an emerging trend and has support and evidence of being able to bring real time information from actual users to clinicians, bridging the current gap in our scientific knowledge [40][41][42]. Here we supplemented existing literature with real-time information from social media to provide the most up-to-date coverage of the topic and extend beyond our existing clinical knowledge.…”