Assessment of the Utility of Social Media for Broad-Ranging Statistical Signal Detection in Pharmacovigilance: Results from the WEB-RADR Project
Ola Caster,Juergen Dietrich,Marie-Laure Kürzinger,Magnus Lerch,Simon Maskell,G. Niklas Norén,Stephanie Tcherny-Lessenot,Benoit Vroman,Antoni Wisniewski,John van Stekelenborg +9 more
TLDR
The results clearly suggest that broad-ranging statistical signal detection in Twitter and Facebook, using currently available methods for adverse event recognition, performs poorly and cannot be recommended at the expense of other pharmacovigilance activities.Abstract:
Social media has been proposed as a possibly useful data source for pharmacovigilance signal detection. This study primarily aimed to evaluate the performance of established statistical signal detection algorithms in Twitter/Facebook for a broad range of drugs and adverse events. Performance was assessed using a reference set by Harpaz et al., consisting of 62 US Food and Drug Administration labelling changes, and an internal WEB-RADR reference set consisting of 200 validated safety signals. In total, 75 drugs were studied. Twitter/Facebook posts were retrieved for the period March 2012 to March 2015, and drugs/events were extracted from the posts. We retrieved 4.3 million and 2.0 million posts for the WEB-RADR and Harpaz drugs, respectively. Individual case reports were extracted from VigiBase for the same period. Disproportionality algorithms based on the Information Component or the Proportional Reporting Ratio and crude post/report counting were applied in Twitter/Facebook and VigiBase. Receiver operating characteristic curves were generated, and the relative timing of alerting was analysed. Across all algorithms, the area under the receiver operating characteristic curve for Twitter/Facebook varied between 0.47 and 0.53 for the WEB-RADR reference set and between 0.48 and 0.53 for the Harpaz reference set. For VigiBase, the ranges were 0.64–0.69 and 0.55–0.67, respectively. In Twitter/Facebook, at best, 31 (16%) and four (6%) positive controls were detected prior to their index dates in the WEB-RADR and Harpaz references, respectively. In VigiBase, the corresponding numbers were 66 (33%) and 17 (27%). Our results clearly suggest that broad-ranging statistical signal detection in Twitter and Facebook, using currently available methods for adverse event recognition, performs poorly and cannot be recommended at the expense of other pharmacovigilance activities.read more
Citations
More filters
Journal ArticleDOI
Pharmacovigilance - The next chapter
TL;DR: Spontaneous reporting remains irreplaceable in signal and alert generation in drug safety, despite its inherent limitations, and more systematic and quantitative methods should be sought, such as claims databases for reactions resulting in hospital admissions.
Journal ArticleDOI
The Impact of the COVID-19 "Infodemic" on Drug-Utilization Behaviors: Implications for Pharmacovigilance.
Marco Tuccori,I Convertino,S Ferraro,E Cappello,G Valdiserra,Daniele Focosi,Corrado Blandizzi +6 more
TL;DR: The rationale behind the claims for use of these drugs in COVID-19, the communication about their effects on the disease, the consequences of this communication on people’s behavior, and the responses of some influential regulatory authorities are analyzed in an attempt to minimize the actual or potential risks arising from this behavior are analyzed.
Journal ArticleDOI
Recommendations for the Use of Social Media in Pharmacovigilance: Lessons from IMI WEB-RADR
John van Stekelenborg,Johan Ellenius,Simon Maskell,Tomas Bergvall,Ola Caster,Nabarun Dasgupta,Juergen Dietrich,Sara Gama,David J. Lewis,David J. Lewis,Victoria Newbould,Sabine Brosch,Carrie E. Pierce,Gregory Powell,Alicia Ptaszynska-Neophytou,Antoni F. Z. Wiśniewski,Phil Tregunno,G. Niklas Norén,Munir Pirmohamed,Munir Pirmohamed +19 more
TL;DR: From this original research, several recommendations are presented with supporting rationale and consideration of the limitations, and novel text and data mining methods for social media analysis have been developed and evaluated.
Journal ArticleDOI
Artificial Intelligence Within Pharmacovigilance: A Means to Identify Cognitive Services and the Framework for Their Validation.
Ruta Mockute,Sameen Desai,Sujan Perera,Bruno Assuncao,Karolina Danysz,Niki Tetarenko,Darpan Gaddam,Danielle Abatemarco,Mark Widdowson,Sheryl Beauchamp,Salvatore Cicirello,Edward Mingle +11 more
TL;DR: This study identifies areas across the PV value chain that can be augmented by cognitive service solutions using the methodologies of contextual analysis and cognitive load theory and proposes a foundational framework to identify and validate services to better support the gathering of quality data and to better serve the PV professional.
Journal ArticleDOI
Establishing a Framework for the Use of Social Media in Pharmacovigilance in Europe.
Sabine Brosch,Anne-Marie de Ferran,Victoria Newbould,Diane Farkas,Marina Lengsavath,Phil Tregunno +5 more
TL;DR: The Innovative Medicines Initiative WEB-RADR (Web-Recognising Adverse Drug Reactions) project looked at opportunities and challenges in using social media in pharmacovigilance as a rapidly evolving source of large, real-time data, which could provide new information on the actual use of medicines and potential safety issues.
References
More filters
Journal ArticleDOI
Use of proportional reporting ratios (PRRs) for signal generation from spontaneous adverse drug reaction reports
TL;DR: The process of generating ‘signals’ of possible unrecognized hazards from spontaneous adverse drug reaction reporting data has been likened to looking for a needle in a haystack but statistical approaches to the data have been underutilised.
Journal ArticleDOI
A Bayesian neural network method for adverse drug reaction signal generation
Andrew Bate,Marie Lindquist,I. R. Edwards,Sten Olsson,Roland Orre,Anders Lansner,R.M. De Freitas +6 more
TL;DR: The BCPNN will be an extremely useful adjunct to the expert assessment of very large numbers of spontaneously reported ADRs, and can be used in the detection of significant signals from the data set of the WHO Programme on International Drug Monitoring.
Journal ArticleDOI
Quantitative signal detection using spontaneous ADR reporting.
TL;DR: The role of Bayesian shrinkage in screening spontaneous reports, the importance of changes over time in screening the properties of the measures and some suggestions as to where emerging research is likely to lead are given.
Journal ArticleDOI
Social Media Analytics and Intelligence
TL;DR: This special issue samples the state of the art in social media analytics and intelligence research that has direct relevance to the AI subfield from either an methodological or domain perspective.
Journal ArticleDOI
VigiBase, the WHO Global ICSR Database System: Basic Facts
TL;DR: The main aim of the WHO International Drug Monitoring Programme, started in 1968, is to identify the earliest possible pharmacovigilance signals, and the VigiBase system includes a web-based reporting tool, an automated signal detection process using advanced data mining, and search facilities.