Use of Social Media for Pharmacovigilance Activities: Key Findings and Recommendations from the Vigi4Med Project

The large-scale use of social media by the population has gained the attention of stakeholders and researchers in various fields. In the domain of pharmacovigilance, this new resource was initially considered as an opportunity to overcome underreporting and monitor the safety of drugs in real time in close connection with patients. Research is still required to overcome technical challenges related to data extraction, annotation, and filtering, and there is not yet a clear consensus concerning the systematic exploration and use of social media in pharmacovigilance. Although the literature has mainly considered signal detection, the potential value of social media to support other pharmacovigilance activities should also be explored. The objective of this paper is to present the main findings and subsequent recommendations from the French research project Vigi4Med, which evaluated the use of social media, mainly web forums, for pharmacovigilance activities. This project included an analysis of the existing literature, which contributed to the recommendations presented herein. The recommendations are categorized into three categories: ethical (related to privacy, confidentiality, and follow-up), qualitative (related to the quality of the information), and quantitative (related to statistical analysis). We argue that the progress in information technology and the societal need to consider patients’ experiences should motivate future research on social media surveillance for the reinforcement of classical pharmacovigilance.

[1]  M. Lindquist,et al.  Quality criteria for early signals of possible adverse drug reactions , 1990, The Lancet.

[2]  J. Hartigan,et al.  A Bayesian Analysis for Change Point Problems , 1993 .

[3]  Andrew Herxheimer,et al.  Paroxetine, Panorama and user reporting of ADRs: Consumer intelligence matters in clinical practice and post-marketing drug surveillance , 2002 .

[4]  Carlo Curino,et al.  Mining officially unrecognized side effects of drugs by combining web search and machine learning , 2005, CIKM '05.

[5]  B. Golomb,et al.  Physician Response to Patient Reports of Adverse Drug Effects , 2007, Drug safety.

[6]  S. Schröder,et al.  Drug related problems with Antiparkinsonian agents: consumer Internet reports versus published data , 2007, Pharmacoepidemiology and drug safety.

[7]  J. Moncrieff,et al.  ACTA PSYCHIATRICA , 2006 .

[8]  E. Larson,et al.  Dissemination of health information through social networks: twitter and antibiotics. , 2010, American journal of infection control.

[9]  Jian Yang,et al.  Towards Internet-Age Pharmacovigilance: Extracting Adverse Drug Reactions from User Posts in Health-Related Social Networks , 2010, BioNLP@ACL.

[10]  [One step more toward pharmacovigilance 2.0. Integration of web data community for a pharmacovigilance more alert]. , 2011, Presse medicale.

[11]  Un pas de plus vers une pharmacovigilance 2.0 , 2011 .

[12]  Richard B. Berlin,et al.  Predicting adverse drug events from personal health messages. , 2011, AMIA ... Annual Symposium proceedings. AMIA Symposium.

[13]  Robin E. Ferner,et al.  Internet Accounts of Serious Adverse Drug Reactions , 2012, Drug Safety.

[14]  Guideline on good pharmacovigilance practices ( GVP ) Module , 2013 .

[15]  Mary S Vaughan Sarrazin,et al.  Patient Perspectives of Dabigatran: Analysis of Online Discussion Forums , 2013, The Patient - Patient-Centered Outcomes Research.

[16]  S J Stanhope,et al.  Exploiting Online Discussions to Discover Unrecognized Drug Side Effects , 2013, Methods of Information in Medicine.

[17]  Amit P. Sheth,et al.  PREDOSE: A semantic web platform for drug abuse epidemiology using social media , 2013, J. Biomed. Informatics.

[18]  L Pochard,et al.  Analysis of patients' narratives posted on social media websites on benfluorex's (Mediator®) withdrawal in France , 2014, Journal of clinical pharmacy and therapeutics.

[19]  Daniel Neagu,et al.  Social media analysis for product safety using text mining and sentiment analysis , 2014, 2014 14th UK Workshop on Computational Intelligence (UKCI).

[20]  M. Ibara,et al.  Regulatory Definitions and Good Pharmacovigilance Practices in Social Media , 2015, Therapeutic innovation & regulatory science.

[21]  A. Burgun,et al.  Adverse Drug Reaction Identification and Extraction in Social Media: A Scoping Review , 2015, Journal of medical Internet research.

[22]  Ronen Feldman,et al.  Utilizing Text Mining on Online Medical Forums to Predict Label Change due to Adverse Drug Reactions , 2015, KDD.

[23]  S. Golder,et al.  Systematic review on the prevalence, frequency and comparative value of adverse events data in social media. , 2015, British journal of clinical pharmacology.

[24]  Danushka Bollegala,et al.  Social media and pharmacovigilance: A review of the opportunities and challenges. , 2015, British journal of clinical pharmacology.

[25]  Kenneth H. Lai,et al.  Clinicians’ Reports in Electronic Health Records Versus Patients’ Concerns in Social Media: A Pilot Study of Adverse Drug Reactions of Aspirin and Atorvastatin , 2016, Drug Safety.

[26]  Christopher C. Yang,et al.  Using Health-Consumer-Contributed Data to Detect Adverse Drug Reactions by Association Mining with Temporal Analysis , 2015, ACM Trans. Intell. Syst. Technol..

[27]  Dragan Ilic,et al.  The Acceptability Among Health Researchers and Clinicians of Social Media to Translate Research Evidence to Clinical Practice: Mixed-Methods Survey and Interview Study , 2015, Journal of medical Internet research.

[28]  Rajesh Ghosh,et al.  Aims and approaches of Web-RADR: a consortium ensuring reliable ADR reporting via mobile devices and new insights from social media , 2015, Expert opinion on drug safety.

[29]  Wei Luo,et al.  Guidelines for Developing and Reporting Machine Learning Predictive Models in Biomedical Research: A Multidisciplinary View , 2016, Journal of medical Internet research.

[30]  Rachel E. Ginn,et al.  Social Media Mining for Toxicovigilance: Automatic Monitoring of Prescription Medication Abuse from Twitter , 2016, Drug Safety.

[31]  Marc Van Audenrode,et al.  Can social media data lead to earlier detection of drug‐related adverse events? , 2016, Pharmacoepidemiology and drug safety.

[32]  Pierre Zweigenbaum,et al.  Identification of Drug-Related Medical Conditions in Social Media , 2016, LREC.

[33]  Vagelis Hristidis,et al.  Demographic-Based Content Analysis of Web-Based Health-Related Social Media , 2016, Journal of medical Internet research.

[34]  Olivier Blin,et al.  Investigating patient narratives posted on Internet and their informativeness level for pharmacovigilance purpose: The example of comments about statins. , 2017, Therapie.

[35]  Christopher C. Yang,et al.  Automated Off-label Drug Use Detection from User Generated Content , 2017, BCB.

[36]  Eric R. LaRose,et al.  Adverse Drug Event Discovery Using Biomedical Literature: A Big Data Neural Network Adventure , 2017, JMIR medical informatics.

[37]  Michel Beigbeder,et al.  Vigi4Med Scraper: A Framework for Web Forum Structured Data Extraction and Semantic Representation , 2017, PloS one.

[38]  Jeffery L Painter,et al.  Using Social Listening Data to Monitor Misuse and Nonmedical Use of Bupropion: A Content Analysis , 2017, JMIR public health and surveillance.

[39]  Melissa M. Truffa,et al.  Using Social Media Data in Routine Pharmacovigilance: A Pilot Study to Identify Safety Signals and Patient Perspectives , 2017, Pharmaceutical Medicine.

[40]  Anne Cocos,et al.  Deep learning for pharmacovigilance: recurrent neural network architectures for labeling adverse drug reactions in Twitter posts , 2017, J. Am. Medical Informatics Assoc..

[41]  Julien Souvignet,et al.  The Adverse Drug Reactions from Patient Reports in Social Media Project: Five Major Challenges to Overcome to Operationalize Analysis and Efficiently Support Pharmacovigilance Process , 2017, JMIR research protocols.

[42]  Gregory E. Powell,et al.  Enabling social listening for cardiac safety monitoring: Proceedings from a drug information association–cardiac safety research consortium cosponsored think tank , 2017, American heart journal.

[43]  Marina Lengsavath,et al.  Social Media Monitoring and Adverse Drug Reaction Reporting in Pharmacovigilance , 2017, Therapeutic innovation & regulatory science.

[44]  Jingcheng Du,et al.  Leveraging machine learning-based approaches to assess human papillomavirus vaccination sentiment trends with Twitter data , 2017, BMC Medical Informatics and Decision Making.

[45]  G. Niklas Norén,et al.  Assessment of the Utility of Social Media for Broad-Ranging Statistical Signal Detection in Pharmacovigilance: Results from the WEB-RADR Project , 2018, Drug Safety.

[46]  Davy Weissenbacher,et al.  Pharmacoepidemiologic Evaluation of Birth Defects from Health-Related Postings in Social Media During Pregnancy , 2018, Drug Safety.

[47]  Graeme Hirst,et al.  Utility of social media and crowd-intelligence data for pharmacovigilance: a scoping review , 2018, BMC Medical Informatics and Decision Making.

[48]  M. Keller,et al.  Reproductive Health and Medication Concerns for Patients With Inflammatory Bowel Disease: Thematic and Quantitative Analysis Using Social Listening , 2018, Journal of medical Internet research.

[49]  So Hyun Park,et al.  Identification of Primary Medication Concerns Regarding Thyroid Hormone Replacement Therapy From Online Patient Medication Reviews: Text Mining of Social Network Data , 2018, Journal of medical Internet research.

[50]  F. Bellet,et al.  Comment on “Assessment of the Utility of Social Media for Broad-Ranging Statistical Signal Detection in Pharmacovigilance: Results from the WEB-RADR Project” , 2018, Drug Safety.

[51]  P. Myint,et al.  The pale evidence for treatment of iron-deficiency anaemia in older people , 2018, Therapeutic advances in drug safety.

[52]  Christopher C. Yang,et al.  Exploiting OHC Data with Tensor Decomposition for Off-Label Drug Use Detection , 2018, 2018 IEEE International Conference on Healthcare Informatics (ICHI).

[53]  R. Azam Accessing social media information for pharmacovigilance: what are the ethical implications? , 2018, Therapeutic advances in drug safety.

[54]  Berry de Bruijn,et al.  Data and systems for medication-related text classification and concept normalization from Twitter: insights from the Social Media Mining for Health (SMM4H)-2017 shared task , 2018, J. Am. Medical Informatics Assoc..

[55]  Goran Nenadic,et al.  Frequent discussion of insomnia and weight gain with glucocorticoid therapy: an analysis of Twitter posts , 2017, npj Digital Medicine.

[56]  Xavier Rafael-Palou,et al.  Comparative analysis of predictive methods for early assessment of compliance with continuous positive airway pressure therapy , 2018, BMC Medical Informatics and Decision Making.

[57]  Natalia Grabar,et al.  Detection and Analysis of Drug Misuses. A Study Based on Social Media Messages , 2018, Front. Pharmacol..

[58]  C. Blandizzi,et al.  The usefulness of listening social media for pharmacovigilance purposes: a systematic review , 2018, Expert opinion on drug safety.

[59]  H. Riper,et al.  Behind the Scenes of Online Therapeutic Feedback in Blended Therapy for Depression: Mixed-Methods Observational Study , 2018, Journal of medical Internet research.

[60]  J. Slattery,et al.  An algorithm to detect unexpected increases in frequency of reports of adverse events in EudraVigilance , 2017, Pharmacoepidemiology and drug safety.

[61]  Anita Burgun,et al.  Detection of Cases of Noncompliance to Drug Treatment in Patient Forum Posts: Topic Model Approach , 2018, Journal of medical Internet research.

[62]  Sue Rees,et al.  Using social media in safety signal management: is it reliable? , 2018, Therapeutic advances in drug safety.

[63]  Fabio Vivarelli,et al.  Geraniol Pharmacokinetics, Bioavailability and Its Multiple Effects on the Liver Antioxidant and Xenobiotic-Metabolizing Enzymes , 2018, Front. Pharmacol..

[64]  N. Shah,et al.  Detecting Chemotherapeutic Skin Adverse Reactions in Social Health Networks Using Deep Learning , 2018, JAMA oncology.

[65]  S. Golder,et al.  Methods to Compare Adverse Events in Twitter to FAERS, Drug Information Databases, and Systematic Reviews: Proof of Concept with Adalimumab , 2018, Drug Safety.

[66]  Cyril Grouin,et al.  Descriptions of Adverse Drug Reactions Are Less Informative in Forums Than in the French Pharmacovigilance Database but Provide More Unexpected Reactions , 2018, Front. Pharmacol..

[67]  M. Jaulent,et al.  Evaluating Twitter as a complementary data source for pharmacovigilance , 2018, Expert opinion on drug safety.

[68]  Cédric Bousquet,et al.  Signal Detection for Baclofen in Web Forums: A Preliminary Study , 2018, MIE.

[69]  Cartic Ramakrishnan,et al.  Sorting Through the Safety Data Haystack: Using Machine Learning to Identify Individual Case Safety Reports in Social-Digital Media , 2018, Drug Safety.

[70]  H. Dolk,et al.  An assessment of pregnant women's knowledge and use of the Internet for medication safety information and purchase , 2018, Journal of advanced nursing.

[71]  Andrew Bate,et al.  The hope, hype and reality of Big Data for pharmacovigilance , 2018, Therapeutic advances in drug safety.

[72]  Pierre Zweigenbaum,et al.  Initial Experiments for Pharmacovigilance Analysis in Social Media Using Summaries of Product Characteristics , 2019, MedInfo.

[73]  Marina Lengsavath,et al.  Establishing a Framework for the Use of Social Media in Pharmacovigilance in Europe , 2019, Drug Safety.

[74]  N. Chavannes,et al.  Electronic Health Self-Management Interventions for Patients With Chronic Kidney Disease: Systematic Review of Quantitative and Qualitative Evidence , 2019, Journal of medical Internet research.

[75]  M. Benkebil,et al.  Benefits of combining change‐point analysis with disproportionality analysis in pharmacovigilance signal detection , 2018, Pharmacoepidemiology and drug safety.

[76]  S. Golder,et al.  Understanding Public Attitudes Toward Researchers Using Social Media for Detecting and Monitoring Adverse Events Data: Multi Methods Study , 2019, Journal of medical Internet research.

[77]  S. Tcherny-Lessenot,et al.  Comparison of text processing methods in social media–based signal detection , 2019, Pharmacoepidemiology and drug safety.

[78]  V. Welch,et al.  Using Social Media to Uncover Treatment Experiences and Decisions in Patients With Acute Myeloid Leukemia or Myelodysplastic Syndrome Who Are Ineligible for Intensive Chemotherapy: Patient-Centric Qualitative Data Analysis , 2019, Journal of medical Internet research.

[79]  Pierre Zweigenbaum,et al.  French Levothyrox® Crisis: Retrospective Analysis of Social Media , 2019 .

[80]  N. Shah,et al.  Early Detection of Adverse Drug Reactions in Social Health Networks: A Natural Language Processing Pipeline for Signal Detection , 2019, JMIR public health and surveillance.

[81]  Evgeny A. Antipov,et al.  The effects of adverse drug reactions on patients' satisfaction: Evidence from publicly available data on Tamiflu (oseltamivir) , 2019, Int. J. Medical Informatics.

[82]  Natalia Grabar,et al.  Detecting Drug Non-Compliance in Internet Fora Using Information Retrieval and Machine Learning Approaches , 2019, MedInfo.

[83]  H. Zeilhofer,et al.  Social Media Surveillance of Multiple Sclerosis Medications Used During Pregnancy and Breastfeeding: Content Analysis , 2019, Journal of medical Internet research.

[84]  Antoni F. Z. Wisniewski,et al.  Recommendations for the Use of Social Media in Pharmacovigilance: Lessons from IMI WEB-RADR , 2019, Drug Safety.

[85]  Dimitra Pappa,et al.  Harnessing social media data for pharmacovigilance: a review of current state of the art, challenges and future directions , 2019, International Journal of Data Science and Analytics.

[86]  Abeed Sarker,et al.  Mining social media for prescription medication abuse monitoring: a review and proposal for a data-centric framework , 2019, J. Am. Medical Informatics Assoc..

[87]  A. Pariente,et al.  Pharmacology and social media: Potentials and biases of web forums for drug mention analysis—case study of France , 2019, Health Informatics J..