Mining Patients' Narratives in Social Media for Pharmacovigilance: Adverse Effects and Misuse of Methylphenidate

Abstract

Background: The Food and Drug Administration (FDA) in the United States and the European Medicines Agency (EMA) have recognized social media as a new data source to strengthen their activities regarding drug safety.Objective: Our objective in the ADR-PRISM project was to provide text mining and visualization tools to explore a corpus of posts extracted from social media. We evaluated this approach on a corpus of 21 million posts from five patient forums, and conducted a qualitative analysis of the data available on methylphenidate in this corpus.Methods: We applied text mining methods based on named entity recognition and relation extraction in the corpus, followed by signal detection using proportional reporting ratio (PRR). We also used topic modeling based on the Correlated Topic Model to obtain the list of the matics in the corpus and classify the messages based on their topics.Results: We automatically identified 3443 posts about methylphenidate published between 2007 and 2016, among which 61 adverse drug reactions (ADR) were automatically detected. Two pharmacovigilance experts evaluated manually the quality of automatic identification, and a f-measure of 0.57 was reached. Patient's reports were mainly neuro-psychiatric effects. Applying PRR, 67% of the ADRs were signals, including most of the neuro-psychiatric symptoms but also palpitations. Topic modeling showed that the most represented topics were related to Childhood and Treatment initiation, but also Side effects. Cases of misuse were also identified in this corpus, including recreational use and abuse.Conclusion: Named entity recognition combined with signal detection and topic modeling have demonstrated their complementarity in mining social media data. An in-depth analysis focused on methylphenidate showed that this approach was able to detect potential signals and to provide better understanding of patients' behaviors regarding drugs, including misuse.

Recommendations for the Use of Social Media in Pharmacovigilance: Lessons from IMI WEB-RADR

“…Admittedly, WEB-RADR’s focus on Twitter and Facebook limits the generalisability of this conclusion and research conducted during the WEB-RADR project and elsewhere using patient fora have identified some data-rich areas. Although the WEB-RADR study of Caster et al [15] did not show any benefit in SD performance using data from patient fora, evidence has been generated concerning methylphenidate and misuse [31, 32], and elsewhere research has shown that social media data can provide real-world use data and outcomes to inform safety decision making [11, 33, 34].…”

Identification of Adverse Drug Event–Related Japanese Articles: Natural Language Processing Analysis

“…Numerous studies have already identified ADEs reported in medical articles via NLPs [ 8 , 9 ], electronic health records [ 5 , 6 ], and social media posts [ 10 , 11 ]. An annotated corpus for the automatic detection of ADEs was created for case reports in medical articles [ 26 ].…”

“…Existing automation research targets different source materials, reflecting the wide range of signals processed by real-world postmarketing surveillance. These inputs include electronic health records [ 5 , 6 ], patient reports [ 7 ], medical articles [ 8 , 9 ], and social media posts [ 10 , 11 ]. This study focuses on medical articles as they comprise a substantial portion of postmarketing surveillance in many countries.…”

Implementation science and periodontal practice: Translation of evidence into periodontology

“…In dentistry, we see this with underutilization of pit and fissure sealants despite robust evidence of their effectiveness . Misuse is the incorrect provision of care; for example, prescription of medications for the wrong purpose, dose, or duration, such as seen in the current opioid epidemic in the USA …”