Introduction and ObjectiveSocial 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.MethodsPerformance 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.ResultsAcross 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%).ConclusionsOur 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.Electronic supplementary materialThe online version of this article (10.1007/s40264-018-0699-2) contains supplementary material, which is available to authorized users.

A favorable benefit–risk profile remains an essential requirement for marketing authorization of medicinal drugs and devices. Furthermore, prior subjective, implicit and inconsistent ad hoc benefit–risk assessment methods have rightly evolved towards more systematic, explicit or “structured” approaches. Contemporary structured benefit–risk evaluation aims at providing an objective assessment of the benefit–risk profile of medicinal products and a higher transparency for decision making purposes. The use of a descriptive framework should be the preferred starting point for a structured benefit–risk assessment. In support of more precise assessments, quantitative and semi-quantitative methodologies have been developed and utilized to complement descriptive or qualitative frameworks in order to facilitate the structured evaluation of the benefit–risk profile of medicinal products. In addition, quantitative structured benefit–risk analysis allows integration of patient preference data. Collecting patient perspectives throughout the medical product development process has become increasingly important and key to the regulatory decision-making process. Both industry and regulatory authorities increasingly rely on descriptive structured benefit–risk evaluation and frameworks in drug, vaccine and device evaluation and comparison. Although varied qualitative methods are more commonplace, quantitative approaches have recently been emphasized. However, it is unclear how frequently these quantitative frameworks have been used by pharmaceutical companies to support submission dossiers for drug approvals or to respond to the health authorities’ requests. The objective of this study has been to identify and review, for the first time, currently available, published, structured, quantitative benefit–risk evaluations which may have informed health care professionals and/or payor as well as contributed to decision making purposes in the regulatory setting for drug, vaccine and/or device approval. Plain language summary Quantitative evaluation of the benefit–risk balance for medicinal products The review of the benefits and the risks associated with a medicinal product is called benefit–risk assessment. One of the conditions for a medicinal product to receive marketing authorization is to demonstrate a positive benefit–risk balance in which the benefits outweigh the risks. In order to enhance the transparency and consistency in the assessment of benefit–risk balance, frameworks and quantitative methods have been developed for decision making purposes and regulatory approvals of medicinal products. This article considers published quantitative benefit–risk evaluations which may have informed health care professionals and/or payor as well as contributed to decision making purposes in the regulatory setting for drug, vaccine and/or device approval.

Future research is needed to find better refinements of query data and/or the metrics to improve the specificity of these web query log algorithms.

BackgroundWhile traditional signal detection methods in pharmacovigilance are based on spontaneous reports, the use of social media is emerging. The potential strength of Web-based data relies on their volume and real-time availability, allowing early detection of signals of disproportionate reporting (SDRs).ObjectiveThis study aimed (1) to assess the consistency of SDRs detected from patients’ medical forums in France compared with those detected from the traditional reporting systems and (2) to assess the ability of SDRs in identifying earlier than the traditional reporting systems.MethodsMessages posted on patients’ forums between 2005 and 2015 were used. We retained 8 disproportionality definitions. Comparison of SDRs from the forums with SDRs detected in VigiBase was done by describing the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, receiver operating characteristics curve, and the area under the curve (AUC). The time difference in months between the detection dates of SDRs from the forums and VigiBase was provided.ResultsThe comparison analysis showed that the sensitivity ranged from 29% to 50.6%, the specificity from 86.1% to 95.5%, the PPV from 51.2% to 75.4%, the NPV from 68.5% to 91.6%, and the accuracy from 68% to 87.7%. The AUC reached 0.85 when using the metric empirical Bayes geometric mean. Up to 38% (12/32) of the SDRs were detected earlier in the forums than that in VigiBase.ConclusionsThe specificity, PPV, and NPV were high. The overall performance was good, showing that data from medical forums may be a valuable source for signal detection. In total, up to 38% (12/32) of the SDRs could have been detected earlier, thus, ensuring the increased safety of patients. Further enhancements are needed to investigate the reliability and validation of patients’ medical forums worldwide, the extension of this analysis to all possible drugs or at least to a wider selection of drugs, as well as to further assess performance against established signals.

Maternal exposure to intranasal triamcinolone during pregnancy was not associated with the risk of SGA/spontaneous abortions/overall malformations. However, it has been shown to increase the risk of respiratory system defects. Chance finding cannot be ruled out.

No abstract

No abstract

Purpose Adverse event (AE) identification in social media (SM) can be performed using various types of natural language processing (NLP) and machine learning (ML). These methods can be categorized by complexity and precision level. Co‐occurrence‐based ML methods are rather basic, as they identify simultaneous appearance of drugs and clinical events in a single post. In contrast, statistical learning methods involve more complex NLP and identify drugs, events, and associations between them. We aimed to compare the ability of co‐occurrence and NLP to identify AEs and signals of disproportionate reporting (SDR) in patient‐generated SM. We also examined the performance of lift in SM‐based signal detection (SD). Methods Our examination was performed in a corpus of SM posts crawled from open online patient forums and communities, using the spontaneously reported VigiBase data as reference data set. Results We found that co‐occurrence and NLP produce AEs, which are 57% and 93% consistent with VigiBase AEs, respectively. Among the SDRs identified both in SM and in VigiBase, up to 55.3% were identified earlier in co‐occurrence, and up to 32.1% were identified earlier in NLP‐processed SM. Using lift in SM SD provided performance similar to frequentist methods, both in co‐occurrence and in NLP‐processed AEs. Conclusion Our results indicate that using SM as a data source complementary to traditional pharmacovigilance sources should be considered further. Various levels of SM processing may be considered, depending on the preferred policies and tolerance for false‐positive to false‐negative balance in routine pharmacovigilance processes.