Network Analysis for Signal Detection in Spontaneous Adverse Event Reporting Database: Application of Network Weighting Normalization to Characterize Cardiovascular Drug Safety.

Introduction: Signal detection yields confirmed signals in only 2.1%, which imposes a heavy burden on the pharmacovigilance system in the European Union.
Objectives: We aimed to develop a network theoretical metric to increase the confirmed signal ratio of individual case safety report (ICSR) networks.
Methods: ICSRs of five cardiovascular adverse events were requested from EudraVigilance. We developed Vigilace™, a web-based application to build network representation of ICSRs. Three network-based signal scores, which we termed NEWS (normalized edge weight for signals) scores, were calculated by normalizing the weight of each edge in the report-based weighted network by the weight of the same edge in topological weighted networks. Depending on the third node in topological network edges, we defined full-, adverse event-, and drug-type NEWS scores. Area under the receiver operating characteristic curves (AUROC) were analyzed to compare the reporting odds ratio (ROR) and NEWS scores.
Results: Overall, 72,475 ICSRs were accessed from EudraVigilance. Drug-type NEWS (NEWS _D ) score performed better (DeLong test, p-value <0.05) compared with the ROR in case of four adverse events: acute myocardial infarction (AUROC: 0.856 vs. 0.720), arrhythmia (0.657 vs. 0.614), pulmonary hypertension (0.861 vs. 0.720), and QT prolongation (0.830 vs. 0.749). Postural orthostatic tachycardia syndrome was excluded due to the lack of reference data.
Conclusion: This is the first demonstration that report-based weighting normalized by topological weighting of co-reported drugs, which we termed as NEWS _D score, can perform better compared with the ROR. An application was developed for ICSR network analysis that facilitates the calculation of this score.
(© 2022. The Author(s).)