Comparison of drug safety data obtained from the monitoring system, literature, and social media: An empirical proof from a Chinese patent medicine

Objectives: To investigate the consistency of adverse events (AEs) and adverse drug reactions (ADRs) reported in the literature, monitoring and social media data. Methods: Using one Chinese patent medicine-Cordyceps sinensis extracts (CSE) as an example, we obtained safety data from the national monitoring system (July 2002 to February 2016), literature (up to November 2016) and social media (May 2019). For literature data, we searched the Chinese National Knowledge Infrastructure Database (CNKI), WanFang database, Chinese Science and Technology Periodical Database (VIP), Chinese Biomedical Literature Database (SinoMed), PubMed, Embase and the Cochrane Library. Social media data was from the Baidu post bar and Sina micro-blog. Two authors independently screened the literature and extracted data by PRISMA Harms checklist was followed. AEs and ADRs were coded using the World Health Organization Adverse Reaction Terminology (WHO-ART). AEs and ADRs were grouped into thirty-one organ-system classes for comparisons. Frequencies, relative frequencies and rank were used as metrics. Radar chart was used to manifest the features of the distributions and proportions. Results: 610 AEs reported in CFDA monitoring data were associated with CSE, of which 537 (88.03%) were suspected ADRs (10.49% certain). 5568 AEs were identified from 172 papers (63% RCTs, 37% other types of studies including case series, case reports, ADR monitoring reports and reviews), in which 86 (1.54%) were ADRs (1.54% certain). 15 AEs (0 certain ADR) were identified from social media. AEs, ADRs and their affected system-organ classes, looked largely similar, but different in every aspect when looking at details. Data from RCTs demonstrated the most disparity. Conclusions: In our study, the most prevalent AEs and ADRs, mainly gastro-intestinal system disorders including nausea, diarrhea and vomiting, in monitoring system were largely similar with those in literature and social media. But data from different sources varied if looked at details. Multiple data sources (the monitoring system, literature and social media) should be integrated to collect safety information of interventions. The distributions of AEs and ADRs from RCTs were least similar with the data from other sources. Our empirical proof is consistent with other similar studies.