Search

With the advent of live-attenuated, quadrivalent, and cell-cultured vaccines for influenza, there have been discussions on the safety of these vaccines compared to conventional vaccines (such as inactivated, trivalent, and egg-cultured vaccines) because of the development of neurological adverse events (AEs). This study aimed to compare the trends and safety signals in the AE reporting systems of the US and South Korea and, more particularly, to evaluate the association between influenza vaccination and Guillain–Barré syndrome (GBS). In total, 400,535 AE reports from the US Vaccine Adverse Event Reporting System (VAERS) and 28,766 AE reports from the Korea Adverse Event Reporting System (KAERS) between 2005 and 2017 were assessed. Disproportionality analysis was performed to detect the safety signals and examine the potential risk of GBS with influenza vaccination using the case/non-case approach. In both databases, GBS was the most frequently reported AE following influenza immunization. Using the case/non-case approach, the adjusted reporting odds ratio (ROR) of GBS was 3.57 (95% confidence interval [CI], 3.16–4.03) and 3.09 (95% CI, 0.83–11.45) in the VAERS and KAERS data, respectively. People vaccinated with live-attenuated vaccines reported 2.30 times (95% CI, 1.74–3.05) more cases of GBS than those vaccinated with other types of vaccines. Our analysis of the VAERS and KAERS reports for AEs following immunization (AEFI) for influenza shows the need for cautious monitoring regarding the development of GBS after influenza vaccination, particularly, after live-attenuated vaccination. However, owing to potential reporting bias caused by limited AEFI reports after the introduction of new types of influenza vaccines, further prospective safety studies are needed. [ABSTRACT FROM AUTHOR]

Introduction: Various methods have been implemented to detect adverse drug reaction (ADR) signals. However, the applicability of machine learning methods has not yet been fully evaluated. Objective: To evaluate the feasibility of machine learning algorithms in detecting ADR signals of nivolumab and docetaxel, new and old anticancer agents. Methods: We conducted a safety surveillance study of nivolumab and docetaxel using the Korea national spontaneous reporting database from 2009 to 2018. We constructed a novel input dataset for each study drug comprised of known ADRs that were listed in the drug labels and unknown ADRs. Given the known ADRs, we trained machine learning algorithms and evaluated predictive performance in generating safety signals of machine learning algorithms (gradient boosting machine [GBM] and random forest [RF]) compared with traditional disproportionality analysis methods (reporting odds ratio [ROR] and information component [IC]) by using the area under the curve (AUC). Each method then was implemented to detect new safety signals from the unknown ADR datasets. Results: Of all methods implemented, GBM achieved the best average predictive performance (AUC: 0.97 and 0.93 for nivolumab and docetaxel). The AUC achieved by each method was 0.95 and 0.92 (RF), 0.55 and 0.51 (ROR), and 0.49 and 0.48 (IC) for respective drug. GBM detected additional 24 and nine signals for nivolumab and 82 and 76 for docetaxel compared to ROR and IC, respectively, from the unknown ADR datasets. Conclusion: Machine learning algorithm based on GBM performed better and detected more new ADR signals than traditional disproportionality analysis methods. [ABSTRACT FROM AUTHOR]