Background Vaccine safety surveillance is important because it is related to vaccine hesitancy, which affects vaccination rate. To increase confidence in vaccination, the active monitoring of vaccine adverse events is important. For effective active surveillance, we developed and verified a machine learning-based active surveillance system using national claim data. Methods We used two databases, one from the Korea Disease Control and Prevention Agency, which contains flu vaccination records for the elderly, and another from the National Health Insurance Service, which contains the claim data of vaccinated people. We developed a case-crossover design based machine learning model to predict the health outcome of interest events (anaphylaxis and agranulocytosis) using a random forest. Feature importance values were evaluated to determine candidate associations with each outcome. We investigated the relationship of the features to each event via a literature review, comparison with the Side Effect Resource, and using the Local Interpretable Model-agnostic Explanation method. Results The trained model predicted each health outcome of interest with a high accuracy (approximately 70%). We found literature supporting our results, and most of the important drug-related features were listed in the Side Effect Resource database as inducing the health outcome of interest. For anaphylaxis, flu vaccination ranked high in our feature importance analysis and had a positive association in Local Interpretable Model-Agnostic Explanation analysis. Although the feature importance of vaccination was lower for agranulocytosis, it also had a positive relationship in the Local Interpretable Model-Agnostic Explanation analysis. Conclusion We developed a machine learning-based active surveillance system for detecting possible factors that can induce adverse events using health claim and vaccination databases. The results of the study demonstrated a potentially useful application of two linked national health record databases. Our model can contribute to the establishment of a system for conducting active surveillance on vaccination.

Vaccines require higher safety standards than most other medicinal products because they are given to healthy individuals, including infants, children, and elderly. Despite various activities by national agencies, public concern about vaccine safety often arises. Post-marketing activities for vaccine safety can be broadly classified into passive and active surveillances. Many countries as well as Korea operate passive vaccine safety surveillance systems that report adverse events related to vaccines. However, the active surveillance systems operate only in several countries, such as the United States of America (USA), Europe, Canada and Australia. In the US, Vaccine Safety Datalink (VSD) and Post-Licensure Rapid Immunization Safety Monitoring (PRISM) were developed in 1990 and 2009 respectively for monitoring vaccine actively. In the case of Europe, the Vaccine Adverse Event Surveillance and Communication (VAESCO) consortium was launched in 2008. After the end of VAESCO, the Accelerated Development of VAccine beNefit-risk Collaboration in Europe (ADVANCE) was organized to establish a vaccine benefit-risk monitoring framework in 2013. Canada has been operating a vaccine active monitoring system known as the Canadian Immunization Monitoring Program, ACTive (IMPACT) since 1991. The objective of this review was to describe and compare background, databases, and analysis systems of various vaccine active surveillance systems in the US, Europe, and Canada. We described the examples of studies on the safety of influenza A (H1N1) vaccines carried out in each system. This review could help provide directions for the future development of the ideal active vaccine safety surveillance system in Korea.

No abstract

Objectives: The purpose of this study was to investigate the human papillomavirus (HPV) vaccination proportion and the factors associated with HPV non-vaccination according to the characteristics of Americans. Methods: The 2015-2018 National Health and Nutrition Survey (NHANES) data were analyzed. The subjects aged 9 to 26 were divided into subgroups according to age and sex. Results: The meaningful variables influencing HPV vaccination included birth country, health insurance, hepatitis A vaccine, hepatitis B vaccine, routine place to go for healthcare and times receive healthcare last year. The factors associated with HPV non-vaccination were income, hepatitis A vaccine, hepatitis B vaccine and times receive healthcare last year. Conclusions: This study was based on a survey of Americans, so the factors associated with HPV non-vaccination may differ from those of Koreans.