Signal detection of human papillomavirus vaccines using the Korea Adverse Events Reporting System database, between 2005 and 2016

The Role of Scientific Research in Human Papillomavirus Vaccine Discussions on Twitter: Social Network Analysis

BACKGROUND

Attitudes toward the human papillomavirus (HPV) vaccine and accuracy of information shared about this topic in web-based settings vary widely. As real-time, global exposure to web-based discourse about HPV immunization shapes the attitudes of people toward vaccination, the spread of misinformation and misrepresentation of scientific knowledge contribute to vaccine hesitancy.

OBJECTIVE

In this study, we aimed to better understand the type and quality of scientific research shared on Twitter (recently rebranded as X) by vaccine-hesitant and vaccine-confident communities.

METHODS

To analyze the use of scientific research on social media, we collected tweets and retweets using a list of keywords associated with HPV and HPV vaccines using the Academic Research Product Track application programming interface from January 2019 to May 2021. From this data set, we identified tweets referring to or sharing scientific literature through a Boolean search for any tweets with embedded links, hashtags, or keywords associated with scientific papers. First, we used social network analysis to build a retweet or reply network to identify the clusters of users belonging to either the vaccine-confident or vaccine-hesitant communities. Second, we thematically assessed all shared papers based on typology of evidence. Finally, we compared the quality of research evidence and bibliometrics between the shared papers in the vaccine-confident and vaccine-hesitant communities.

RESULTS

We extracted 250 unique scientific papers (including peer-reviewed papers, preprints, and gray literature) from approximately 1 million English-language tweets. Social network maps were generated for the vaccine-confident and vaccine-hesitant communities sharing scientific research on Twitter. Vaccine-hesitant communities share fewer scientific papers; yet, these are more broadly disseminated despite being published in less prestigious journals compared to those shared by the vaccine-confident community.

CONCLUSIONS

Vaccine-hesitant communities have adopted communication tools traditionally wielded by health promotion communities. Vaccine-confident communities would benefit from a more cohesive communication strategy to communicate their messages more widely and effectively.

Application of tree-based machine learning classification methods to detect signals of fluoroquinolones using the Korea Adverse Event Reporting System (KAERS) database

BACKGROUND

Safety issues for fluoroquinolones have been provided by regulatory agencies. This study was conducted to identify signals of fluoroquinolones reported in the Korea Adverse Event Reporting System (KAERS) using tree-based machine learning (ML) methods.

RESEARCH DESIGN AND METHODS

All adverse events (AEs) associated with the target drugs reported in the KAERS from 2013 to 2017 were matched with drug label information. A dataset containing label-positive and -negative AEs was arbitrarily divided into training and test sets. Decision tree, random forest (RF), bagging, and gradient boosting machine (GBM) were fitted on the training set with hyperparameters tuned using five-fold cross-validation and applied to the test set. The ML method with the highest area under the curve (AUC) scores was selected as the final ML model.

RESULTS

Bagging was selected as the final ML model for gemifloxacin (AUC score: 1) and levofloxacin (AUC: 0.9987). RF was selected in ciprofloxacin, moxifloxacin, and ofloxacin (AUC scores: 0.9859, 0.9974, and 0.9999 respectively). We found that the final ML methods detected additional signals that were not detected using the disproportionality analysis (DPA) methods.

CONCLUSIONS

The bagging-or-RF-based ML methods performed better than DPA and detected novel AE signals previously unidentified using the DPA methods.

Detecting early safety signals of infliximab using machine learning algorithms in the Korea adverse event reporting system

There has been a growing attention on using machine learning (ML) in pharmacovigilance. This study aimed to investigate the utility of supervised ML algorithms on timely detection of safety signals in the Korea Adverse Event Reporting System (KAERS), using infliximab as a case drug, between 2009 and 2018. Input data set for ML training was constructed based on the drug label information and spontaneous reports in the KAERS. Gold standard dataset containing known AEs was randomly divided into the training and test sets. Two supervised ML algorithms (gradient boosting machine [GBM], random forest [RF]) were fitted with hyperparameters tuned on the training set by using a fivefold validation. Then, we stratified the KAERS data by calendar year to create 10 cumulative yearly datasets, in which ML algorithms were applied to detect five pre-specified AEs of infliximab identified during post-marketing surveillance. Four AEs were detected by both GBM and RF in the first year they appeared in the KAERS and earlier than they were updated in the drug label of infliximab. We further applied our models to data retrieved from the US Food and Drug Administration Adverse Event Reporting System repository and found that they outperformed existing disproportionality methods. Both GBM and RF demonstrated reliable performance in detecting early safety signals and showed promise for applying such approaches to pharmacovigilance.

Lung Cancer Adverse Events Reports for Angiotensin-Converting Enzyme Inhibitors: Data Mining of the FDA Adverse Event Reporting System Database

Because of contradictory evidence from clinical trials, the association between angiotensin-converting enzyme inhibitors (ACEIs) and lung cancer needs further evaluation. As such, the current study is to assess disproportionate reporting of primary malignant lung cancer among reports for ACEIs submitted to the FDA adverse event reporting system utilizing a pharmacovigilance approach. We conducted a disproportionality analysis of primary malignant lung cancer adverse events associated with 10 ACEIs by calculating the reported odds ratios (ROR) and information component (IC) with 95% confidence intervals (CI). ROR was adjusted for sex, age, and reporting year by logistic regression analyses. From January 2004 to March 2020, a total of 622 cases of lung cancer adverse event reports were identified for ACEIs users. Significant disproportionate association was found for ACEIs as a drug class (ROR: 1.22, 95% CI: 1.13–1.32; IC: 0.28, 95% CI: 0.17–0.39. adjusted ROR: 1.23, 95% CI: 1.02–1.49). After stratification based on gender, a subset analysis suggested that female patients exhibited a significant disproportionate association, while male patients did not. Sensitivity analyses that limited the data by reporting region, comorbidity, and reporting year also showed similar trends. Statistical significant lung cancer signals were detected among patients who received ACEI, especially female patients. The disproportionality analysis of the FAERS database suggests mildly increased reporting of lung cancer among ACEI users. Further robust epidemiological studies are necessary to confirm this relationship.

Association between human papillomavirus vaccination and serious adverse events in South Korean adolescent girls: nationwide cohort study

OBJECTIVE

To evaluate the association between human papillomavirus (HPV) vaccination and serious adverse events in adolescent girls in South Korea.

DESIGN

Cohort study.

SETTING

A large linked database created by linking the Korea Immunization Registry Information System and the National Health Information Database, between January 2017 and December 2019.

PARTICIPANTS

441 399 girls aged 11-14 years who had been vaccinated in 2017: 382 020 had been vaccinated against HPV and 59 379 had not been vaccinated against HPV.

MAIN OUTCOME MEASURES

Outcomes were 33 serious adverse events, including endocrine, gastrointestinal, cardiovascular, musculoskeletal, haematological, dermatological, and neurological diseases. A cohort design was used for the primary analysis and a self-controlled risk interval design for the secondary analysis; both analyses used a risk period of one year after HPV vaccination for each outcome. Incidence rate and adjusted rate ratios were estimated using Poisson regression in the primary analysis, comparing the HPV vaccinated group with the HPV unvaccinated group, and adjusted relative risks were estimated using conditional logistic regression in the secondary analysis.

RESULTS

Among the 33 predefined serious adverse events, no associations were found with HPV vaccination in the cohort analysis, including Hashimoto's thyroiditis (incidence rate per 100 000 person years: 52.7 v 36.3 for the vaccinated and unvaccinated groups; adjusted rate ratio 1.24, 95% confidence interval 0.78 to 1.94) and rheumatoid arthritis (incidence rate per 100 000 person years: 168.1 v 145.4 for the vaccinated and unvaccinated groups; 0.99, 0.79 to 1.25), with the exception of an increased risk observed for migraine (incidence rate per 100 000 person years: 1235.0 v 920.9 for the vaccinated and unvaccinated groups; 1.11, 1.02 to 1.22). Secondary analysis using self-controlled risk intervals confirmed no associations between HPV vaccination and serious adverse events, including migraine (adjusted relative risk 0.67, 95% confidence interval 0.58 to 0.78). Results were robust to varying follow-up periods and for vaccine subtypes.

CONCLUSIONS

In this nationwide cohort study, with more than 500 000 doses of HPV vaccines, no evidence was found to support an association between HPV vaccination and serious adverse events using both cohort analysis and self-controlled risk interval analysis. Inconsistent findings for migraine should be interpreted with caution considering its pathophysiology and the population of interest.

Machine Learning for Detection of Safety Signals From Spontaneous Reporting System Data: Example of Nivolumab and Docetaxel

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.