A statistical analysis of vaccine-adverse event data

The association between adverse events of COVID-19 vaccination and anxiety and willingness to receive a booster dose

Many countries have initiated a booster dose for COVID-19 vaccination. However, little is known about the association between adverse events to vaccination and individual psychological status and willingness to receive the booster dose. From December 1, 2021 to February 1, 2022, 474 participants answered a questionnaire in a university town in China, and information about previous adverse events, anxiety status, and vaccination intention were collected. Chi-square test and logistic regression models were used to analyze the factors associated with willingness to receive booster dose of vaccine. Previous adverse events, such as pain at the injection site, fatigue, muscle pain and headache were associated with anxiety of the participants. About 76.2% of the participants were willing to receive booster dose of vaccine. However, adverse event was not associated with their willingness to receive the booster dose. Participants with age ≤25 were less willing to receive the booster dose, although the association was not statistically significant in the multivariable model. In conclusion, the adverse events of COVID-19 vaccination were associated with psychology status of the vaccinated people. It is still necessary to strengthen the public education on COVID-19 vaccination to improve the vaccination willingness of people, especially among the young people.

COVID-19 Vaccine Adverse Event Detection Based on Multi-Label Classification With Various Label Selection Strategies

Analyzing massive VAERS reports without medical context may lead to incorrect conclusions about vaccine adverse events (VAE). Facilitating VAE detection promotes continual safety improvement for new vaccines. This study proposes a multi-label classification method with various term-and topic-based label selection strategies to improve the accuracy and efficiency of VAE detection. Topic modeling methods are first used to generate rule-based label dependencies from Medical Dictionary for Regulatory Activities terms in VAE reports with two hyper-parameters. Multiple label selection strategies, namely one-vs-rest (OvsR), problem transformation (PT), algorithm adaption (AA), and deep learning (DL) methods, are used in multi-label classification to examine the model performance, respectively. Experimental results indicated that the topic-based PT methods improve the accuracy by up to 33.69% using a COVID-19 VAE reporting data set, which improves the robustness and interpretability of our models. In addition, the topic-based OvsR methods achieve an optimal accuracy of up to 98.88%. The accuracy of the AA methods with topic-based labels increased by up to 87.36%. By contrast, the state-of-art LSTM- and BERT-based DL methods have relatively poor performance with accuracy rates of 71.89% and 64.63%, respectively. Our findings reveal that the proposed method effectively improves the model accuracy and strengthens VAE interpretability by using different label selection strategies and domain knowledge in multi-label classification for VAE detection.

Vaccine adverse event reporting system (VAERS): Evaluation of 31 years of reports and pandemics' impact

Background

Vaccine adverse event reporting system (VAERS) was established in the United States (U.S.) as an early warning system with a main purpose of collecting post-marketing Adverse events following immunizations (AEFIs) reports to monitor the vaccine safety and to mitigate the risks from vaccines. During the coronavirus diseases 2019 (COVID-19) pandemic, VAERS got more attention as its important role in monitoring the safety of the vaccines. The aim of this study was to investigate VAERS patterns, reported AEFI, vaccines, and impact of different pandemics since its inception.

Methods

This was an observational study using VARES data from 2/7/1990 to 12/11/2021. Patterns of reports over years were first described, followed by a comparison of reports statistics per year. Furthermore, a comparison of incidents (death, ER visits, etc.) statistics over years, in addition to statistics of each vaccine were calculated. Moreover, each incident's statistics for each vaccine were calculated and top vaccines were reported. All analyses were conducted using R (Version 1.4.1717) and Excel for Microsoft 365.

Results

There were 1,396,280 domestic and 346,210 non-domestic reports during 1990-2021, including 228 vaccines. For both domestic and non-domestic reports, year of 2021 had the highest reporting rate (48.52 % and 70.33 %), in addition a notable change in AEFIs patterns were recorded during 1991, 1998, 2000, 2006, 2009, 2011, and 2017. AEFIs were as follow: deaths (1.00 % and 4.08 %), ER or doctor visits (13.37 % and 2.27 %), hospitalizations (5.84 % and 27.78 %), lethal threat (1.42 % and 4.38 %), and disabilities (1.4 % and 7.96 %). Pyrexia was the top reported symptom during the past 31 years, except for 2021 where headache was the top one. COVID-19 vaccines namely Moderna, Pfizer-Biontech, and Janssen were the top 3 reported vaccines with headache, pyrexia, and fatigue as the top associated AEFIs. Followed by Zoster, Seasonal Influenza, Pneumococcal, and Human papillomavirus vaccines.

Conclusions

The large data available in VARES make it a useful tool for detecting and monitoring vaccine AEFIs. However, its usability relies on understating the limitations of this surveillance system, the impact of governmental regulations, availability of vaccines, and public health recommendations on the reporting rate.

COVID-19 vaccine design using reverse and structural vaccinology, ontology-based literature mining and machine learning

Rational vaccine design, especially vaccine antigen identification and optimization, is critical to successful and efficient vaccine development against various infectious diseases including coronavirus disease 2019 (COVID-19). In general, computational vaccine design includes three major stages: (i) identification and annotation of experimentally verified gold standard protective antigens through literature mining, (ii) rational vaccine design using reverse vaccinology (RV) and structural vaccinology (SV) and (iii) post-licensure vaccine success and adverse event surveillance and its usage for vaccine design. Protegen is a database of experimentally verified protective antigens, which can be used as gold standard data for rational vaccine design. RV predicts protective antigen targets primarily from genome sequence analysis. SV refines antigens through structural engineering. Recently, RV and SV approaches, with the support of various machine learning methods, have been applied to COVID-19 vaccine design. The analysis of post-licensure vaccine adverse event report data also provides valuable results in terms of vaccine safety and how vaccines should be used or paused. Ontology standardizes and incorporates heterogeneous data and knowledge in a human- and computer-interpretable manner, further supporting machine learning and vaccine design. Future directions on rational vaccine design are discussed.

Analyzing adverse drug reaction using statistical and machine learning methods: A systematic review

BACKGROUND

Adverse drug reactions (ADRs) are unintended negative drug-induced responses. Determining the association between drugs and ADRs is crucial, and several methods have been proposed to demonstrate this association. This systematic review aimed to examine the analytical tools by considering original articles that utilized statistical and machine learning methods for detecting ADRs.

METHODS

A systematic literature review was conducted based on articles published between 2015 and 2020. The keywords used were statistical, machine learning, and deep learning methods for detecting ADR signals. The study was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses statement (PRISMA) guidelines.

RESULTS

We reviewed 72 articles, of which 51 and 21 addressed statistical and machine learning methods, respectively. Electronic medical record (EMR) data were exclusively analyzed using the regression method. For FDA Adverse Event Reporting System (FAERS) data, components of the disproportionality method were preferable. DrugBank was the most used database for machine learning. Other methods accounted for the highest and supervised methods accounted for the second highest.

CONCLUSIONS

Using the 72 main articles, this review provides guidelines on which databases are frequently utilized and which analysis methods can be connected. For statistical analysis, >90% of the cases were analyzed by disproportionate or regression analysis with each spontaneous reporting system (SRS) data or electronic medical record (EMR) data; for machine learning research, however, there was a strong tendency to analyze various data combinations. Only half of the DrugBank database was occupied, and the k-nearest neighbor method accounted for the greatest proportion.

Adverse Events Following BNT162b2 mRNA COVID-19 Vaccine Immunization among Healthcare Workers in a Tertiary Hospital in Johor, Malaysia

Background: The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), or 2019 coronavirus disease (COVID-19), was declared as pandemic in early 2020. While several studies reported the short-term adverse events (AE) of the mRNA COVID-19 vaccines, medium-term AE have not been extensively evaluated. This study aimed to evaluate the 6-month side effect profiles of the BNT162b2 mRNA vaccine. Methods: This was a descriptive cross-sectional study conducted in a tertiary hospital. Hospital workers who received two doses of the Cominarty (BNT162b2) mRNA vaccine, six months post-vaccination, were invited to participate in this study. All participants completed a self-reported survey assessing AEs occurrence and severity, duration of onset and recovery and if they previously reported these AEs. Results: Of the 670 respondents who completed the survey, 229 (34.2%) experienced at least one AEs, with a total of 937 AEs reported during the 6-month period. After the first dose, the most common reported localized symptoms were pain (n = 106, 27.2%), swelling (n = 38, 9.8%) and erythematous (n = 12, 3.1%) at injection site. Systemic symptoms reported include fatigue (n = 72, 18.5%), fever (n = 55, 14.1%) and headache (n = 46, 11.8%). After the second dose, pain at site of injection (n = 112, 20.4%), swelling (n = 42, 7.7%) and erythematous (n = 14, 2.6%) were among the localized AE reported, while fever (n = 121, 22.1%), fatigue (n = 101, 18.4%) and headache (n = 61, 11.1%) were the most common systemic AE. The proportion of respondents who experienced moderate (first dose: 156 events; second dose: 272 events) and severe (1st dose: 21 events; 2nd dose: 30 events) AEs were higher after the second dose. Most AEs commonly resolved within 1–2 days, and none required hospitalization. No new onset of AE was observed 7 days post-vaccination. A total of 137 (59.8%) participants did not proceed to formal AE reporting. Conclusion: Most of the AEs reported were of mild to moderate intensity and short-term, consistent with those reported in previous studies. No medium-term finding was detected in the survey. AE reporting was not routinely performed, necessitating the attention of health authorities in order to enhance pharmacovigilance.

Differentially private release of medical microdata: an efficient and practical approach for preserving informative attribute values

Background

Various methods based on k-anonymity have been proposed for publishing medical data while preserving privacy. However, the k-anonymity property assumes that adversaries possess fixed background knowledge. Although differential privacy overcomes this limitation, it is specialized for aggregated results. Thus, it is difficult to obtain high-quality microdata. To address this issue, we propose a differentially private medical microdata release method featuring high utility.

Methods

We propose a method of anonymizing medical data under differential privacy. To improve data utility, especially by preserving informative attribute values, the proposed method adopts three data perturbation approaches: (1) generalization, (2) suppression, and (3) insertion. The proposed method produces an anonymized dataset that is nearly optimal with regard to utility, while preserving privacy.

Results

The proposed method achieves lower information loss than existing methods. Based on a real-world case study, we prove that the results of data analyses using the original dataset and those obtained using a dataset anonymized via the proposed method are considerably similar.

Conclusions

We propose a novel differentially private anonymization method that preserves informative values for the release of medical data. Through experiments, we show that the utility of medical data that has been anonymized via the proposed method is significantly better than that of existing methods.