BackgroundAlbeit the need for sex-disaggregated results of adverse events after immunization (AEFIs) is gaining attention since the COVID-19 pandemic, studies with emphasis on sexual dimorphism in response to COVID-19 vaccination are relatively scarce. This prospective cohort study aimed to assess differences in the incidence and course of reported AEFIs after COVID-19 vaccination between males and females in the Netherlands and provides a summary of sex-disaggregated outcomes in published literature.MethodsPatient reported outcomes of AEFIs over a six month period following the first vaccination with BioNTech-Pfizer, AstraZeneca, Moderna or the Johnson&Johnson vaccine were collected in a Cohort Event Monitoring study. Logistic regression was used to assess differences in incidence of ‘any AEFI’, local reactions and the top ten most reported AEFIs between the sexes. Effects of age, vaccine brand, comorbidities, prior COVID-19 infection and the use of antipyretic drugs were analyzed as well. Also, time-to-onset, time-to-recovery and perceived burden of AEFIs was compared between the sexes. Third, a literature review was done to retrieve sex-disaggregated outcomes of COVID-19 vaccination.ResultsThe cohort included 27,540 vaccinees (38.5% males). Females showed around two-fold higher odds of having any AEFI as compared to males with most pronounced differences after the first dose and for nausea and injection site inflammation. Age was inversely associated with AEFI incidence, whereas a prior COVID-19 infection, the use of antipyretic drugs and several comorbidities were positively associated. The perceived burden of AEFIs and time-to-recovery were slightly higher in females.DiscussionThe results of this large cohort study correspond to existing evidence and contribute to the knowledge gain necessary to disentangle the magnitude of the effect sex in response to vaccination. Whilst females have a significant higher probability of experiencing an AEFI than males, we observed that the course and burden is only to a minor extent different between the sexes.

Background The number of Individual Case Safety Reports (ICSRs) in pharmacovigilance databases are rapidly increasing world‐wide. The majority of ICSRs at the Netherlands Pharmacovigilance Centre Lareb is reviewed manually to identify potential signal triggering reports (PSTR) or ICSRs which need further clinical assessment for other reasons. Objectives To develop a prediction model to identify ICSRs that require clinical review, including PSTRs. Secondly, to identify the most important features of these reports. Methods All ICSRs (n = 30 424) received by Lareb between October 1, 2017 and February 26, 2021 were included. ICSRs originating from marketing authorisation holders and ICSRs reported on vaccines were excluded. The outcome was defined as PSTR (yes/no), where PSTR ‘yes’ was defined as an ICSR discussed at a signal detection meeting. Nineteen features were included, concerning structured information on: patients, adverse drug reactions (ADR) or drugs. Data were divided into a training (70%) and test set (30%) using a stratified split to maintain the PSTR/no PSTR ratio. Logistic regression, elastic net logistic regression and eXtreme Gradient Boosting models were trained and tuned on a training set. Random down‐sampling of negative controls was applied on the training set to adjust for the imbalanced dataset. Final models were evaluated on the test set. Model performances were assessed using the area under the curve (AUC) with 95% confidence interval of a receiver operating characteristic (ROC), and specificity and precision were assessed at a threshold for perfect sensitivity (100%, to not miss any PSTRs). Feature importance plots were inspected and a selection of features was used to re‐train and test model performances with fewer features. Results 1439 (4.7%) of reports were PSTR. All three models performed equally with a highest AUC of 0.75 (0.73–0.77). Despite moderate model performances, specificity (5%) and precision (5%) were low. Most important features were: ‘absence of ADR in the Summary of product characteristics’, ‘ADR reported as serious’, ‘ADR labelled as an important medical event’, ‘ADR reported by physician’ and ‘positive rechallenge’. Model performances were similar when using only nine of the most important features. Conclusions We developed a prediction model with moderate performances to identify PSTRs with nine commonly available features. Optimisation of the model using more ICSR information (e.g., free text fields) to increase model precision is required before implementation.

Objective: To improve a previously developed prediction model that could assist in the triage of individual case safety reports using the addition of features designed from free text fields using natural language processing.Methods: Structured features and natural language processing (NLP) features were used to train a bagging classifier model. NLP features were extracted from free text fields. A bag-of-words model was applied. Stop words were deleted and words that were significantly differently distributed among the case and non-case reports were used for the training data. Besides NLP features from free-text fields, the data also consisted of a list of signal words deemed important by expert report assessors. Lastly, variables with multiple categories were transformed to numerical variables using the weight of evidence method.Results: the model, a bagging classifier of decision trees had an AUC of 0.921 (95% CI = 0.918–0.925). Generic drug name, info text length, ATC code, BMI and patient age. were most important features in classification.Conclusion: this predictive model using Natural Language Processing could be used to assist assessors in prioritizing which future ICSRs to assess first, based on the probability that it is a case which requires clinical review.