No abstract

We detected disproportionate reports of premature ovarian insufficiency (POI) and related events, including amenorrhea, menstruation irregular, FSH increased, and premature menopause, following human papillomavirus (HPV) vaccine from FDA Vaccine Adverse Event Reporting System (VAERS). The signal was detected by the methods of Bayesian Confidence Propagation Neural Network (BCPNN) and Multi-item Gamma Poisson Shrinker (MGPS). When both methods detected a positive result, a signal was generated. Besides, time-scan map is drawn based on the IC value and 95%CI of BCPNN, if the IC curve showed a steady upward trend and the 95%CI narrowed, the signal was stable and strong association.The results showed that there were not POI reports of HPV vaccine, but VAERS received a total of 2, 389, 27 POI related events for HPV2, HPV4, HPV9 respectively from the year of marketed to 2018. No signal was detected for HPV2. HPV4-POI ralated events were all detected as signals by two methods. There was only one signal of menstruation irregular for HPV9. Time scan of HPV4-POI ralated events showed those signals were stability and strong association, but not for HPV9. Our results only represent statistical association between HPV vaccine and POI related events, causal relationship needs further investigation.

No abstract

The aim of this study was to apply machine learning methods to deeply explore the risk factors associated with adverse drug events (ADEs) and predict the occurrence of ADEs in Chinese pediatric inpatients. Data of 1,746 patients aged between 28 days and 18 years (mean age = 3.84 years) were included in the study from January 1, 2013, to December 31, 2015, in the Children’s Hospital of Chongqing Medical University. There were 247 cases of ADE occurrence, of which the most common drugs inducing ADEs were antibacterials. Seven algorithms, including eXtreme Gradient Boosting (XGBoost), CatBoost, AdaBoost, LightGBM, Random Forest (RF), Gradient Boosting Decision Tree (GBDT), and TPOT, were used to select the important risk factors, and GBDT was chosen to establish the prediction model with the best predicting abilities (precision = 44%, recall = 25%, F1 = 31.88%). The GBDT model has better performance than Global Trigger Tools (GTTs) for ADE prediction (precision 44 vs. 13.3%). In addition, multiple risk factors were identified via GBDT, such as the number of trigger true (TT) (+), number of doses, BMI, number of drugs, number of admission, height, length of hospital stay, weight, age, and number of diagnoses. The influencing directions of the risk factors on ADEs were displayed through Shapley Additive exPlanations (SHAP). This study provides a novel method to accurately predict adverse drug events in Chinese pediatric inpatients with the associated risk factors, which may be applicable in clinical practice in the future.