![]() ![]() Despite moderate model performances, specificity (5%) and precision (5%) were low. All three models performed equally with a highest AUC of 0.75 (0.73–0.77). Feature importance plots were inspected and a selection of features was used to re-train and test model performances with fewer features. 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). Final models were evaluated on the test set. Random down-sampling of negative controls was applied on the training set to adjust for the imbalanced dataset. Logistic regression, elastic net logistic regression and eXtreme Gradient Boosting models were trained and tuned on a training set. Data were divided into a training (70%) and test set (30%) using a stratified split to maintain the PSTR/no PSTR ratio. Nineteen features were included, concerning structured information on: patients, adverse drug reactions (ADR) or drugs. The outcome was defined as PSTR (yes/no), where PSTR ‘yes’ was defined as an ICSR discussed at a signal detection meeting. ICSRs originating from marketing authorisation holders and ICSRs reported on vaccines were excluded. MethodsĪll ICSRs ( n = 30 424) received by Lareb between Octoand Februwere included. Secondly, to identify the most important features of these reports. To develop a prediction model to identify ICSRs that require clinical review, including PSTRs. 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. The number of Individual Case Safety Reports (ICSRs) in pharmacovigilance databases are rapidly increasing world-wide. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |