Target adverse event profiles for predictive safety in the post-market setting.
|アブストラクト||We improved a previous pharmacological target adverse-event profile model to predict adverse events on FDA drug labels at the time of approval. The new model uses more drugs and features for learning as well as a new algorithm. Comparator drugs sharing similar target activities to a drug of interest were evaluated by aggregating adverse events from the FDA Adverse Event Reporting System (FAERS), FDA drug labels, and medical literature. An ensemble machine learning model was used to evaluate FAERS case count, disproportionality scores, percent of comparator drug labels with a specific adverse event, and percent of comparator drugs with the reports of the event in the literature. Overall classifier performance was F1 of 0.71, area under the precision-recall curve of 0.78, and area under the receiver operating characteristic curve of 0.87. Target adverse-event analysis continues to show promise as a method to predict adverse events at the time of approval.|
|ジャーナル名||Clinical pharmacology and therapeutics|
|投稿者||Schotland, Peter; Racz, Rebecca; Jackson, David B; Soldatos, Theodoros G; Levin, Robert; Strauss, David; Burkhart, Keith|
|組織名||Division of Applied Regulatory Science, Office of Clinical Pharmacology, CDER,;FDA, Silver Spring, MD, USA.;Office of Oncologic Diseases, Office of New Drugs, CDER, FDA, Silver Spring, MD,;USA.;Molecular Health GmbH, Heidelberg, Germany.;Office of Surveillance and Epidemiology, CDER, FDA, Silver Spring, MD, USA.|