2020
Peter Schotland, Rebecca Racz, David B. Jackson, Theodoros G. Soldatos, Robert Levin, David Strauss, Keith Burkhart
https://ascpt.onlinelibrary.wiley.com/doi/abs/10.1002/cpt.2074
Abstract
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.
