Predicting adverse drug reactions

Researchers at Children’s Hospital Boston have created a new mathematical model that combines multiple forms of widely available data to predict adverse drug events (ADEs). This new method may be able to predict adverse effects years earlier than current approaches, which rely on reporting drug safety issues as they accumulate over time. To create this model, researchers integrated information from a commercially available drug safety database with data on drug chemistry and information on drug and ADE taxonomy. Then, they took a snapshot of 809 drugs and 852 kinds of adverse events associated with those drugs in the drug safety database in 2005. Using the network model, they generated a list of predicted drug-ADE relationships and compared that list to a second snapshot of the database from 2010. The network model effectively predicted drug-ADE relationships that were absent in the 2005 snapshot but present in 2010.