Quick Hits: Guidelines Could Boost Use of Hypertension Meds, Using AI to Predict Drug Interactions & More

Artificial intelligence may be able to predict potential side effects of drug interactions. A new system called Decagon, developed by computer scientists at Stanford University, could aid doctors in making more informed decisions about which drugs to prescribe and help researchers find better combinations of drugs to treat complex diseases. Currently, there is no real way of knowing potential interactions for most drug combinations. “There are about 1,000 different known side effects and 5,000 drugs on the market, making for nearly 125 billion possible side effects between all possible pairs of drugs,” according to a Stanford news release. “Most of these have never been prescribed together, let alone systematically studied.” Researchers found a way around this problem by developing a system (Decagon) that is designed to deduce patterns about drug interaction side effects and predict previously unseen consequences from taking 2 drugs together. In many cases, the predicted side effects, which were based on the patterns detected, came true. To date, Decagon only considers side effects associated with pairs of drugs. In the future, scientists hope to further develop the system to incorporate more complex regimens. Posted July 10, 2018. Via Stanford News.

Leave a Reply

Your email address will not be published. Required fields are marked *