Data science uncovers drug interactions with significant risks

Warnings for specific prescription drugs may not cover the implications of mixing certain medications, which can mean side effects much worse than just dizziness or upset stomach. While many of the dangerous drug parings have been discovered, many are still hidden. Researchers from New York's Columbia University Medical Center and the Data Science Institute at Columbia University are using data science to uncover such interactions.

Researchers were able to use a government database of reported drug side effects and match them with patient records to discover eight pairs of potential dangerous drugs that lead to a higher rate of deadly heart conditions. The combined medications deemed the most dangerous consisted of ceftriaxone and lansoprazole, a heartburn medication more commonly known as Prevacid.

Alone, the medications do not lead to heart-related risks. But together, they were found to affect the electoral activity in the heart. Together, they can lead to the development of long QT syndrome, when the heart rhythm is effected and may cause sudden death, and are 1.4 times more likely to have an extended QT interval.

"What's most surprising is that you can go from a database of billions of data points to making a prediction that two molecules together can change the functions of a protein in a single heart cell," said Nicholas Tatonetti, PhD, assistant professor of biomedical informatics at Columbia University Medical Center and a member of Columbia's Data Science Institute. "It means these algorithms are really useful in medical research."

The U.S. Food and Drug Administration has been informed of these findings in the hope that further testing on combining ceftriaxone lansoprazole with three other potentially dangerous medications.

"Drug interactions occur often, but they often go unrecognized, and we have needed better methods of detection," said Raymond Woosley, MD, PhD, a national expert on drug-induced long QT syndrome and founding president of ACZERT, an Arizona nonprofit organization focused on drug safety.