Computational linguistics saving lives

Grzegorz Kondrak of the University of Alberta has developed a way to use computational linguistics data in an AI system that spots drug names that are too much alike.

The FDA is using his system to evaluate new drug names by comparing them to existing ones. By ensuring more unique drug names medical errors due to confusing similar-sounding and similar-looking names can be reduced. In the USA that's as many as 162,500 deaths a year that could be prevented.

Kondrak originally developed the software to find similarities in words for language history comparisons, and says it was criticized as having no practical application at the time. A recent article in Artificial Intelligence in Medicine proves otherwise.

A noble scientist, he adds that he makes his research openly available.

"If anyone asks for it, I just give it to them," Kondrak said. "I was a funded researcher, and I look at it as my responsibility to share what I've learned and what I've done."

"When you do basic research sometimes you don't know how it might become of use, but if this software helps to reduce even just 10 per cent of prescription errors in the U.S. that translates into helping a lot of people, and it's very satisfying to contribute to that."