AI–spectroscopy combo rats out fentanyl and its illicit kin
Researchers have developed an AI algorithm that can identify illegally cooked-up fentanyl, teaching itself to spot dangerous new impostors as it goes.
The system, which works with infrared light spectroscopy, has a future in law enforcement and the military, keeping personnel from handling these substances any more than they must.
In fact, the authors of the study describing the work, all from the University of Central Florida, report the AI system will power a device they’re building for the Defense Advanced Research Projects Agency.
“Fentanyl is a leading cause of drug overdose death in the U.S.,” lead author Mengyu Xu, PhD, points out in a news item posted at a school online outlet, UCF Today. “It and its derivatives have a low lethal dose and may lead to death of the user, could pose hazards for first responders and even be weaponized in an aerosol.”
In the study, Xu and colleagues trained the algorithm on a national database of organic molecules. They homed it in on molecules that have at least one characteristic in common with fentanyl itself, letting it learn how to spot those molecules from their infrared spectral properties.
Testing the AI/spectroscopy system, they found it achieved nearly 93% accuracy at the task.
The current research used infrared spectral data from gases, but the researchers are working on a similar study using machine learning for ferreting out fentanyl and its derivatives in powder form, UCF Today reports, adding that a final product may be ready in a matter of months.
Dave P. has worked in journalism, marketing and public relations for more than 30 years, frequently concentrating on hospitals, healthcare technology and Catholic communications. He has also specialized in fundraising communications, ghostwriting for CEOs of local, national and global charities, nonprofits and foundations.