Gaithersburg, MD — Recently developed synthetic intelligence software program can decide whether or not firefighters may be about to expertise a doubtlessly deadly cardiac occasion.
That’s what a workforce of researchers from the National Institute of Standards and Technology, the University of Rochester, and Google contend in a report that particulars their machine-learning mannequin.
Using AI expertise and current electrocardiogram information for 112 firefighters, the researchers created the Heart Health Monitoring, or H2M, mannequin.
Individual heartbeats from the EKGs have been labeled both as regular or irregular, with the latter probably indicating irregular coronary heart rhythms. Such rhythms can immediate the center to cease pumping blood, usually due to a coronary heart assault, and set off sudden cardiac arrest – the main explanation for on-the-job dying among firefighters.
The H2M mannequin appropriately recognized irregular EKG samples with almost 97% accuracy.
In a press launch, NIST researcher Chris Brown says sudden cardiac occasions “are by far the No. 1 killer of firefighters.” The launch notes that about 40% of on-duty fatalities may be attributed to sudden cardiac arrest occasions, which “kill on-duty firefighters at twice the rate of police officers and four times the rate of other emergency responders.”
The researchers say they hope the mannequin finally can be utilized in a conveyable coronary heart monitor that firefighters may put on whereas on the job.
“This technology can save lives,” NIST researcher Wai Cheong Tam stated within the launch. “It could benefit not only firefighters, but other first responders and additional populations in the general public.”
The analysis was revealed on-line within the Fire Safety Journal.
