• Posted October 29, 2024

AI Might Help Pick Up Heart Trouble in Dogs

Artificial intelligence can accurately detect heart murmurs in dogs, a new study finds.

The AI program detects heart murmurs in canines with 90% accuracy, similar to the accuracy of expert cardiologists, researchers report.

And in more than half the cases tested, the AI completely agreed with a cardiologist’s assessment of the murmur’s seriousness.

These heart murmurs are a key indicator of heart valve disease, the most common heart condition in adult dogs, researchers said.

About 1 in every 30 dogs seen by a vet has a heart murmur, researchers said in background notes. The condition is higher in small breed dogs and older dogs.

Early detection is crucial, as timely medication can extend their lives, researchers said.

“Heart disease in humans is a huge health issue, but in dogs it’s an even bigger problem,” said lead investigator Andrew McDonald, a research associate in stethoscope acoustics with the University of Cambridge Department of Engineering. “Most smaller dog breeds will have heart disease when they get older, but obviously dogs can’t communicate in the same way that humans can, so it’s up to primary care vets to detect heart disease early enough so it can be treated.”

For the study, researchers started with a database of heart sounds gathered from about 1,000 patients using a digital stethoscope. They developed an AI program to check for heart murmur, then adapted it so it could be used on dogs.

“As far as we’re aware, there are no existing databases of heart sounds in dogs, which is why we started out with a database of heart sounds in humans,” said researcher Anurag Agarwal, a professor of acoustics and biomedical technology at the University of Cambridge. “Mammalian hearts are fairly similar, and when things go wrong, they tend to go wrong in similar ways.”

The team then tested the AI on nearly 800 dogs undergoing routine heart exams at four vet clinics in the U.K.

“Mitral valve disease mainly affects smaller dogs, but to test and improve our algorithm, we wanted to get data from dogs of all shapes, sizes and ages,” explained researcher Dr. Jose Novo Matos, a teaching professor of small animal cardiology with Cambridge’s Department of Veterinary Medicine. “The more data we have to train it, the more useful our algorithm will be, both for vets and for dog owners.”

The researchers fine-tuned the AI so it could detect and grade heart murmurs based on digital recordings, differentiating between murmurs caused by mild heart disease and those stemming from advanced disease.

The AI agreed with an expert cardiologist’s assessment in more than half of the cases tested, researchers report. About 90% of the time, the AI’s judgment was within a single grade of the cardiologist’s judgment.

The new study was published Oct. 28 in the Journal of Veterinary Internal Medicine.

“The grade of heart murmur is a useful differentiator for determining next steps and treatments, and we’ve automated that process,” McDonald said in a Cambridge news release. “For vets and nurses without as much stethoscope skill, and even those who are incredibly skilled with a stethoscope, we believe this algorithm could be a highly valuable tool.”

There are drugs available to help dogs with heart valve disease, whereas in humans the only available treatment is surgery, the researchers noted.

“Knowing when to medicate is so important, in order to give dogs the best quality of life possible for as long as possible,” Agarwal said. “We want to empower vets to help make those decisions.”

“So many people talk about AI as a threat to jobs, but for me, I see it as a tool that will make me a better cardiologist,” Novo Matos said. “We can’t perform heart scans on every dog in this country -- we just don’t have enough time or specialists to screen every dog with a murmur. But tools like these could help vets and owners, so we can quickly identify those dogs who are most in need of treatment.”

More information

The American Kennel Club has more about heart disease in dogs.

SOURCE: University of Cambridge, news release, Oct. 28, 2024