When it comes to our canine companions, their health matters to us just as much as our own. We often wish they could tell us when something is not right. But what if there was a way to listen to what dogs cannot say?
Researchers at the University of Cambridge have developed a machine learning algorithm that can accurately detect heart murmurs – a key indicator of cardiac disease in dogs.
A regular feature in small breeds like King Charles Spaniels, cardiac disease is a serious issue that can significantly affect a dog’s quality of life.
“Heart disease in humans is a huge health issue, but in dogs it’s an even bigger problem,” said first author Dr. Andrew McDonald from Cambridge’s 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.”
The solution? Technology that can. The team at Cambridge adapted an algorithm initially created for humans to effectively detect and grade heart murmurs in dogs.
And the results are astonishing. With a sensitivity accuracy of 90%, the algorithm performs at par with expert cardiologists. So how does this actually work?
At the core of this technology is a machine learning algorithm fine-tuned to replicate whether a heart murmur has been detected by a cardiologist.
Initially created with a database of heart sounds from about 1,000 human patients, the algorithm was then adapted to be compatible with heart sounds from dogs.
The data for this adaptation came from nearly 800 dogs who underwent routine heart examinations at four veterinary specialist centers in the UK.
The ultimate goal? To make the innovative algorithm capable of distinguishing between murmurs associated with mild disease and those indicating advanced heart disease that requires further treatment.
Professor Anurag Agarwal, who led the research, is a specialist in acoustics and bioengineering.
“Knowing when to medicate is so important, in order to give dogs the best quality of life possible for as long as possible,” said Professor Agarwal. “We want to empower vets to help make those decisions.”
And it is not just the vets who will benefit. For dog owners, this technology could hold the key to extending their beloved pet’s life with timely diagnosis and treatment.
“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,” noted study co-author Jose Novo Matos.
“But tools like these could help vets and owners, so we can quickly identify those dogs who are most in need of treatment.”
Artificial intelligence (AI) is proving to be a transformative force in veterinary medicine, offering solutions that were deemed improbable not long ago.
By bridging the communication gap between human caregivers and canine patients, AI technologies like the heart murmur algorithm not only enhance diagnostic precision but also expedite the decision-making process in clinical settings.
This confluence of advanced technology and veterinary care illustrates the vast potential AI holds in revolutionizing animal healthcare.
With further research and development, similar algorithms could emerge, specializing in detecting other common ailments in dogs, promising a new era of comprehensive and personalized vet care.
Looking ahead, the journey from academic research to practical applications in veterinary clinics highlights the importance of collaboration across disciplines.
The partnership between engineers, veterinary experts, and technology developers underscores a collective commitment to improving animal welfare.
Continued collaboration is vital to refine and expand diagnostic tools that leverage machine learning, ensuring veterinarians are well-equipped to face the challenges of modern pet healthcare.
As innovations like these continue to evolve, they pave the way for a more integrated approach to managing and enhancing the longevity of dogs beyond heart health, ultimately fostering a deeper human-dog connection.
The results not only present a promising future in canine cardiology but also set the stage for how machine learning can benefit healthcare beyond humans.
As we continue to explore the possibilities of machine learning, this study reaffirms our belief that technology, when used well, is not a threat but a tool.
“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,” said Novo Matos.
The research was supported in part by the Kennel Club Charitable Trust, the Medical Research Council, and Emmanuel College Cambridge.
The study is published in the Journal of Veterinary Internal Medicine.
—–
Like what you read? Subscribe to our newsletter for engaging articles, exclusive content, and the latest updates.
Check us out on EarthSnap, a free app brought to you by Eric Ralls and Earth.com.
—–
