Researchers led by the University of Cambridge have developed a groundbreaking AI algorithm that accurately detects heart murmurs in dogs, potentially revolutionizing early diagnosis and treatment of canine heart disease.
A team of researchers led by the University of Cambridge has developed a cutting-edge machine learning algorithm capable of accurately detecting heart murmurs in dogs. These murmurs are significant indicators of mitral valve disease and other cardiac conditions, which are particularly prevalent in small breeds like King Charles Spaniels.
“Heart disease in humans is a huge health issue, but in dogs, it’s an even bigger problem,” first author Andrew McDonald, a research associate at Cambridge’s Department of Engineering, said in a news release.
The newly-developed AI algorithm, initially designed to detect heart conditions in humans, was adapted and fine-tuned to interpret audio recordings from digital stethoscopes used on dogs. This remarkable innovation demonstrated a 90% sensitivity in detecting heart murmurs, aligning closely with the accuracy achieved by expert cardiologists.
Heart murmurs are a fundamental symptom of mitral valve disease, the most common heart condition in adult dogs. Early detection of this disease can lead to timely medication that significantly extends a dog’s life.
The significance of this research is underlined by the fact that one in 30 dogs visiting a veterinarian has a heart murmur, with the prevalence being higher in older and smaller dogs.
“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,” McDonald added.
The researchers amassed data from nearly 800 dogs undergoing routine heart examinations across four veterinary specialist centers in the UK. Full physical examinations and heart scans (echocardiograms) were performed by cardiologists to identify heart murmurs and diseases, creating the largest dataset of dog heart sounds ever compiled.
The algorithm’s performance was promising, agreeing with cardiologists’ assessments in over half of the cases and within a single grade of accuracy in 90% of cases. Variations in heart murmur grading among different veterinarians make this consistency particularly significant.
“We want to empower general practitioners to detect heart disease and assess its severity to help owners make the best decisions for their dogs,” co-author Jose Novo Matos, a professor of veterinary medicine at Cambridge, said in the news release.
Moreover, the algorithm can differentiate between murmurs associated with mild disease and those indicating advanced heart conditions requiring further treatment. This capability can potentially transform the way primary care veterinarians screen for heart diseases in dogs, offering a cost-effective and efficient diagnostic tool.
“Knowing when to medicate is so important, in order to give dogs the best quality of life possible for as long as possible,” added lead author Anurag Agarwal, a professor of acoustics and biomedical technology at Cambridge.
The detailed findings of this research have been published in the Journal of Veterinary Internal Medicine.
“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 added.
This breakthrough holds the potential to significantly enhance the health and lifespan of countless dogs, empowering veterinarians to diagnose and treat heart diseases earlier and more effectively.