Your data on MRCVSonline
The nature of the services provided by Vision Media means that we might obtain certain information about you.
Please read our Data Protection and Privacy Policy for details.

In addition, (with your consent) some parts of our website may store a 'cookie' in your browser for the purposes of
functionality or performance monitoring.
Click here to manage your settings.
If you would like to forward this story on to a friend, simply fill in the form below and click send.

Your friend's email:
Your email:
Your name:
 
 
Send Cancel

Scientists use AI to detect and grade canine heart murmurs
Smaller breeds such as King Charles spaniels at more at risk of mitral valve disease.
Researchers hope technology could help spot early signs of disease.

Scientists have used machine learning to develop an algorithm that can accurately detect and grade heart murmurs in dogs.

Tests showed that the algorithm had a sensitivity of around 90 per cent, which is a similar level of accuracy as an expert cardiologist.

An estimated one in 30 dogs seen by a veterinary surgeon has a heart murmur, which is a key sign of mitral valve disease. The technology could aid early detection.

The team, led by researchers from the University of Cambridge, adapted an algorithm that had originally been designed for humans using a database of heart sounds from around 1,000 human patients.

Anurag Agarwal, professor of acoustics and biomedical technology at the University of Cambridge, explained: “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.

“Mammalian hearts are fairly similar, and when things go wrong, they tend to go wrong in similar ways.”

To train the technology to work on dogs, the researchers gathered data from almost 800 dogs that had undergone routine heart examinations at four specialist centres in the UK. Although smaller breeds, such as King Charles spaniels, are most at risk of mitral valve disease, the data set included a wide range of dogs to improve the quality of the algorithm.

Each dog underwent a full physical examination and an echocardiogram. Heart sounds were recorded using an electronic stethoscope.

Using this data, the researchers fine-tuned the algorithm so that it could detect and grade heart murmurs and tell the difference between murmurs linked to mild disease and those which indicated advanced disease needing further treatment.

Jose Novo Matos, principal clinical cardiologist at the University of Cambridge’s Department of Veterinary Medicine, said: “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.

“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.”

The study has been published in the Journal of Veterinary Internal Medicine.

Image © Shutterstock

Become a member or log in to add this story to your CPD history

Two new roles on BEVA Nurse Committee

News Story 1
 The BEVA has opened two new roles on its Nurse Committee.

There is one role available for a full member (for three years) and one role for a student member (until they qualify).

Members must attend all meetings, occurring four times a year. They will assist the committee in understanding the field, identifying issues and engaging with external parties.

More details can be found here

Click here for more...
News Shorts
BSAVA publishes Guide to Nutrition in Small Animal Practice

The BSAVA has added a small animal nutrition advice booklet to its series of BSAVA guides.

The BSAVA Guide to Nutrition in Small Animal Practice offers a resource for veterinary professionals to provide appropriate nutrition for animals. As well as maintaining the wellbeing of healthy pets, the guide explores how nutritional requirements change in times of illness and disease.

The guide is divided into five sections, which explore the importance of nutritional assessment; diet types; feeding at different life stages; feeding for specific situations; and feeding for specific diseases. Online resources are also in the BSAVA Library including client handouts and videos.

It is designed to be suitable for referencing, in-depth case planning and team training sessions.

The BSAVA Guide to Nutrition in Small Animal Practice can be purchased online from the BSAVA store.