Dr Miriam Stoppard shares exciting research from Imperial College London that offers a glimpse into how AI could improve the diagnosis of heart disease.

Artificial Intelligence is revolutionising medical research with new discoveries, not least those revealing the secrets of ECGs (electrocardiograms) that our eyes can’t see.

And in doing so AI can predict the risk of developing heart disease, and even the risk of early death.

Now that’s a giant step forward as it would enable doctors to track disease earlier and prioritise the most urgent cases for treatment.

What does an ECG do? It records the electrical activity of the heart and spots abnormalities.

It’s one of the most common medical tests we can have and experts now believe that AI could improve its efficiency incredibly.

To show how, a team from Imperial College London has trained an AI model to work on millions of ECGs previously taken as part of routine care, in a bid to accurately predict which patients went on to experience new disease, worse disease, or who subsequently died.

The AI model was trained to ‘read’ ECGs to see patterns in the electrical signals better than a cardiologist. Imperial’s research lead, Dr Arunashis Sau explains: “The AI model detects much more subtle detail, so it can spot problems in ECGs that would appear normal to us, and potentially long before the disease develops fully.”

The model – known as AIRE – was able to identify the risk of death in 78% of cases. The system can predict, with a high level of accuracy, future health risks such as heart rhythm problems, heart attacks and heart failure, as well as when someone would die from a non-heart related cause.

Dr Sau further adds: “Our analysis shows the AI can tell us a lot about not only the heart but also what is going on elsewhere in the body and it may be able to detect accelerated ageing.”

The senior author, Imperial’s Dr Fu Siong Ng believes their work “could have a positive impact on how patients are treated, and ultimately improve patient longevity and quality of life.

“It could also reduce waiting lists and allow more efficient allocation of resources. We believe this could have major benefits for the NHS, and globally.”

Professor Bryan Williams of the British Heart Foundation, which funded the research, says: “This large, exciting study offers a glimpse into how AI could be used to improve diagnosis of heart disease.

“This could take the use of ECGs beyond what has previously been possible, by helping assess risk of future heart and health problems, as well as risk of death.”

Dr Sau concludes: “It’s a possibility that we could see patients provided with wearable technology that provides doctors with continuous remote monitoring and a potential alert system.”

Share.
Exit mobile version