Computer AI trained to spot if you’ll have heart attack in the next year

By Mark Waghorn via SWNS

A computer has been trained to spot whether someone will have a heart attack in the next year, from routine eye tests.

The AI (artificial intelligence) system opens the door to a cheap and simple screening program for the world's number one killer.

It predicts patients at risk of a heart attack in the next 12 months - and is up to 80 percent accurate.

The breakthrough adds to evidence our peepers are windows into overall health.

Project supervisor Professor Alex Frangi, of the University of Leeds, said: "Cardiovascular diseases, including heart attacks, are the leading cause of early death worldwide and the second-largest killer in the UK.

"This causes chronic ill-health and misery worldwide. This technique opens up the possibility of revolutionizing the screening of cardiac disease.

"Retinal scans are comparatively cheap and routinely used in many optician practices.

"As a result of automated screening, patients who are at high risk of becoming ill could be referred to specialist cardiac services.

"The scans could also be used to track the early signs of heart disease."

The retina is a small membrane at the back of the eye containing light-sensitive cells.

Doctors have recognized changes to the tiny blood vessels suggest vascular disease - including heart problems.

An advanced type of AI known as 'deep learning' was used to 'teach' the machine to automatically read more than 5,000 scans.

They were taken during visits to opticians' or eye clinics. Participants were members of the UK Biobank which is tracking the health of half a million Britons.

Deep learning is a complex series of algorithms that enable machines to make forecasts based on patterns in data.

The technique described in the journal Nature Machine Intelligence could revolutionize heart therapy, say the international team.

It was correct 70 to 80 percent of the time - offering hope of a second referral mechanism for in-depth cardiovascular investigation.

Co-author Professor Chris Gale, a consultant cardiologist at Leeds Teaching Hospitals NHS Trust, said: “The AI system has the potential to identify individuals attending routine eye screening who are at higher future risk of cardiovascular disease, whereby preventative treatments could be started earlier to prevent premature cardiovascular disease."

It identified associations between pathology in the retina and changes in the patient's heart.

Once the image patterns were learned, the AI system could estimate the size and pumping efficiency of the left ventricle from retinal scans alone.

This is one of the heart's four chambers. An enlarged ventricle is linked with an increased risk of heart disease.

The computer combined the estimated size of the left ventricle and its pumping efficiency with basic demographic data like age and sex.

Currently, such information is determined with MRI (magnetic resonance imaging) or echocardiography scans of the heart.

The diagnostic tests are expensive and are often only available in a hospital.

They are inaccessible for people in countries with less well-resourced healthcare systems.

They also increase healthcare costs and waiting times in wealthy nations.

Co-author Sven Plein, of the British Heart Foundation who is professor of cardiovascular imaging at Leeds said: "The AI system is an excellent tool for unraveling the complex patterns that exist in nature.

"That is what we have found here – the intricate pattern of changes in the retina linked to changes in the heart."

Last week a similar study by an Australian-led team identified a link between biological aging of the retina and mortality.

Those whose retina was 'older' than their actual years were up to 67 percent more likely to die over the next decade.

The analysis was based on almost 47,000 members of the UK Biobank aged 40 to 69.

Cardiovascular disease claims 17 million lives a year - including 160,000 in the UK.