Routine eye tests can flag up people at risk of suffering a heart attack
Why you really SHOULD go to Specsavers: Routine eye tests can flag up people at risk of suffering a heart attack in the next year, experts say
- Scientists trained an AI to examine routine eye scans for signs of heart disease
- Using UK eye scans the AI identified up to 80% of people who had a heart attack
- Researchers hope the can be used to help flag at risk heart patients to be treated
- An equivalent scan currently requires people to book an appointment at hospital
<!–
<!–
<!–
<!–
<!–
(function (src, d, tag){
var s = d.createElement(tag), prev = d.getElementsByTagName(tag)[0];
s.src = src;
prev.parentNode.insertBefore(s, prev);
}(“https://www.dailymail.co.uk/static/gunther/1.17.0/async_bundle–.js”, document, “script”));
<!–
DM.loadCSS(“https://www.dailymail.co.uk/static/gunther/gunther-2159/video_bundle–.css”);
<!–
A routine eye test at the opticians could be used to flag patients at risk of having a heart attack, a study suggests.
Scientists have developed an AI programme that can analyse routine eye scans for early warning signs of a heart problem.
It works by looking at changes to tiny blood vessels at the back of the eye, which evidence suggests contains key information on heart health.
Problems with blood circulation can cause cells in the retina to become damaged and die, leaving behind a permanent mark.
University of Leeds researchers were able to accurately identify patients who had a heart attack within a year with up to 80 per cent accuracy.
The study of 3,000 patients was published in the journal Nature Machine Intelligence.
Cardiovascular disease is the second largest killer in the UK, causing 160,000 deaths each year – an average of 460 fatalities a day. In the US, heart disease kills 659,000 people each year.
Scientists hope the AI could use routine eye scans taken at optometrists and raise the alarm if it spotted any signs of a heart problem
- How a simple eye scan could tell how likely you are to die… Simple eye test could detect early signs of heart disease,… Cataract surgery may cut the risk of developing dementia by… Men who worry lots in middle age at greater risk of heart…
What is the retina?
The retina is a layer of cells at the back of the eyeball opposite the pupil.
It is responsible for converting light which enters the eye into chemical messages.
These chemical messages are sent to the brain and interpreted as the images that form our sense of sight.
Previous studies have suggesting that taking scans of the retina is a good way to detect heart disease.
This is because poor circulation, a possible early indicator of heart disease, can cause parts of the retina to die, leaving a permanent mark.
Optometrists frequently look at the retinas of both eyes during a standard eye test looking for signs of other health problems.
Deeper and more specialised image scans of retinas are available at some UK optometrists but these are sometimes not included in a standard eye test.
Professor Alex Frangi, an expert in computational medicine at the University of Leeds, and who supervised the research, said this AI could revolutionise the detection of heart disease.
‘This technique opens-up the possibility of revolutionising the screening of cardiac disease,’ he said.
‘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 study also involved scientists from York, China, France, the US, and Belgium.
Scientists trained the AI by having it analyse the retinal scans of more than 5,000 Britons and then by having it associate signs of damage in the retina with changes in a patient’s heart.
The AI programme could then estimate the size and pumping efficacy of the left ventricle, one of the heart’s four chambers.
An enlarged or inefficient left ventricle indicator is an indicator of heart disease.
If it detected a concerning left ventricle, the AI could then use a patient’s basic medical data, such as their age and gender, to estimate their heart attack risk in the next year.
The AI’s results were cross referenced with historical patient data to see if they had suffered one.
Current technology means scanning the left ventricle requires one of two kinds of scan, an ultrasound called an echocardiography, or an MRI of the heart.
Both of these are expensive and can only be a carried out in hospital so developing other ways to assess heart health could save the NHS time and money.
The authors of the most recent study added that the AI system could also prove useful in countries that have extremely limited capacity for expensive heart scans.
People can mistake the classic symptoms of a heart attack, such as chest pain for another health problem, and in some cases can not have them at all.
Some studies put the number of heart attacks that go unnoticed as almost half while others estimate it as one in five.
In England people between 40-to-74 are invited to a general health check-up which includes some tests for heart disease every five years. Similar schemes are also in place in the other UK nations.
About 14million people in the UK are thought to be living with high blood pressure one of the key risk factors for a heart attack, with 5million of this group unaware they are at risk.
Comments 40
Share what you think
-
Newest -
Oldest -
Best rated -
Worst rated
The comments below have not been moderated.
The views expressed in the contents above are those of our users and do not necessarily reflect the views of MailOnline.
Close
Do you want to automatically post your MailOnline comments to your Facebook Timeline?
Your comment will be posted to MailOnline as usual.
Close
Do you want to automatically post your MailOnline comments to your Facebook Timeline?
Your comment will be posted to MailOnline as usual
We will automatically post your comment and a link to the news story to your Facebook timeline at the same time it is posted on MailOnline. To do this we will link your MailOnline account with your Facebook account. We’ll ask you to confirm this for your first post to Facebook.
You can choose on each post whether you would like it to be posted to Facebook. Your details from Facebook will be used to provide you with tailored content, marketing and ads in line with our Privacy Policy.