AI-Powered Eye Scans Could Predict Heart Attack and Stroke Risk

Eye scan can reveal risk of having a heart attack or stroke

A simple digital photograph of the back of the eye can predict a major cardiovascular event -- such as a heart attack or stroke -- set to happen in the next decade with 70% accuracy, according to research supported by the British Heart Foundation and the National Institute for Health and Care Research (NIHR). Researchers believe the routine retinal scans could also be used to track people's heart health over time, as they also found links between someone's three-year change in risk score and their odds of a major cardiovascular event. The eye scan is analyzed using AI, which takes just a fraction of a second to produce a personalized risk prediction. People at the highest risk could be referred to a GP, who might end up prescribing blood pressure tablets or statins to lower their cholesterol. In the future, researchers hope anyone getting an eye test could get an alert on their heart health pinged to their smartphone. Dr. Ify Mordi, British Heart Foundation Research Fellow at the University of Dundee and consultant cardiologist, led the study published in the journal Cardiovascular Diabetology. He said, "It may be surprising, but the eyes are a window to the heart. "If there is damage or narrowing of the blood vessels at the back of the eye, there is a good chance that will also be seen in the blood vessels further inside the body, supplying the heart, which could lead to a heart attack or stroke. "This is a one-stop scan which is routinely performed and takes less than a minute. It could be an important part of the package, alongside blood pressure and cholesterol checks, in identifying people who could benefit from medication or lifestyle changes." Researchers at the University of Dundee developed AI technology to analyze digital retinal photographs, which are usually part of a routine eye test on the high street. First, the AI was instructed to look for red flags such as blood vessel narrowing, blockages and damage, which could be signs of impending heart problems. Then a "black box" approach was taken, allowing the technology to use machine deep-learning to search for any detail it chose in the images, which could range from the size to the arrangement of blood vessels. After being trained on around 4,200 images, the black box AI was judged on how well the technology could predict those people who went on to have a heart attack or stroke, or die from cardiovascular disease -- also usually a heart attack or stroke -- in the next decade. The team found that black box AI predicted 70% of these cases when tested on eye scans from more than 1,200 people. Some of these people had also undergone a second scan, three years after their first. When the researchers analyzed how risk scores identified by AI changed between the scans, they found the fifth of this group with the largest increase in their risk score had a 54% higher risk of a major cardiovascular event than the rest of the group. This 54% higher risk was seen in people whose AI score increased by as little as 3% in three years -- for example whose 10-year risk of a cardiovascular event rose from 20% to 23%. The team also compared the AI technology to the prediction people get currently from routine health checks with their GP -- their "cardiovascular risk score" -- which provides a percentage risk of someone suffering a major cardiac event in the next decade, based on factors like their age, sex, blood pressure reading, cholesterol level and whether they smoke. Researchers found that the risk score and retinal scan identified almost exactly the same proportion of people at risk of a heart attack, stroke or death from cardiovascular disease. When both a clinical risk score, the retinal scan and a further genetic test were combined, the accuracy rose to 73%. That means the three together could potentially identify an extra three people in every 100 people at risk of a heart attack, stroke or death from cardiovascular disease. The AI tool was trialed in the study on people with diabetes, as they get routine retinal scans on the NHS to check for complications affecting the eyes. But researchers say analysis of blood vessels in the eye to judge cardiovascular risk should work for most people, and not just those with diabetes. The study was a collaboration between clinical researchers who trialed the technology, including Dr. Mordi and Dr. Alex Doney, at the University of Dundee, alongside computer scientists who developed the AI technology, led by the university's Professor Emanuele Trucco and Dr. Mohammad Syed. Professor Bryan Williams OBE, chief scientific and medical officer at the British Heart Foundation said, "The more accurately we can detect someone's risk of a heart attack or stroke, the better the opportunities to prevent these happening. "Cutting-edge innovations, like the use of retinal scans alongside health checks, could play a role in improving risk prediction, which is important if we are to reach the British Heart Foundation's goal to prevent 125,000 heart attacks and strokes in the UK by 2035. "However, more research is needed to show this prediction accuracy is robust, and to determine the feasibility of incorporating retinal scans into clinical practice."

High street eye test could predict heart attack risk

High street eye scans could be used to predict heart attack risk, a study has found. A new artificial intelligence tool could predict a person's risk of suffering a heart attack or stroke within the next 10 years just from analysing a routine eye test. Researchers from the University of Dundee used AI to examine digital retinal photographs, which capture images of the back of the eye. The software has learnt to detect abnormalities or patterns in the size and arrangement of the blood vessels that would suggest an increased risk of developing a heart condition. The experts said it could now predict the likelihood of someone going on to suffer a "major cardiovascular event", such as a heart attack or stroke, within the next 10 years to 70 per cent accuracy. They hope the test could one day be offered alongside blood pressure and cholesterol checks to allow doctors to identify and treat patients at risk of heart issues sooner.. People with type 2 diabetes For the study, the research team trialled the AI software on the eye scans of people with type 2 diabetes. Diabetes patients have regular eye tests to check for diabetic retinopathy, a condition where high blood sugar levels damage the blood vessels in the retina and lead to sight loss. Dr Ify Mordi, a British Heart Foundation (BHF) research fellow at the University of Dundee and consultant cardiologist, said: "It may be surprising but the eyes are a window to the heart. "If there is damage or narrowing of the blood vessels at the back of the eye, there is a good chance that it will also be seen in the blood vessels further inside the body, supplying the heart, which could lead to a heart attack or stroke." Dr Mordi added: "This is a one-stop scan which is routinely performed and takes less than a minute. "It could be an important part of the package, alongside blood pressure and cholesterol checks, in identifying people who could benefit from medication or lifestyle changes." Professor Bryan Williams, chief scientific and medical officer at the BHF, said: "The more accurately we can detect someone's risk of a heart attack or stroke, the better the opportunities to prevent these happening. "Cutting-edge innovations, like the use of retinal scans alongside health checks, could play a role in improving risk prediction, which is important if we are to reach the British Heart Foundation's goal to prevent 125,000 heart attacks and strokes in the UK by 2035. "However, more research is needed to show this prediction accuracy is robust, and to determine the feasibility of incorporating retinal scans into clinical practice." The study was published in the journal Cardiovascular Diabetology.

Routine eye scan 'could predict 10-year heart attack and stroke risk', University of Dundee study suggests

A scan which forms part of a routine eye test could help predict a person's risk of having a heart attack or stroke within the next 10 years, a study has suggested. Researchers at the University of Dundee used artificial intelligence (AI) to analyse digital retinal photographs, which are taken to capture images from the back of the eye to look for certain conditions. The technology was able to produce personalised risk predictors in less than a second. It is hoped the simple test could one day be offered alongside blood pressure and cholesterol checks to allow doctors to treat patients earlier. For the study, published in the journal Cardiovascular Diabetology, researchers trialled the AI software on the eye scans of people with type 2 diabetes. Those with the condition undergo routine eye tests to check for diabetic retinopathy, a condition where high blood sugar levels damage the blood sugar in the retina. Dr Ify Mordi, British Heart Foundation (BHF) research fellow at the university and consultant cardiologist, said: "It may be surprising, but the eyes are a window to the heart. "If there is damage or narrowing of the blood vessels at the back of the eye, there is a good chance that will also be seen in the blood vessels further inside the body, supplying the heart, which could lead to a heart attack or stroke." The AI tool was instructed to initially look for warning signs on the images, such as blood vessel narrowing or blockages. It was then permitted to look for any detail in the photographs, such as the size or arrangement of blood vessels, before being trained using 4,200 images. The technology was able to predict the people who would go on to have "major cardiovascular events", like heart attacks or strokes, within a decade with 70% accuracy. Dr Mordi said: "This is a one-stop scan which is routinely performed and takes less than a minute. "It could be an important part of the package, alongside blood pressure and cholesterol checks, in identifying people who could benefit from medication or lifestyle changes." Read more from Sky News: 'My voice box was removed after NHS missed my throat cancer' World's biggest human imaging project reaches new milestone Professor Bryan Williams, chief scientific and medical officer at the BHF, said cutting-edge innovations like the AI tool could "play a role in improving risk prediction". He added: "However, more research is needed to show this prediction accuracy is robust, and to determine the feasibility of incorporating retinal scans into clinical practice." Dr Clare Jonas, research lead at the Stroke Association, agreed that AI analyses of health data "have exciting potential for better early detection". She added: "Advances like these could make it easier for people at risk of stroke to take the right steps to stop it from happening. "Whilst there are still many practical questions to answer about whether, when and how AI could be used in clinical practice, we hope the government's 10 Year Health Plan will take such technological advances into account to stop more strokes from devastating people's lives."