Running eye scans through AI algorithm ‘predicts risk of early death’
Scanning the inside of someone’s eye could predict the risk of premature death, a study suggests.
Scientists have developed an artificial intelligence program that can detect early warning signs of a heart problem.
It works by measuring the thickness of small arteries and veins at the back of the eye, which are thought to hold key information about heart health.
Problems with blood circulation can cause the blood vessels in the retina to thicken, eventually leading to vision loss without treatment.
In a study of 88,000 Britons, it was able to predict 54 percent of heart attack and stroke cases and 58 percent of heart disease deaths.
Doctors said the test offered an alternative that was “non-invasive” and could be used to monitor heart health during regular eye exams.
Heart disease is the leading cause of death in the United States, claiming a life every 34 seconds, or 690,000 people a year.
There are no guidelines on how often a person should be screened for heart disease.
But the Centers for Disease Control and Prevention recommends that everyone over the age of 20 be tested for high cholesterol, a predictor of heart disease, at least every five years.
They also recommend regular blood pressure tests and checks of blood glucose levels every three years.
How is your risk of heart disease measured?
Doctors today measure your risk for heart disease using a variety of factors.
These include taking into account your age, gender and underlying conditions such as smoking.
But they will also take a measurement of your blood pressure and a blood test to check your cholesterol levels.
The Centers for Disease Control and Prevention (CDC) say that Americans over the age of 20 should have their cholesterol checked every five years.
For those with an underlying risk factor, such as diabetes, they should be checked more often.
Testing is usually done based on age, gender, smoking, and blood pressure to determine heart disease risk. Doctors also check cholesterol levels, so they require a blood test.
The new method used images of the retinal vasculature, which photographs the back of the eye to show the blood vessels along with the optic nerve.
Doctors use it during eye tests to check for health problems, such as retinal degeneration and glaucoma, where the optic nerve is damaged.
They developed a computer program that can read the scans to take thousands of measurements of the width of blood vessels across the retina.
He then analyzes them to see if they have thickened.
The results are then used along with a person’s age, smoking status and medical history to estimate their risk of death from heart disease.
The results showed that in the British sample, the algorithm predicted 191 deaths from heart disease, but 327 were recorded (58 percent accuracy).
He also estimated that there would be 454 cases of stroke or heart attack in the group, and 839 (54 percent) were recorded.
Follow-up for the British sample was, on average, about seven years after the initial eye exam.
The algorithm was also tested in a separate group of 7,400 patients in Europe aged between 48 and 92 years.
It found 50 percent of the 201 recorded heart disease deaths and 48 percent of recorded strokes and heart attacks over a period of about nine years.
Dr. Alicja Rudnicka, an epidemiologist who led the paper, and others said it provided a “better prediction” of heart disease risk than current methods.
They added: ‘In the general population, it can be used as a non-contact form of systemic vascular health monitoring, to [move] those at medium-high risk… for further clinical risk assessment.’
In a linked editorial, Dr. Ify Mordi and Dr. Emanuele Trucco, doctors at the University of Dundee in Scotland, said the new method was “appealing” to use.
‘Using retinal screening in this way would presumably require a significant increase in the number of ophthalmologists or otherwise trained assessors,’ they suggest.
‘What is needed now is for ophthalmologists [and others] work together to design studies to determine if the use of this information improves clinical outcomes.’
The method, called Quantitative Analysis of Retinal Vessel Topology and Size (QUARTZ), was revealed in a study in the British Journal of Ophthalmology.
