Lard disease is the first cause of death in the world, the second in France after cancer. Health conditions like obesity or diabetes increase the risk of developing heart disease, and blood tests or blood pressure measurements can provide a better estimate of a person’s likelihood of having heart problems. There may soon be an even easier way to predict heart disease risk: by scanning your eye.
A study published this month (link below) describes a quick and affordable cardiovascular screening method using imaging of the retinal vasculature, i.e. a picture of the blood vessels in the back of the eye . A snapshot of the eye is analyzed by artificial intelligence software developed for this purpose. Patients wouldn’t even need to go to their doctor’s office to get tested, all they would have to do is send in an image of their eye.
The team of several English university researchers, including St George’s, University of London, who developed the software highlighted its convenience and affordability compared to existing methods.
According to the researchers, in their study:
AI vasculometric risk prediction is fully automated, low-cost, non-invasive, and has the potential to reach a larger portion of the population in the community, as it is available on the street and there is no need to taking blood samples or measuring blood pressure.
The retina is the tissue at the back of the eye that converts light into electrical impulses, which it sends to the brain through the optic nerve. It contains millions of cells called rods (for night vision) and cones (for color vision), which depend on a network of blood vessels to constantly supply them with nutrients and oxygen.
Besides keeping the retina working, these blood vessels can also act as a “window” to other parts of the body, even the heart. Scientists have discovered a link between features such as the narrowness of the retinal arteries and the sinuosity/tortuosity of the vessels (their curvature), on the one hand, and high blood pressure, hypertension and cardiovascular disease, on the other hand. somewhere else.
Doctors have known for over a hundred years that you can look into your eye and see signs of diabetes and high blood pressure. But the problem was manual assessment: the manual delineation of vessels by human experts. An algorithm ofmachine learning doesn’t have as much trouble doing it though.
The team named their software QUARTZ, short for ” QUantitative Analysis of Retinal vessels Topology and siZe“. They trained the AI using images of the eyes of over 88,000 people (aged 40-69) from the UK Biobank. The team analyzed the width and twist of retinal arteries and veins to develop models for predicting strokes, heart attacks and death from circulatory disease.
They then used QUARTZ to analyze the retinal images of another 7,411 people, aged 48 to 92, and they combined this data with information about their health history (such as smoking, use of statins and previous heart attacks) to predict their risk of heart disease. Participants’ health was tracked for 7 to 9 years, and their results were compared to the predictions of the Framingham risk score (cardiovascular risk factor).
A common tool for estimating the risk of heart disease, this risk score takes into account age, sex, total cholesterol, cholesterol at high density lipoproteinssmoking habits, and systolic blood pressure to estimate a person’s likelihood of developing heart disease within a given time frame, usually 10 to 30 years.
The QUARTZ team compared their data to Framingham’s 10-year risk score predictions and reported that the accuracy of the algorithm was equivalent to that of the conventional tool.
It will take some time for AI to become a diagnostic tool, further clinical trials and regulatory approvals will be needed, as well as clearer methodology to translate its data into clinical practice.
In the meantime, it’s promising to know that tools like this are being developed. Like the Framingham risk assessments, QUARTZ could be used preventively by helping to determine when a person should take medication to lower their blood pressure or cholesterol levels.
An editorial related to the study, written by a doctor and a professor from the University of Dundee (UK) who was not involved in the study, is optimistic.
They write :
The retina is the only place that allows direct noninvasive visualization of the vasculature, potentially providing a rich source of information. The results reinforce evidence from several similar studies that the retina can be a useful and potentially disruptive source of information for cardiovascular disease risk in personalized medicine.
The study published in the British Journal of Ophthalmology: Artificial intelligence-enabled retinal vasculometry for prediction of circulatory mortality, myocardial infarction and stroke and the linked editorial: The eyes as a window to the heart: looking beyond the horizon.