A new study published in the journal BMJ today claims that your eyes can potentially predict the possibility of developing heart disease.

The team discovered that the network of veins and arteries in the retina can reliably predict cardiovascular disease and death without the use of blood tests or blood pressure readings.

Allows for accurate non-invasive screening tests that do not need to be performed in a clinic.

Findings from a study published online in the British Journal of Ophthalmology show that AI-enabled imaging of the retina’s network of veins and arteries can effectively predict cardiovascular illness and death without the need for blood tests or blood pressure measurements.

Circulatory illnesses, which include cardiovascular disease, coronary heart disease, heart failure, and stroke, are major causes of ill health and mortality all over the world. In the United Kingdom alone, circulatory disorders are responsible for one in every four deaths.

Although there are a number of risk frameworks, the researchers claim that they are not always reliable in predicting who would eventually develop or face death from circulatory disorders.

According to previously published research, the size of the retina’s microscopic arteries and veins (called arterioles and venules), which collects and organizes visual information, may serve as a reliable early indicator of cardiovascular disease.

However, it’s unclear if these conclusions hold true consistently and equally for men and women.

In order to create models to evaluate the potential of retinal vasculature imaging combined with known risk factors to predict vascular health and death, the researchers created a fully automated artificial intelligence (AI)-enabled algorithm called QUANTitative Analysis of Retinal vessels Topology and siZe, or QUARTZ for short.

They used QUARTZ to analyze the width, vascular area, and degree of tortuosity (curvature) of the arterioles and venules in the retina of 88,052 UK Biobank participants aged 40 to 69 in order to create prediction models for stroke, heart attack, and mortality from circulatory disease.

After that, they used the models on retinal scans from 7411 people aged 48 to 92 who took part in the European Prospective Investigation into Cancer (EPIC)-Norfolk research.

Both individually and collectively, the effectiveness of QUARTZ was compared to the widely utilized Framingham Risk Scores system.

During the average follow-up period of 7 to 9 years, 327 people with circulatory illness died among the 64,144 UK Biobank participants (average age 56), while 201 people with circulatory disease died among the 5862 EPIC-Norfolk participants (average age 67).

It was found that the width of the arteriolar and venular walls, as well as their tortuosity and variation in width, were strong predictors of death from cardiovascular disease in men. In women, the area and width of the arteries and veins, as well as the shape and width of the veins, helped predict the risk.

The prognostic influence of retinal vasculature on circulatory disease mortality interacted with smoking, hypertension medications, and a prior heart attack.

Overall, between half and two thirds of fatalities from circulatory illness in individuals most at risk were predicted by these predictive models, which were based on age, smoking, medical history, and retinal vasculature.

Additionally, retinal vasculature models identified 3% more incidences of stroke in the EPIC-Norfolk men most at risk, 5% more cases in the UK Biobank women, and approximately 2% fewer cases in the EPIC-Norfolk men. Additionally, among those who were most at risk, Framingham Risk Scores detected more occurrences of heart attacks.

Only minor adjustments were made to the Framingham Risk Scores to better predict stroke and heart attack risk. However, the researchers claim that a less complex non-invasive risk score based on age, sex, smoking, medical history, and retinal vasculature outperformed the Framingham Risk Scores while requiring neither blood tests nor blood pressure measurements.

They recognize that both research groups have healthier lifestyles than other middle-aged adults in similar geographic areas, of whom the majority are White. However, they note that this is the largest population-based investigation of retinal vasculature and that a sizable percentage of patients underwent external validation of the prediction models.

The researchers note that retinal imaging is already a standard procedure in the US and the UK. They conclude that “AI-enabled vasculometry risk prediction is fully automated, low cost, non-invasive, and has the potential to reach a higher proportion of the population in the community because of ‘high street’ availability and because blood sampling or [blood pressure measurement] are not needed.”

According to them,  “[Retinal vasculature]is a microvascular marker, hence offers better prediction for circulatory mortality and stroke compared with [heart attack] which is more macrovascular, except perhaps in women.

“In the general population it could be used as a non-contact form of systemic vascular health check, to triage those at medium-high risk of circulatory mortality for further clinical risk assessment and appropriate intervention.”

They propose that it might be incorporated into the primary care NHS Health Check for people ages 41 to 74 in the UK.

Drs. Ify Mordi and Emanuele Trucco of the University of Dundee in Scotland write in a related editorial that although the use of alterations in the retinal vasculature to assess overall cardiovascular risk is “certainly attractive and intuitive,” it has not yet reached clinical practice.

They speculate that this method of retinal screening “would presumably require a significant increase in the number of ophthalmologists or otherwise trained assessors,” and they ask as to which specialty would be in charge of the additional workload and preventive care: ophthalmologists, cardiologists, or primary care practitioners.

The authors write that “what is now needed is for ophthalmologists, cardiologists, primary care physicians, and computer scientists to work together to design studies to determine whether using this information improves clinical outcome, and if so, to work with regulatory bodies, scientific societies, and healthcare systems to improve clinical workflows and enable practical implementation in routine practice.”

Source: 10.1136/bjophthalmol-2022-321842

Image Credit: Getty

You were reading: Something in Your Eyes Could Reveal if You’re at Risk of Heart Disease or Early Death, New Study Shows