The researchers found that combining information about the pattern of blood vessels in the retina with traditional clinical factors allowed them to better recognize participants’ risk of attack, compared to standard models that included only demographic data. A summary, to be presented at the annual conference of the European Society of Human Genetics in Vienna on Monday, describes in detail how they used data from the UK Biobank, which contains medical records and lifestyle records of 500,000 people, to calculate a measure called dimension fractal They then combined it into a model with factors such as age, gender, systolic blood pressure, body mass index and smoking status, studying people in the database who had suffered a heart attack – also known as a myocardial infarction or MI – after images of their retina. had gathered. Ana Villaplana-Velasco, PhD student at the Usher and Roslin Institutes at the University of Edinburgh and co-author of the presentation, said: when compared to standard models that include only demographic data. “The improvement in our model was even higher if we added a score related to the genetic tendency to develop MI.” The researchers said their analysis found that there was a common genetic basis between the fractal dimension and myocardial infarction. The average age for a heart attack is 60 and they found that their model achieved its best prognostic performance more than five years before the heart attack occurred. They hope that in the future, a simple retinal examination may be able to provide enough information to identify people at risk. “Calculating an individualized MI risk by people over the age of 50 seems appropriate,” said Villaplana-Velasco. “This would allow doctors to suggest behaviors that could reduce the risk, such as quitting smoking and maintaining normal cholesterol and blood pressure.” The researchers believe that it is possible that each disease may have a unique retinal variant profile and suggest that their findings may be useful in locating the tendency for other diseases. Villaplana-Velasco said they would like to repeat the analysis separately in men and women to investigate whether a specific model for gender infarction works for a better risk classification. Professor Sir Nilesh Samani, medical director at the British Heart Foundation, said: “More research is needed to show that this improvement in prognosis is strong. “Work will also be needed to understand the appropriateness of this approach and to determine how best to incorporate these scans into standard clinical practice.” Subscribe to the First Edition, our free daily newsletter – every morning at 7 p.m. BST Dr James Ware, a cardiologist, genomic medicine reader at Imperial College London and a researcher on the Medical Research Council, warned that the research had not been peer-reviewed and that the summary contained limited details, but added: a unique opportunity for immediate visualization of blood vessels and evaluation of vascular health. “Approaches such as those that use computer vision and / or machine learning to identify subtle vascular features that can predict future heart health seem promising.”
