Your eyes reveal your true age
By examining tiny vessels inside a person’s eyes, doctors might one day be able to predict that person’s risk of early death. Though the risks of illness and early death generally increase with chronological age, that risk can vary quite a bit among individuals of the same age. That difference can be explained by a person’s ‘biological age’, which unlike chronological age ticks at an individual rate for each person depending on several health factors.
Previous studies have explored various biomarkers in the body that might be able to determine a person’s biological age, including specific genes, cognitive abilities, blood pressure and immune system function. Past research has shown retinae, light-sensitive layers of nerve tissue at the back of the eyes, are a possible indicator of a person’s biological age because they can provide clues about disease risk. Researchers turned to a deep-learning technique that could predict a
person’s risk of death by analysing the biological age of the retinae.
Their deep-learning model, a type of machine learning and artificial intelligence that’s modelled to learn similar to a human brain, analysed more than 80,000 images of fundus – the internal back surface of the eye that includes the retina. They obtained the images from nearly 47,000 people between the ages of 40 and 69, stored in the UK Biobank, a biomedical database of more than half a million UK residents. To figure out whether their model was accurate, they first analysed more than 19,000 fundus images taken from more than 11,000 participants who were in relatively good health. The idea was that the retinal biological ages of these people should be fairly similar to their chronological age.
The model was fairly accurate in predicting retinal ages, with an accuracy of within 3.5 years to chronological ages. They then used the model to assess the nearly 36,000 remaining participants’ fundus photos, collected across a span of 11 years. They found that 51 per cent of the participants had a ‘retinal age gap’, the difference between biological and chronological age, of more than three years; 28 per cent had a gap of more than five years and 4.5 per cent had a gap of more than ten years. In other words, these participants had ‘older’ eyes compared to their chronological age.
Those who had larger age gaps had a 49 per cent to 67 per cent higher risk of death from causes other than cardiovascular disease or cancer. With every one-year increase in the age gap, the risk of death increased by two per cent for any cause and three per cent for causes other than cardiovascular disease and cancer. But they didn’t find a link between retinal age gap and death due to cardiovascular disease or cancer. The researchers note that because it was an observational study, they couldn’t determine a cause-and-effect relationship.