Aim To develop a deep learning (DL) model that predicts age from fundus images (retinal age) and investigate the association between the retinal age gap (retinal age predicted by the DL model minus chronological age) and the mortality risk. Methods A total of 80,169 fundus images taken from 46,969 participants in the UK Biobank with reasonable quality were included in this study. Of these, 19,200 fundus images from 11,052 participants with no medical history at baseline examination were used to train and validate the DL model for age prediction using five-fold cross-validation. A total of 35,913 of the remaining 35,917 participants had mortality data available and were used to investigate the association between retinal age difference and mortality. Results The DL model achieved a strong correlation of 0.81 (p<0·001) between retinal age and chronological age, and an overall mean absolute error of 3.55 years. Cox regression models showed that each 1-year increase in retinal age gap was associated with a 2% increase in the risk of all-cause mortality (hazard ratio [HR] = 1.02 , 95% CI: 1.00 to 1.03, p = 0.020) and a 3% increase in the risk of cause-specific mortality attributable to non-cardiovascular and non-cancer diseases (HR=1.03, 95% CI: %: 1.00 to 1.05, p=0.041) after multivariable adjustments. No significant association was identified between retinal age difference and cardiovascular or cancer-related mortality. Conclusions Our findings indicate that retinal age gap could be a potential biomarker of aging that is closely related to mortality risk, implicating the potential of retinal imaging as a screening tool for risk stratification and delivery of personalized interventions. . |
Comments
The difference between the biological age of the retina, the light-sensitive layers of nervous tissue at the back of the eye, and a person’s actual (chronological) age is linked to their risk of death, research published online finds in the British Journal of Ophthalmology .
This ’retinal age gap’ could be used as a screening tool, the researchers suggest.
A growing body of evidence suggests that the network of small vessels (microvasculature) in the retina could be a reliable indicator of the overall health of the body’s circulatory system and brain.
While the risks of disease and death increase with age, it is clear that these risks vary considerably between people of the same age, implying that ’biological aging’ is unique to the individual and may be a better indicator of current health and future, says the researcher.
Various tissue, cell, chemical and image-based indicators have been developed to detect biological aging that is out of step with chronological aging. But these techniques are fraught with ethical and privacy issues, in addition to being often invasive, expensive and time-consuming, researchers say.
So they turned to deep learning to see if it could accurately predict the age of a person’s retina from images of the fundus, the inner back surface of the eye, and to see if there was any difference between this and the A person’s actual age, known as the ’retinal age gap’, could be linked to a higher risk of death.
Deep learning is a type of machine learning and artificial intelligence (AI) that mimics the way people acquire certain types of knowledge. But unlike classical machine learning algorithms which are linear, deep learning algorithms are stacked in a hierarchy of increasing complexity.
The researchers relied on 80,169 fundus images taken from 46,969 adults aged 40 to 69, all of whom were part of the UK Biobank, a large population-based study of more than half a million UK residents. middle age and older.
About 19,200 right fundus images from 11,052 participants in relatively good health at the initial Biobank health check were used to validate the accuracy of the deep learning model for retinal age prediction.
This showed a strong association between predicted retinal age and actual age, with overall accuracy within 3.5 years.
The retinal age gap was then assessed in the remaining 35,917 participants over an average follow-up period of 11 years. During this time, 1871 (5%) participants died: 321 (17%) from cardiovascular disease; 1018 (54.5%) cancer; and 532 (28.5%) from other causes, including dementia.
The proportions of "rapidly aging" (those whose retinas appeared older than their actual age) with retinal age gaps of more than 3, 5, and 10 years were, respectively, 51%, 28%, and 4.5%.
Large retinal age gaps in years were significantly associated with a 49% to 67% higher risk of death, other than from cardiovascular disease or cancer.
And each 1-year increase in retinal age difference was associated with a 2% increase in the risk of death from any cause and a 3% increase in the risk of death from a specific cause other than cardiovascular disease. and cancer, after considering influencing factors such as high blood pressure, weight (BMI), lifestyle and ethnicity.
The same process applied to the left eyes produced similar results.
This is an observational study and as such cannot establish cause. The researchers also acknowledge that the retinal images were captured at one point in time and that the participants may not be representative of the UK population as a whole.
However, they write: “Our new findings have determined that retinal age difference is an independent predictor of increased risk of mortality, especially mortality unrelated to cardiovascular disease or cancer. “These findings suggest that retinal age may be a clinically significant biomarker of aging.”
They add: “The retina offers a unique and accessible ’window’ to evaluate the underlying pathological processes of systemic vascular and neurological diseases that are associated with increased risk of mortality.
"This hypothesis is supported by previous studies, which suggested that retinal images contain information on cardiovascular risk factors, chronic kidney diseases, and systemic biomarkers."
The new findings, combined with previous research, add weight to "the hypothesis that the retina plays an important role in the aging process and is sensitive to the cumulative damage of aging that increases the risk of mortality," they explain.
