Detecting signs of Alzheimer’s through our retinas
An international team led by The Chinese University of Hong Kong’s Faculty of Medicine has successfully developed the world’s first artificial intelligence model that can detect Alzheimer’s disease solely through photographs of the fundus – the inside, back surface of the eye. The model is more than 80% accurate after validation.
The retina is an extension of the central nervous system; thus, the eye is a window that can show degenerative changes in the blood vessels and nerves of the brain. Considering fundus photography is widely accessible, non-invasive and cost-effective, this novel AI model incorporated with fundus photography is expected to become an important tool for screening people at high risk of Alzheimer’s disease. Their research was recently published in The Lancet Digital Health.
Within the population of those who are 70 or older in Hong Kong, one in 10 people suffer from dementia, with more than half of those cases attributed to Alzheimer’s disease. Alzheimer’s disease is associated with an excessive accumulation of abnormal amyloid plaque and neurofibrillary tangles in the brains, leading to the death of brain cells and resulting in progressive cognitive decline.
Dr Lisa Au, Clinical Professional Consultant at CU Medicine’s Department of Medicine and Therapeutics, said, “Memory complaints are common among middle-aged and elderly people, and often considered a sign of Alzheimer’s disease. It is sometimes difficult to make an accurate diagnosis of Alzheimer’s disease based on cognitive tests and structural brain imaging. However, methods to detect Alzheimer’s pathology, such as amyloid-PET scans or testing of cerebrospinal fluid collected via lumber puncture, are invasive and less accessible.”
The team developed and validated their AI model using close to 13,000 fundus photographs from 648 Alzheimer’s disease patients and 3,240 cognitively normal subjects. Upon validation, the model showed 84% accuracy, 93% sensitivity and 82% specificity in detecting Alzheimer’s disease. In the multi-ethnic, multi-country datasets, the AI model achieved accuracies ranging from 80% to 92%.
Professor Vincent Mok, Director of the Therese Pei Fong Chow Research Centre for Prevention of Dementia at CU Medicine, remarked, “In addition to its accessibility and non-invasiveness, the accuracy of the new AI model is comparable to imaging tests such as MRIs. It shows potential to become not only a diagnostic test in clinics, but also a screening tool for Alzheimer’s disease in community settings. In the future, we hope to validate its efficacy in identifying high-risk cases of the disease hidden in the community, so that various preventive treatments such as anti-amyloid drugs can be initiated early to slow down cognitive decline and brain damage.”
Dr Carol Cheung, Associate Professor in the Department of Ophthalmology and Visual Sciences at CU Medicine, added, “Notably, our AI model retained a robust ability to differentiate between subjects with and without Alzheimer’s disease, even in the presence of concomitant eye diseases like macular degeneration and glaucoma which are common in city-dwellers and the older population. Our findings should provide more evidence to move AI from code to the real world.”