Artificial intelligence (AI) eye scans could detect Parkinson’s disease in people before they show symptoms, according to a study.
Scientists hope the technology could eventually be used as a screening tool for people at risk of developing the disease.
The study was led by Moorfields Eye Hospital and the UCL Institute of Ophthalmology. The team used AI to analyze an AlzEye dataset and capture retinal markers.
They studied a cohort of 154,830 patients aged 40 and over who attended secondary eye clinics in London between 2008 and 2018.
The process was repeated using data from the UK Biobank, examining 67,311 healthy volunteers aged between 40 and 69 recruited between 2006 and 2010.
It was found that people with Parkinson’s had a thinner eye ganglion cell inner plexiform layer (GCIPL) and inner nuclear layer (INL).
Researchers theorize that examining these layers in the years before symptoms appear could help detect the disease earlier.
Siegfried Wagner, a clinical research fellow at Moorfields and a researcher at the UCL Institute of Ophthalmology, said: “I never cease to be amazed at what we can discover through eye scans.
“Although we are not yet able to predict whether a person will develop Parkinson’s disease, we hope that this method could soon become a pre-screening tool for people at risk of the disease.”
“Detecting signs of a range of diseases before symptoms appear means people could have time in the future to make lifestyle changes to prevent the onset of certain diseases, and physicians could delay the onset and impact of life-changing neurodegenerative diseases .”
Alastair Denniston, Consultant Ophthalmologist at University Hospitals Birmingham, Professor at the University of Birmingham and part of the NIHR Moorfields BRC, added: “This work demonstrates the potential of eye data being used by technology to detect signs and changes that are are too subtle for humans to see. We can now detect very early signs of Parkinson’s, which opens up new treatment options.”
Louisa Wickham, Moorfields medical director, said the use of imaging in a broader population “could have a huge public health impact in the future” and offer the potential for “predictive analytics”.
“OCT (optical coherence tomography) scans are more scalable, non-invasive, less expensive and faster than brain scans for this purpose,” she added.
The project involved the National Institute of Health and Social Care and biomedical research centers at Moorfields Eye Hospital, University Hospital Birmingham, Great Ormond Street Hospital (GOSH), Oxford University Hospital, University College Hospital London and UCL Great Ormond Street Institute involved in children’s health.
The results were published in Neurology, the medical journal of the American Academy of Neurology.
Claire Bale, Associate Research Director at Parkinson’s UK, said: “Intervening earlier to stop the loss of valuable brain cells is key to preventing the disease.”
“Parkinson’s UK and others are already funding clinical trials to explore drug and lifestyle approaches to assess their potential to control, slow or prevent Parkinson’s disease.
“This research gives hope that eye scans could be used to identify people at risk for developing Parkinson’s disease and enable early treatment.
“And since the eye scans analyzed in this study are non-invasive and already in routine use, this could easily be put into practice in the NHS.”