The markers that indicate the presence of Parkinson’s disease can be detected seven years before the first clinical symptoms thanks to the study of the images of the retina. This is confirmed by research carried out at University College London and Moorfields Eye Hospital (United Kingdom).
This is the first time anyone has shown these findings several years before diagnosis.
The study, published in “Neurology”, identifies Parkinson’s markers in eye scans with the help of artificial intelligence (AI). Their analysis of the AlzEye dataset was replicated using the larger UK Biobank database (healthy volunteers), which replicated the findings.
Using these two large and powerful data sets has allowed the team to identify these subtle markers, despite the fact that Parkinson’s disease has a relatively low prevalence (0.1-0.2% of the population).
The generation of the AlzEye data set was made possible by INSIGHTthe world’s largest database of retinal images and associated clinical data.
The use of data from eye scans has revealed signs of other neurodegenerative diseases, including Alzheimer’s, multiple sclerosis and, more recently, schizophrenia, in an emerging and exciting field of research called “oculomics«.
Eye scans and eye data have also been able to reveal a propensity for high blood pressure; cardiovascular diseases including stroke; and diabetes.
Doctors have long known that the eye can act as a “window” to the rest of the body, providing direct insight into many aspects of our health.
High-resolution imaging of the retina is now a routine part of eye care, particularly a type of 3D scanning known as ‘optical coherence tomography‘ (OCT), which is widely used in commercial optical and ophthalmic clinics. In less than a minute, an OCT scan produces a cross section of the retina (the back of the eye) in incredible detail, down to a thousandth of a millimeter.
These images are extremely useful for monitoring eye health, but their value goes far beyond that, as a retinal scan is the only non-intrusive way to see the layers of cells below the skin’s surface.
In recent years, researchers have begun using powerful computers to accurately analyze large numbers of OCT and other eye images, in a fraction of the time it would take a human.
We hope that this method can soon become a pre-screening tool for people at risk of disease.
Siegfried Wagner
University College London y el Hospital Moorfields Eye
Using a type of AI known as “machine learning,” computers can now uncover hidden information about the entire body just from these images. Harnessing this new potential is what oculomics is all about.
Lead author Siegfried Wagner is amazed at what can be discovered through eye scans. «Although we are not ready to predict whether a person will develop Parkinson’s diseasewe hope that this method can soon become a pre-screening tool for people at risk of disease.”
Wagner says that the ability to identify signs of a number of diseases before symptoms emerge means that, in the future, “people may have time to make lifestyle changes to prevent some conditions from arising, and doctors could delay the onset and impact of neurodegenerative disorders.”
“This work demonstrates the potential of eye data, harnessed by technology to detect signs and changes too subtle for humans. We can now detect very early signs of Parkinson’s disease, opening up new treatment possibilities,” says Alistair Denniston, Consultant Ophthalmologist at University Hospitals Birmingham.
For the researcher Louisa Wickhamthe use of images in a broader way in the population «will have a major impact on public health in the future and will eventually lead to predictive analytics.either. OCT scans are more scalable, non-invasive, lower cost, and faster than brain scans for this purpose.”
Parkinson’s disease is a progressive neurological condition, characterized by a reduction in dopamine, and post-mortem examination of patients with Parkinson’s disease has found differences in the INL (inner nuclear layer) of the retina. Previous studies using OCT scans have found potential morphologic abnormalities associated with the disease, but with inconsistencies.
This study confirmed previous reports of a significantly thinner GCIPL (ganglion cell inner plexiform layer), while a thinner INL was found for the first time. In addition, they found that a reduced thickness of these layers was associated with an increased risk of developing Parkinson’s disease, beyond that conferred by other factors or comorbidities.
Future studies are needed to determine if the progression of GCIPL atrophy is driven by brain changes in Parkinson’s disease, or if INL thinning precedes GCIPL atrophy. Exploring this could help explain the mechanism and determine whether retinal imaging could support the diagnosis, prognosis, and complex management of patients affected by Parkinson’s disease..