Early detection of a neurodegenerative disease such as parkinson It would be very important to carry out an early intervention that would help slow down its progression. This could become a reality thanks to a new study carried out by researchers from UCL (University College London) and Moorfields Eye Hospital who have identified Parkinson’s markers on eye scans using artificial intelligence (AI).
The researchers studied images of the retina in Parkinson’s disease to identify these markers that indicate the presence of Parkinson’s in a person seven years before on average the first symptoms appear. Their analysis of the AlzEye dataset was replicated using the larger UK Biobank database (healthy volunteers), which replicated the findings. The findings have been published in Neurology.
The eyes, a ‘window’ to the rest of the organism
This is not the first time that data from eye scans have been used to diagnose a pathology early, since thanks to this type of test, signs of other degenerative diseases such as Alzheimer’s, multiple sclerosis or schizophrenia had already been found before. Eye examinations have also revealed a propensity for high blood pressure, or developing cardiovascular disease or diabetes.
“We hope that this method can soon become a pre-screening tool for people at risk of Parkinson’s disease”
Doctors have known for a long time that the eye can act as a ventana to the rest of the body, offering direct insight into many aspects of health. High-resolution imaging of the retina is now a routine part of eye care, especially a type of 3D scan known as optical coherence tomography (OCT) that, in less than a minute, produces a cross section of the retina ( the back of the eye) in minute detail, down to a thousandth of a millimeter.
In addition to being very useful for monitoring eye health, a retinal scan is the only non-invasive way to see the layers of cells below the skin’s surface, and in recent years researchers have begun using powerful computers to accurately analyze a large number of OCT and other ocular images. Furthermore, using a type of AI known as “machine learning”, computers can discover hidden information about the entire body from these images alone.
“I continue to be amazed at what we can discover through eye scans. Although we are not yet ready to predict whether an individual will develop Parkinson’s, we hope that this method could soon become a screening tool for people at risk of developing the disease,” said Dr. Siegfried Wagner (Institute of Ophthalmology at the UCL and Moorfields Eye Hospital), lead author of the paper.
“Finding signs of a number of diseases before symptoms emerge means that, in the future, people may have time to do lifestyle changes to prevent complicationsand clinicians could delay the onset and impact of life-changing neurodegenerative disorders.”
Professor Alistair Denniston, Consultant Ophthalmologist at Birmingham University Hospitals, Professor at the University of Birmingham and part of the NIHR Moorfields BRC, said: “This work demonstrates the potential of ocular data, harnessed by technology, to detect signs and changes too subtle for humans to detect.” “Now we can detect very early signs of Parkinson’s, which opens new treatment possibilities”.
“The increase in imaging in a broader population will have a huge impact on public health in the future and will eventually lead to predictive analytics. OCT scans are more scalable, non-invasive, lower cost, and faster than brain scans for this purpose,” concludes Louisa Wickham, Moorfields Chief Medical Officer.