Researchers from University College London and Moorfields Eye Hospital NHS Foundation Trust have discovered indicators using eye scans that can detect Parkinson’s disease in patients approximately seven years prior to its clinical manifestation.

This is the first time Parkinson’s has been detected years before diagnosis, thanks to the most extensive study ever conducted on retinal imaging related to Parkinson’s disease. The researchers wrote about their study, findings, and achievement in the peer-reviewed academic journal Neurology (citation below).

With the help of AI (artificial intelligence), they were able to identify Parkinson’s markers in eye scans. They further validated their findings by analyzing the AlzEye dataset and cross-referencing it with the expansive UK Biobank database (comprising healthy volunteers). Despite the low occurrence of Parkinson’s disease in the general population (0.1-0.2%), the combination of these two robust datasets facilitated the detection of these subtle markers.

The creation of the AlzEye dataset was made possible through INSIGHT, the world’s most comprehensive repository of retinal images and associated clinical data.

Photo of a doctor using an eye scanner on a patient

UCL image adapted by


Historically, eye scan data has unveiled signs of various neurodegenerative disorders such as Alzheimer’s, multiple sclerosis, and notably, schizophrenia. This burgeoning and captivating realm of study is called “oculomics.”

Eye scans and eye data have also been able to determine whether people are likely to develop hypertension (high blood pressure), strokes, other cardiovascular diseases, and diabetes.

Eye is a ‘window’ to the rest of the body

Doctors have long known that the eye can act as a ‘window’ to the health of the rest of the body. A routine part of eye care today involves high-resolution images of the retina, in particular ‘optical coherence tomography’ (OCT) – a type of 3-dimensional scan. OCT is widely used today by high-street opticians and eye clinics.

In under a minute, an OCT scan offers a detailed cross-section of the retina with remarkable precision, capturing details down to one-thousandth of a millimeter. The retina is the light-sensitive layer at the back of the eye, converting light into neural signals for the brain.

These images are pivotal for eye health surveillance, yet their significance extends further – retina scans are the sole non-invasive method to observe subdermal cell layers.

Using ‘machine learning’

Recently, scientists have employed advanced computers to efficiently analyze vast quantities of OCTs and other ocular images, many times faster than what a team of researchers could do. Using ‘Machine Learning’, a type of artificial intelligence, computers today can uncover hidden information about the entire body from these images alone.

Machine Learning is a part of AI where computers learn from data, getting better at tasks without being specifically told how, i.e., they learn along the way on their own. Oculomics is all about harnessing this new potential.

Two drawings of old men with Parkinsons' disease

Image created by

Eye scan may one day be a pre-screening tool

Lead author, Dr. Siegfried Wagner, Honorary Clinical Senior Research Fellow at UCL Institute of Ophthalmology and Moorfields Eye Hospital, said:

“I continue to be amazed by what we can discover through eye scans. While we are not yet ready to predict whether an individual will develop Parkinson’s, we hope that this method could soon become a pre-screening tool for people at risk of disease.”

“Finding signs of a number of diseases before symptoms emerge means that, in the future, people could have the time to make lifestyle changes to prevent some conditions arising, and clinicians could delay the onset and impact of lifechanging neurodegenerative disorders.”

Co-author, Professor Alastair Denniston, consultant ophthalmologist at University Hospitals Birmingham, professor at the University of Birmingham, and also part of the NIHR Moorfields BRC, said:

“This work demonstrates the potential for eye data, harnessed by the technology to pick up signs and changes too subtle for humans to see. We can now detect very early signs of Parkinson’s, opening up new possibilities for treatment.”

Wagner, Siegfried Karl, David Romero-Bascones, Mario Cortina-Borja, Dominic J Williamson, Robbert R Struyven, Yukun Zhou, Salil Patel, Rimona S Weil, Chrystalina A Antoniades, Eric J Topol, Edward Korot, Paul J Foster, Konstantinos Balaskas, Unai Ayala, Maitane Barrenechea, Iñigo Gabilondo, Anthony HV Schapira, Anthony P Khawaja, Praveen J Patel, Jugnoo S Rahi, Alastair K Denniston, Axel Petzold, Pearse Andrew Keane. “Retinal Optical Coherence Tomography Features Associated With Incident and Prevalent Parkinson Disease.” Neurology, 21 Aug. 2023, doi:10.1212/WNL.0000000000207727.

Interesting related article: “What is Parkinson’s Disease?”