The Next AI Medical Marvel: Early Detection of Parkinson’s Disease

The intersection between medicine and artificial intelligence is more prevalent than ever. Recently, a team of researchers harnessed the power of AI to detect signs of Parkinson’s disease up to seven years before clinical diagnosis.

This year alone, AI has been a beacon of hope in the medical field, restoring mobility to quadriplegics, combating age-related diseases, predicting cancer treatment outcomes, and even deciphering intricate protein interactions.

This latest study, spearheaded by a University College London and Moorfields Eye Hospital team, looked at retinal scans.

“For the detection of retinal markers in prevalent Parkinson’s Disease, we used data from AlzEye, a retrospective cohort of 154,830 patients aged 40 years and over attending secondary care ophthalmic hospitals in London, UK, between 2008 and 2018,” the researchers explain.

The study confirmed that individuals with Parkinson’s had a “significantly thinner GCIPL (ganglion cell–inner plexiform layer),” and for the first time, also identified a thinner INL (inner nuclear layer).

The GCIPL is a part of the retina in which certain types of neuron cells called ganglion cells talk to each other to pass along visual information to the brain.

What does this mean in layman’s terms? Simply put, the study concluded that the reduced membrane thickness observed in Parkinson’s patients could be due to the cerebral neurodegeneration involved in Parkinson’s disease. This is seen in other neurodegenerative diseases as well.

The real game-changer here is the involvement of AI in pre-screening for the disease. The study’s findings were made possible by the largest study to date on retinal imaging in Parkinson’s disease, and the rapid analytical power of artificial intelligence was pivotal in analyzing all of the data. The ability of AI to ingest vast amounts of data and uncover patterns that might elude the notice human researchers was instrumental in these discoveries.

“Increasing imaging across a wider population will have a huge impact on public health in the future, and will eventually lead to predictive analysis,” Miss Louisa Wickham, Moorfields’ medical director, explained. “OCT scans are more scalable, non-invasive, lower cost and quicker than brain scans for this purpose.”

Professor Alastair Denniston, consultant ophthalmologist at University Hospitals Birmingham, told UCL that AI can be a powerful aid in medical research.

“We can now detect very early signs of Parkinson’s, opening up new possibilities for treatment,” he said.

“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,” concurred lead author Siegfried Wagner. “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.”