Simple eye exam may help early Parkinson’s diagnosis

Research shows artificial intelligence can detect disease from images of the eye fundus
Reuters Health

A simple eye exam, coupled with an advanced machine-learning algorithm, can help diagnose Parkinson’s disease early, new research suggests.

Thinning of the retina walls and retinal microvasculature occurs in Parkinson’s disease (PD) and may represent an early non-motor sign of the disease.

Maximilian Diaz, a PhD student of biomedical engineering at the University of Florida in the US, and colleagues trained a type of artificial intelligence called a ‘support vector machine’ to learn to detect signs suggestive of PD in fundus eye images.

They used data from two age- and gender-matched datasets from the UK Biobank and the University of Florida to compare fundus eye images from 310 PD patients and 266 healthy controls.