AI can predict Parkinson’s disease subtypes with up to 95% accuracy

There is no current method to differentiate the different Parkinson's subtypes in live patients, meaning that many may not be getting the best available treatment. — dpa

Scientists have developed an artificial intelligence (AI) tool that can classify four subtypes of Parkinson’s disease with up to 95% accuracy.

Researchers from the Francis Crick Institute and the UCL Queen Square Institute of Neurology in the United Kingdom “trained” a computer programme to recognise the subtypes of the condition using images of stem cells from patients.