Advertisement
Parkinson’s disease is a neurodegenerative disorder, the symptoms of which include tremors, slowness of movement and gait, and memory problems.
Using machine learning, researchers analysed blood samples of 72 patients having Rapid Eye Movement Behaviour Disorder (iRBD), in which they physically act out their dreams without knowing it.
Machine learning is a type of artificial intelligence which learns from past data to make future predictions.
Related Articles
Advertisement
Upon analysing the blood samples, the machine learning tool, developed by the researchers, found that almost 80 per cent of the 72 iRBD patients had the same profile as an individual having ageing-related neurodegenerative disease.
The researchers also tested the tool if it could predict the chances of the patient developing Parkinson’s. For this, the iRBD patients were followed up for ten years.
The researchers found that the tool correctly predicted 16 patients to develop the neurodegenerative condition and could do this up to seven years before the onset of any symptoms.
“By determining eight proteins in the blood, we can identify potential Parkinson’s patients several years in advance. This means that drug therapies could potentially be given at an earlier stage, which could possibly slow down disease progression or even prevent it from occurring,” said first author Michael Bartl, University Medical Center Goettingen, Germany.