AI-Powered Blood Test Could Revolutionize Parkinson’s Detection


A team from UCL and University Medical Center Goettingen has developed an AI-powered blood test that predicts Parkinson’s disease up to seven years before symptoms appear. This neurodegenerative disorder, affecting nearly 10 million people worldwide, progresses as brain cells die, losing the ability to produce dopamine due to the alpha-synuclein protein buildup. Currently, treatments start only after symptoms develop.

The new test analyzes eight biomarkers altered in Parkinson’s patients with 100% accuracy. Published in Nature Communications, the study showed the test could also predict Parkinson’s in patients with Rapid Eye Movement Behaviour Disorder (iRBD), a condition where 75-80% of patients develop synucleinopathy, including Parkinson’s. The AI tool identified that 79% of iRBD patients had profiles similar to Parkinson’s patients. Follow-up over ten years confirmed these predictions.

Lead researcher Professor Kevin Mills hopes to make the test widely accessible within two years with adequate funding. The team is also developing a simpler blood spot test for even earlier predictions. Funded by EU Horizon 2020 and Parkinson’s UK, this research represents a significant step towards early Parkinson’s detection and treatment, according to Professor David Dexter of Parkinson’s UK.