University College London researchers have created an artificial intelligence (AI)-powered blood test that can predict the onset of Parkinson's disease up to seven years before symptoms appear. This achievement could revolutionize the way we approach this debilitating neurodegenerative disorder.
"As new therapies become available to treat Parkinson's, we need to diagnose patients before they have developed the symptoms," explained Professor Kevin Mills, the study's senior author. "At present, we are shutting the stable door after the horse has bolted, and we need to start experimental treatments before patients develop symptoms."
Search Antibodies Search Now Use our Antibody Search Tool to find the right antibody for your research. Filter
by Type, Application, Reactivity, Host, Clonality, Conjugate/Tag, and Isotype.
The research, published in Nature Communications, employed machine learning to analyze a panel of eight biomarkers in the blood, whose concentrations are altered in Parkinson's patients. This approach provided a diagnosis with 100% accuracy, according to the team.
To test the predictive power of the AI tool, the team analyzed blood samples from 72 patients with Rapid Eye Movement Behaviour Disorder (iRBD), a condition strongly linked to the development of Parkinson's. The AI correctly identified 79% of these patients as having the same profile as someone with Parkinson's.
"By determining 8 proteins in the blood, we can identify potential Parkinson's patients several years in advance," said co-first author Michael Bartl. "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."
Over the course of ten years, the AI predictions matched the clinical conversion rate, accurately predicting 16 patients who went on to develop Parkinson's, up to seven years before symptom onset.
Kailash Bhatia, a co-author, is currently examining the test's accuracy in high-risk populations, such as those with genetic mutations linked to Parkinson's.