A simple blood test utilizing artificial intelligence (AI) could predict Parkinson’s disease up to seven years before the onset of symptoms, according to a study led by researchers at UCL and University Medical Center Goettingen. The findings, published in Nature Communications, offer hope for early diagnosis and treatment of the world’s fastest-growing neurodegenerative disorder.
Protecting Brain Cells: The Key to Slowing Parkinson’s Progression
Parkinson’s disease is caused by the death of nerve cells in the substantia nigra, a part of the brain that controls movement. These cells produce dopamine, a crucial chemical for motor function. Current treatments focus on replacing dopamine after symptoms have already developed, but researchers believe that early prediction and diagnosis could lead to therapies that protect these cells and slow or stop the disease’s progression.
Professor Kevin Mills, senior author from UCL Great Ormond Street Institute of Child Health, emphasizes the importance of early diagnosis: “As new therapies become available to treat Parkinson’s, we need to diagnose patients before they have developed the symptoms. We cannot regrow our brain cells and therefore we need to protect those that we have.”
Machine Learning Accurately Identifies Parkinson’s Biomarkers
The research team used machine learning, a branch of AI, to analyze a panel of eight blood-based biomarkers altered in Parkinson’s patients. The tool provided a diagnosis with 100% accuracy and predicted the likelihood of developing the disease in patients with Rapid Eye Movement Behaviour Disorder (iRBD), a condition where 75-80% of patients go on to develop a brain disorder caused by the abnormal buildup of a protein called alpha-synuclein.
The AI predictions matched the clinical conversion rate over a ten-year follow-up, correctly identifying 16 patients who developed Parkinson’s up to seven years before symptoms appeared. Co-first-author Dr Michael Bartl from University Medical Center Goettingen and Paracelsus-Elena-Klinik Kassel noted, “By determining 8 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.”
The researchers are now working on further validating the test’s accuracy in high-risk populations and developing a simpler blood spot test that could predict Parkinson’s even earlier. The study was funded by an EU Horizon 2020 grant, Parkinson’s UK, the National Institute for Health and Care Research GOSH Biomedical Research Centre (NIHR GOSH BRC), and the Szeben-Peto Foundation.
Professor David Dexter, Director of Research at Parkinson’s UK, called the research “a major step forward in the search for a definitive and patient friendly diagnostic test for Parkinson’s” and noted that with more work, the blood-based test could potentially distinguish between Parkinson’s and other conditions with similar early symptoms.
More Information
- Michael J. Fox Foundation for Parkinson’s Research: This foundation is a leading source of funding for Parkinson’s research and provides a wealth of information on the disease, including its causes, symptoms, and treatment options. https://www.michaeljfox.org/
- Parkinson’s Disease Foundation: This foundation provides another excellent resource for information on Parkinson’s disease, as well as support programs and advocacy efforts. https://www.parkinson.org/
- National Institute on Neurological Disorders and Stroke (NINDS): This government website provides information on Parkinson’s disease, including its causes, symptoms, diagnosis, and treatment. It also includes information on clinical trials that are currently underway. https://www.ninds.nih.gov/health-information/disorders/parkinsons-disease
