Scientists have created a straightforward blood test that utilizes artificial intelligence (AI) to forecast Parkinson’s disease up to seven years before symptoms appear. Parkinson’s disease is a rapidly growing neurodegenerative disorder that currently impacts almost 10 million people worldwide. This condition is progressive and leads to a decline in mobility and coordination over time.It is caused by the death of nerve cells in the part of the brain called the substantia nigra, which controls movement. These nerve cells die or become impaired, losing the ability to produce an important chemical called dopamine, due to the build-up of a protein alpha-synuclein.
Currently, people with Parkinson’s are treated with dopamine replacement therapy after they have already developed symptoms, such as tremor, slowness of movement and gait, and memory problems. But researchers believe that early prediction and diagnosis would be valuable for finding treatments that could slow or stop Parkinson’s by protecting the dopamine production.A study published in the journal ‘Nature Communications’ reveals that researchers have used cutting-edge technology to identify potential biomarkers for Parkinson’s disease. The team, led by Professor Kevin Mills of the UCL Great Ormond Street Institute of Child Health, aims to develop a diagnostic test for the disease that can be used before symptoms appear.
The researchers emphasize the importance of early diagnosis, stating that as new therapies for Parkinson’s become available, it is crucial to identify patients before symptoms manifest. They highlight the fact that brain cells cannot be regenerated, underscoring the need to protect existing cells. Professor Mills compares the current approach to “shutting the stable door after the horse has bolted,” and stresses the importance of initiating experimental treatments before symptoms arise.
By leveraging state-of-the-art technology, the researchers hope to identify new and improved biomarkers for Parkinson’s disease, paving the way for the development of an early diagnostic test. This proactive approach could revolutionize the way Parkinson’s is diagnosed and treated, ultimately benefiting patients and advancing medical research.The goal is to integrate the test into NHS laboratories, and it may be achievable with adequate funding within two years. The study, which was published in Nature Communications, discovered that machine learning, a type of AI, could diagnose Parkinson’s with 100% accuracy by analyzing eight blood-based biomarkers that are changed in Parkinson’s patients. The researchers also tested whether the test could forecast the risk of developing Parkinson’s by examining blood samples from 72 patients with Rapid Eye Movement.Behaviour Disorder (iRBD), also known as REM sleep behaviour disorder, causes patients to physically act out their dreams unknowingly, often experiencing vivid or violent dreams. Research has shown that approximately 75-80% of individuals with iRBD will eventually develop a synucleinopathy, a type of brain disorder characterized by the abnormal accumulation of alpha-synuclein protein in brain cells, which can lead to conditions such as Parkinson’s disease.
A machine learning tool analyzed the blood of these patients and found that 79% of those with iRBD had a similar blood profile to individuals with Parkinson’s disease.
Over the course of ten years, the patients were monitored, and the AI predictions proved to be accurate.The team accurately predicted 16 patients who would develop Parkinson’s up to seven years before any symptoms appeared. They are continuing to monitor these patients to confirm the accuracy of the test. Dr. Michael Bartl and Dr. Jenny Hällqvist conducted the research from the clinical side and are working to verify the accuracy of the test.By detecting certain markers in the blood, we can potentially identify individuals who may develop Parkinson’s disease several years before symptoms appear. This could lead to earlier administration of drug therapies, potentially slowing down the progression of the disease or even preventing it altogether.
“We have not only created a test for diagnosing the disease, but we can also pinpoint markers that are directly connected to processes such as inflammation and the breakdown of non-functional proteins. These markers could potentially serve as targets for new drug treatments,” stated co-author Professor Kailash Bhatia (UCL Queen Square Institute of Neurology and National Hospital for Neurology & Neurosurgery).The accuracy of the test is currently being evaluated by Dr. Ry and his team. They are doing this by analyzing samples from individuals who are at high risk of developing Parkinson’s, such as those with specific gene mutations like ‘LRRK2’ or ‘GBA’ which result in Gaucher disease.
The team is also seeking funding to develop a simpler blood spot test. This test would involve placing a drop of blood on a card, which could then be sent to the lab for analysis. The goal is to determine if this test can predict Parkinson’s disease even earlier than the seven years before symptoms appear, as seen in the current study.
The research was supported by a grant from the EU Horizon 2020 program, Park.The National Institute for Health and Care Research GOSH Biomedical Research Centre (NIHR GOSH BRC), and the Szeben-Peto Foundation are collaborating with Professor David Dexter, Director of Research at Parkinson’s UK, to fund research in the UK. “This co-funded research by Parkinson’s UK is a significant advancement in the quest for a definitive and patient-friendly diagnostic test for Parkinson’s,” says Professor David Dexter. He also mentions that finding biological markers in the blood could be less invasive than the currently used lumbar puncture in clinical research. This blood-based test has the potential to differentiate between Parkinson’s and other conditions like Multiple Systems Atrophy or Dementia with Lewy Bodies in the early stages. The recent findings contribute to the ongoing efforts to develop a simple test for and measure Parkinson’s.
