Summary: Researchers have developed an AI-powered blood test that can predict Parkinson’s disease up to seven years before symptoms appear. The test analyzes eight blood biomarkers and has shown 100% accuracy in diagnosing the disease.
This breakthrough offers the possibility of early intervention and treatment before significant damage occurs to the brain.
Highlights:
- The blood test uses AI to analyze eight biomarkers associated with Parkinson’s disease.
- It can predict the onset of Parkinson’s disease up to seven years in advance with great precision.
- Early diagnosis could allow rapid interventions to slow or prevent the progression of the disease.
Source: UCL
A team of researchers, led by scientists from UCL and Goettingen University Medical Center, have developed a simple blood test that uses artificial intelligence (AI) to predict Parkinson’s disease up to seven years before the appearance of symptoms.
Parkinson’s disease is the fastest growing neurodegenerative disease in the world, currently affecting nearly 10 million people worldwide.
This disease is a progressive disorder caused by the death of nerve cells in the part of the brain called 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 buildup of a protein alpha-synuclein.
Currently, people with Parkinson’s disease are treated with dopamine replacement therapy after they have already developed symptoms, such as tremors, slowness of movement and gait, and memory problems. But researchers believe early prediction and diagnosis would be helpful in finding treatments that could slow or stop Parkinson’s disease by protecting dopamine-producing brain cells.
Lead author Professor Kevin Mills (UCL Great Ormond Street Institute of Child Health) said: “As new treatments become available to treat Parkinson’s disease, we need to diagnose patients before they develop symptoms. We can’t regrow our brain cells, so we need to protect the ones we do have.
“Currently we close the stable door after the horse has run away and we have to start experimental treatments before patients develop symptoms. Therefore, we decided to use cutting-edge technology to find new and better biomarkers for Parkinson’s disease and develop them into a test that we can apply in any major NHS laboratory. With sufficient funding, we hope this will be possible within two years. »
The research, published in Natural communicationsfound that when a branch of AI called machine learning analyzed a panel of eight blood biomarkers whose concentrations are altered in Parkinson’s patients, it could provide a diagnosis with 100% accuracy.
The team then experimented to see if the test could predict the likelihood of a person developing Parkinson’s disease.
To do this, they analyzed the blood of 72 patients with rapid eye movement behavior disorder (iRBD). This disorder causes patients to physically act out their dreams without knowing it (having vivid or violent dreams).
It is now known that approximately 75% to 80% of these people with iRBD will develop synucleinopathy (a type of brain disorder caused by the abnormal accumulation of a protein called alpha-synuclein in brain cells), including the disease of Parkinson’s.
When the machine learning tool analyzed the blood of these patients, it identified that 79% of iRBD patients had the same profile as someone with Parkinson’s disease.
The patients were followed for ten years and the AI predictions have so far matched the clinical conversion rate – with the team correctly predicting that 16 patients would develop Parkinson’s disease and being able to do so until seven years before the onset of the disease. of any symptoms. The team is now continuing to follow people at risk of developing Parkinson’s disease, to further verify the accuracy of the test.
Co-first author Dr Michael Bartl (Goettingen University Medical Center and Paracelsus-Elena-Klinik Kassel), who led the research on the clinical side alongside Dr Jenny Hällqvist (UCL Queen Square Institute of Neurology and National Hospital of neurology and neurosurgery), said: “By determining 8 proteins in the blood, we can identify potential Parkinson’s patients several years in advance.
“This means that drug treatments could potentially be given at an earlier stage, which could potentially slow the progression of the disease, or even prevent it from happening at all.
“Not only have we developed a test, but we can also diagnose the disease based on markers directly linked to processes such as inflammation and breakdown of non-functional proteins. These markers therefore represent possible targets for new drug treatments.
Co-author Professor Kailash Bhatia (UCL Queen Square Institute of Neurology and National Hospital for Neurology & Neurosurgery) and his team are currently examining the accuracy of the test by analyzing samples from people at high risk of developing Parkinson’s disease , For example. those with mutations in particular genes such as “LRRK2” or “GBA” that cause Gaucher disease.
The team also hopes to secure funding to create a simpler blood test, where a drop of blood can be spotted on a card and sent to the laboratory to determine whether it can predict Parkinson’s disease even earlier than seven years before the appearance of symptoms. In this study.
The research was funded by an EU Horizon 2020 grant, Parkinson’s UK, the National Institute for Health and Care Research GOSH Biomedical Research Center (NIHR GOSH BRC) and the Szeben-Peto Foundation.
Professor David Dexter, Director of Research at Parkinson’s UK, said: “This research, co-funded by Parkinson’s UK, represents a major milestone in the search for a definitive, user-friendly diagnostic test for Parkinson’s disease.
“The search for identifiable and measurable biological markers in the blood is much less invasive than a lumbar puncture, which is increasingly used in clinical research.
“With more work, it might be possible that this blood test could distinguish between Parkinson’s disease and other diseases with some early similarities, such as multiple system atrophy or dementia with Lewy bodies.
“The results add to an exciting wave of recent activity aimed at finding a simple way to test and measure Parkinson’s disease.”
About this Parkinson’s research news
Author: Poppy Tombs
Source: UCL
Contact: Poppy tombs – UCL
Picture: Image is credited to Neuroscience News
Original research: Free access.
“Plasma proteomics identifies biomarkers predicting Parkinson’s disease up to 7 years before symptom onset” by Kevin Mills et al. Natural communications
Abstract
Plasma proteomics identifies biomarkers predicting Parkinson’s disease up to 7 years before symptom onset
Parkinson’s disease is becoming more and more common. It progresses from the pre-motor stage (characterized by non-motor symptoms such as REM sleep behavior disorder) to the disabling motor stage.
We need objective biomarkers for early/premotor stages of the disease so that we can intervene and slow down the underlying neurodegenerative process.
Here, we validate a targeted multiplexed mass spectrometry assay for blood samples from newly diagnosed motor Parkinson’s disease patients (not= 99), premotor individuals with isolated REM sleep behavior disorder (two cohorts: not= 18 and not= 54 longitudinally) and healthy controls (not= 36).
Our machine learning model accurately identifies all Parkinson’s patients and classifies 79% of premotor individuals up to 7 years before motor onset by analyzing the expression of eight proteins: the granululin precursor Mannan- binding-lectin-serine-peptidase-2, Endoplasmic reticulum-chaperone-BiP, prostaglaindin-H2-D-isomaerase, intercellular adhesion molecule-1, complement C3, Dickkopf-WNT signaling pathway inhibitor-3 and inhibitor of plasma protease-C1. Many of these biomarkers correlate with symptom severity.
This specific blood panel indicates molecular events at an early stage and could help identify at-risk participants for clinical trials aimed at slowing/preventing motor Parkinson’s disease.