Parkinson’s disease is a progressive disease caused by the death of nerve cells in a part of the brain called the substantia nigra, which controls movement. These nerve cells die or are destroyed, losing the ability to produce a chemical called dopamine due to the accumulation of the protein alpha-synuclein.
Currently, people with this condition are treated with dopamine replacement therapy after the onset of symptoms such as tremors, slowness of movements and gait, memory problems.
Experts believe that early prediction and diagnosis will be valuable for find treatments that can slow or stop Parkinson’s disease protecting brain cells that produce dopamine.
To try to detect the disease earlier, a team of researchers led by scientists from University College London (UCL) in the UK and the University Medical Center Göttingen in Germany developed a simple blood test that uses artificial intelligence (AI) to predict Parkinson’s disease seven years before symptom onset.
Kevin Mills, lead author, explains: “As new treatments for Parkinson’s disease become available, we need to diagnose patients before they develop symptoms.”. We cannot regenerate our brain cells and therefore must protect the ones we have. Currently, we close the stable door after a horse has escaped and we need to start experimental treatments before patients develop symptoms. So we decided to use cutting-edge technology to find new and better biomarkers for Parkinson’s disease and develop a test based on them that we can use in any large NHS laboratory. We hope that with sufficient funding this will be possible within two years.”
The study showed that when a branch of artificial intelligence called machine learning analyzed a panel of eight biomarkers blood levels, whose concentrations vary in patients with Parkinson’s disease, can provide a diagnosis with 100% accuracy.
The team then experimented to see if the test could predict a person’s likelihood of developing Parkinson’s disease. They did this by analyzing the blood of 72 patients with rapid eye movement disorder (iRBD). This disorder causes patients to physically act out their dreams without even knowing it (by having vivid or violent dreams). It is now known that approximately 75-80% of people with iRBD will develop synucleinopathy (a type of brain disease caused by an abnormal accumulation of the protein alpha-synuclein in brain cells), including Parkinson’s disease.
When A machine learning tool analyzed the blood of these patients found that 79% of patients with iRBD had the same profile as people with Parkinson’s disease.
Patients were followed for ten years and AI prognoses currently correspond to the clinical conversion rate: The team correctly predicted that 16 patients would develop Parkinson’s disease, and were able to do so seven years before it began. any symptoms. The team is currently continuing to monitor those predicted to develop Parkinson’s disease to further test the test’s accuracy.
Co-author Michael Bartl (University Medical Center Göttingen and Paracelsus-Helen-Kassel Hospital), who carried out the study from a clinical perspective together with Dr Jenny Hellqvist (UCL Queen Square Institute of Neuroscience and National Hospital for Neurology and Neurosurgery), states: “By identifying 8 proteins in blood, we can identify possible patients with Parkinson’s disease several years in advance. This means that drug therapy can be prescribed at an earlier stage.” which could slow the progression of the disease or even prevent its onset.
Keep going: “We not only developed a test, but we can diagnose the disease based on markers that are directly related to processes such as inflammation and the degradation of non-functional proteins. “Consequently, these markers represent possible targets for new pharmacological treatments.”
Co-author Professor Kailash Bhatia (UCL Queen Square Institute of Neuroscience and National Hospital for Neurology and Neurosurgery) and his team are currently testing the accuracy of the test by analyzing samples those members of the population who are at high risk of developing Parkinson’s disease
, For example. those who have mutations in certain genes, such as “LRRK2” or “GBA”, that cause Gaucher disease.
The team also hopes to receive funding to create a simpler blood test in which a drop of blood can be detected on a card and sent to a laboratory for testing. can it predict parkinson’s disease even earlier than seven years before the onset of symptoms. in this studio.