AI-enabled blood tests can detect Parkinson’s disease years before its onset
A blood test using artificial intelligence can predict who will develop Parkinson’s disease up to seven years before symptoms appear, researchers say.
The test is designed to work with equipment already found in many NHS laboratories and, if validated in a broad population of people, could be made available to the healthcare system within two years.
There are currently no drugs to protect the brain against Parkinson’s, but an accurate predictive test would allow clinics to identify people who would benefit most from clinical trials of treatments that aim to slow or stop the disease.
“At the moment we close the stable door after the horse has run away,” said Prof Kevin Mills, senior author of the study at the UCL Great Ormond Street Institute of Child Health. “We need to reach people before they develop symptoms. It is always better to prevent than to cure.”
Parkinson’s disease is the fastest growing neurodegenerative disorder in the world, a trend mainly driven by the aging of the population. The condition affects more than 150,000 people in Britain and 10 million people worldwide. It is caused by the buildup of a protein called alpha-synuclein that damages or destroys nerve cells that produce an important substance called dopamine in a part of the brain called the substantia nigra.
People who develop Parkinson’s disease may experience tremors, movement problems and muscle stiffness, as well as problems with balance, memory, dizziness and nerve pain. Many receive dopamine replacement therapy, but efforts are underway to find treatments that slow or stop the disease.
To develop the test, scientists from UCL and the University of Göttingen used a machine learning algorithm to discover a characteristic pattern of eight blood proteins in patients with Parkinson’s. The algorithm could then predict future Parkinson’s in other patients who provided blood samples. In one patient, the condition was correctly predicted more than seven years before symptoms occurred. “It is possible that it goes back even further,” says Dr Jenny Hällqvist from the UCL Institute of Neurology, and first author of the study published in Nature communication.
Professor Roger Barker, a neurologist who specializes in Parkinson’s disease at the University of Cambridge and Addenbrooke Hospital, said the test, if validated by other groups, would increase the ability to diagnose Parkinson’s disease in its very early stages , allowing patients to be included in clinical trials when the disease process had just begun. “As such, we could treat people with Parkinson’s with disease-modifying therapies before they have lost many cells in their brains,” he said. “Clearly we have yet to find such therapies, but this study is a step in the right direction.”
Prof. Ray Chaudhuri, the medical director of the Parkinson Foundation International Center of Excellence, said there was a “huge unmet need” for blood tests that predict and diagnose Parkinson’s disease, but warned that such tests pose “major challenges”.
“Parkinson’s is not a single disease, but a syndrome and can manifest itself in different ways,” he said. “That is why management differs and there is no one standard for everyone. The forecast is unlikely to identify these subgroups at this stage.” Without effective treatments, early diagnosis poses significant ethical concerns, he added, and may also impact patients’ insurance policies.
“The trial helps us have a group of people with Parkinson’s who may be ready or suitable for future trials with neuroprotective molecules,” Chaudhuri said. “Additionally, there is some preliminary evidence that in such “at-risk” people with Parkinson’s, physical activity and programmed exercise may be beneficial in terms of potentially slowing the progression of the disease.”