Researchers have identified, with the help of artificial intelligence, a biological signature of Parkinson’s disease that, they hope, could lead to a simple blood test for detecting this condition at least seven years before the onset of symptoms. Parkinson’s disease could be predicted seven years before the onset of the first symptoms. What role does artificial intelligence play?
Currently, there are no drugs that can slow down or stop Parkinson’s disease, and efforts to develop preventive treatments are hampered by the ability to know if a person will develop this condition. With the help of machine learning — a form of artificial intelligence — researchers from University College London and the University Medical Center in Goetingen, Sweden, analyzed blood samples from people with Parkinson’s and detected eight key proteins or «biomarkers» common to those suffering from this condition.
Artificial intelligence was used to analyze blood samples taken a decade ago from people with a sleep disorder, called rapid eye movement disorder, of which about 75% end up developing Parkinson’s. So far, artificial intelligence has been able to correctly predict which patients will develop Parkinson’s disease. Moreover, the tool managed to do this up to seven years before the onset of the first symptoms, reveals the cited source.
«This means that drug therapies could be administered at an earlier stage, which could slow the progression of the disease or even prevent its onset,» said Dr. Michale Bartl from UMC Goetingen. A blood test that predicts Parkinson’s years in advance could be essential for accelerating clinical studies — but it is not without ethical obstacles, says neurologist professor Ray Chaudhuri, from King’s College in London, according to Sky News.
Researchers still have work to do to validate the accuracy of the tests and to develop a version that can be easily used in the clinic.
