A new blood test has the potential to predict whether a person will develop Parkinson’s disease up to seven years before any symptoms arise. The test analyzes proteins in the blood, identifying differences in concentrations between individuals with and without Parkinson’s. By utilizing this test alongside an artificial intelligence (AI) tool, scientists can identify people with a confirmed Parkinson’s diagnosis and those within an at-risk group who are likely to develop the condition.
“We need to diagnose patients before they have developed the symptoms,” stated study author Professor David Mills, a professor of translational omics at University College London, in a press release. Currently, most individuals are treated only after they begin to exhibit signs of Parkinson’s, which Mills emphasizes is too late. “We cannot regrow our brain cells, and therefore we need to protect those that we have,” Mills stressed. “At present, we are shutting the stable door after the horse has bolted, and we need to start experimental treatments before patients develop symptoms.”
Parkinson’s disease affects millions worldwide and causes over 300,000 deaths annually – a number that is tragically rising. The disease involves the clumping of proteins inside brain cells that produce dopamine, a crucial chemical messenger for movement coordination. These protein clumps damage and ultimately kill the cells, leading to the characteristic symptoms of Parkinson’s: tremors, muscle stiffness, slow movement, and unstable posture. Eventually, it can lead to difficulty walking, increasing the risk of fatal falls, and can also severely affect swallowing and breathing.
In the new study, published on June 18th in the journal ‘Brain,’ researchers identified eight proteins whose levels differed significantly in the blood of people with Parkinson’s compared to those without the disease. Using these “biomarkers,” they trained an AI tool to identify patients whose protein profiles resembled those associated with Parkinson’s, even if they did not exhibit symptoms. When tested on a group of 41 patients (30 with Parkinson’s and 11 without), the AI tool achieved 100% accuracy in classification, according to the researchers.
The researchers then investigated a separate group of 54 individuals with a family history of Parkinson’s. These participants provided one to five blood samples over the course of the study. The scientists utilized the blood test and AI tool to examine the participants’ protein profiles. For 47 individuals, the AI flagged at least one blood sample as predictive of Parkinson’s, forecasting the eventual onset of the condition. The scientists have been monitoring these patients, and so far, 11 have developed Parkinson’s, while five developed a related condition called REM sleep behavior disorder. The test anticipated the onset of symptoms by an average of 3.5 years, and in one case, as much as 7.3 years.
“Predicting Parkinson’s early would identify a new group of people that could take part in clinical trials,” said Dr. Beckie Fletcher, the research communications lead at Parkinson’s U.K., in an email to Live Science. “This could help more quickly identify that could slow or stop the condition and even identify those that might stimulate regrowth of dopamine-producing cells,” said Fletcher, who was not involved in the new study. These treatments would represent a significant improvement over current Parkinson’s treatments, which primarily focus on preventing dopamine breakdown or converting other substances into dopamine within the brain.
The researchers plan to continue their follow-up studies to observe who else in the study develops Parkinson’s, further validating the test’s predictive power. They also intend to verify their findings in larger populations and refine the biomarkers used. Ultimately, their goal is to develop a simplified version of the test that requires only a drop of blood, eliminating the need for a full vial.
“We’ve seen tremendous progress in the development of exciting new tests for Parkinson’s in the last year alone,” said Fletcher. “We are hopeful that these new tests will start being used within the next few years,” initially for clinical trials and research, and eventually for routine patient care.
