Early detection of Parkinson’s disease can make all the difference to the effectiveness of treatment. By the time physical symptoms appear, much damage has already been done. So, is there a way to detect the disease earlier?
There just may be, if the results of research from the University of New South Wales (UNSW) are anything to go by.
Working in collaboration with researchers at Boston University, the UNSW team has published results in the journal ACS Central Science, demonstrating the use of a computer algorithm to analyse biomarkers for Parkinson’s in patients’ bodily fluids.
In the study, the UNSW team examined blood samples taken from healthy individuals during the Spanish portion of the World Health Organization’s European Prospective Investigation into Cancer and Nutrition (EPIC) study.
From those samples, the team identified 39 individuals who went on to develop Parkinson’s disease within the 15-year follow-up period.
Simultaneously, the researchers were training a machine learning program, known as CRANK-MS, to properly categorise metabolites in the human body – chemical substances that aid the body in metabolism. Greatly reduced or slowed metabolism is a strong marker for Parkinson’s disease.
The researchers got the algorithm to compare the metabolite structure of the 39 Parkinson’s patients with those of a control group. They were able to identify several unique combinations of metabolites that could potentially be early warning signs for Parkinson’s.
UNSW researcher Diana Zhang explains that the computer algorithm uses statistics data to identify the problematic combinations.
“The most common method of analysing metabolomics data is through statistical approaches,” she says.
“So, to figure out which metabolites are more significant for the disease versus control groups, researchers usually look at correlations involving specific molecules.
“But here we take into account that metabolites can have associations with other metabolites – which is where the machine learning comes in. With hundreds to thousands of metabolites, we’ve used computational power to understand what’s going on.”
At the moment, the only reliable method of diagnosing Parkinson’s is by observing physical symptoms such as a hand tremor. There is no blood test that can detect the condition in non-genetic cases.
The algorithm-driven method has potential as an early warning system but the team warned that further validation studies would be needed using much larger cohorts and conducted in multiple parts of the globe before the tool could be used reliably in a clinical setting.
Among the limited cohort examined for this study, the results were certainly promising. CRANK-MS was able to analyse chemicals found in blood to detect Parkinson’s disease with an accuracy of up to 96 per cent.
Has your family experienced Parkinson’s disease? What will this mean for Parkinson’s management in the future? Let us know what you think in the comments section below.
