Scientists at UNSW Sydney and collaborators at Boston University have developed a tool that can detect Parkinson’s disease early, years before the first symptoms appear.
In a study published today in the journal ACS Central Scienceresearchers described how they used neural networks to analyze biomarkers in patient fluids.
Researchers at the UNSW School of Chemistry examined blood samples taken from healthy individuals collected by the European Prospective Investigation into Cancer and Nutrition (EPIC) in Spain. The team focused on 39 of her patients who developed Parkinson’s disease up to 15 years later and ran machine learning programs on datasets containing extensive information about their metabolites.
After comparing these metabolites to those of 39 matched control patients (people who participated in the same study who did not develop Parkinson’s disease), the team found that the We were able to identify a unique combination of metabolites that could lead to
As UNSW researcher Diana Zhang explains, she developed a machine learning tool called CRANK-MS with Associate Professor W. Alexander Donald.
“The most common way to analyze metabolomics data is through statistical approaches,” says Zhang.
“Therefore, researchers typically look at correlations involving specific molecules to understand which metabolites are more important for disease compared to controls.
“But here we are considering that metabolites may be related to other metabolites. I used my computational power to understand what was going on.”
Read more: Being told you have Parkinson’s will change your life
A/Prof. Donald said the researchers used a list of unedited data in addition to looking at combinations of metabolites.
“Usually, researchers use machine learning to look at metabolite-disease correlations and first reduce the number of chemical signatures before inputting them into the algorithm,” he says.
“But here we don’t do any data reduction to begin with, we just feed all the information into CRANK-MS. And from there we get the model predictions, and we all know which metabolites are driving the predictions the most.” step, which means we can now detect metabolites that may have been missed by traditional approaches.”
How this is important for Parkinson’s disease
Parkinson’s disease is currently diagnosed by observing physical symptoms such as hand tremors at rest. There are no blood tests or laboratory tests to diagnose non-genetic cases. However, people with Parkinson’s disease may develop atypical symptoms, such as sleep disturbances and apathy, decades before motor symptoms appear. Therefore, CRANK-MS can be used at the first sign of these atypical symptoms to rule out or rule out the risk of developing Parkinson’s disease in the future.
However, A/Prof Donald stresses that validation studies using much larger cohorts and conducted in multiple regions of the world are needed before the tool can be used reliably. However, in the limited cohort investigated for this study, the results were promising, with CRANK-MS able to analyze chemicals found in blood to detect Parkinson’s disease with up to 96% accuracy. .
“This study is interesting on many levels,” he says.
“First, the accuracy of predicting Parkinson’s disease prior to clinical diagnosis is very high. We were able to identify markers.Third, some of the chemical markers that best facilitate accurate predictions have previously been implicated in Parkinson’s disease in cell-based assays but not in humans. was.”
food for thought
When the researchers looked at metabolites in people who developed Parkinson’s disease, they made some interesting discoveries.
For example, triterpenoids had lower blood levels in people who later developed Parkinson’s disease compared to those who did not. Commonly found in food. Future research could investigate whether eating these foods can naturally prevent the development of Parkinson’s disease.
Read more: Funding Early Detection of Parkinson’s Disease
Also worthy of further investigation is the presence of polyfluorinated alkyl substances (PFAS) in people who developed Parkinson’s disease, which may be related to exposure to industrial chemicals.
“There is evidence to suggest it is a PFAS, but we need more characterization data to be 100% sure,” says A/Prof Donald.
Free for everyone
CRANK-MS is a publicly available tool for researchers wishing to use machine learning for disease diagnosis using metabolomics data.
“We built the model on purpose,” says Zhang.
“The application of CRANK-MS to detect Parkinson’s disease is just one example of how AI can improve the way we diagnose and monitor disease. to identify new biomarkers of interest.
“The tool is easy to use and on average can produce results in less than 10 minutes on a traditional laptop.”
