Machine Learning Tool May Diagnose Parkinson’s Years Before Symptoms Appear

metabolites are important for disease prediction, we developed a machine learning algorithm that can identify unique combinations of metabolites that are associated with a particular disease,” said lead researcher Dr. David Grayden.

The researchers used CRANK-MS to analyse data from a cohort of PD patients and healthy controls. The results showed that the machine learning algorithm was able to identify unique combinations of metabolites that could be used to detect PD early.