Australia develops AI tool to predict Parkinson's disease onset

Scientists from the University of New South Wales (UNSW), Australia in collaboration with Boston University, U.S have developed an artificial intelligence (AI)/machine learning algorithm, which has shown potential to identify Parkinson’s disease, years before symptom onset. 

The researchers used AI to analyse metabolomic data, to identify Parkinson’s disease biomarkers. The study used blood samples taken from healthy individuals gathered by the Spanish European Prospective Investigation into Cancer and Nutrition (EPIC). Within the dataset, there were 39 people that would go on to develop Parkinson’s up to 15 years later. By comparing metabolites in these participants, to 39 people who did not develop Parkinson’s, the team was able to identify the unique combinations of metabolites that could potentially prevent or be warning signs of Parkinson’s disease. 

There is currently no blood test to identify the risk for non-genetic Parkinson’s disease, however this may change if the new tool is validated. 

The new algorithm is called CRANK-MS, short for Classification and Ranking Analysis using a Neural network that generates Knowledge from Mass Spectrometry.

“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 diseases,” Diana Zhang, a study co-author from UNSW, said in a press release.