Researchers Used Artificial Intelligence To Identify Three New Distinct Subtypes Of Parkinson’s Disease In A Groundbreaking New Study
Over 10 million people around the world are living with Parkinson’s disease, according to the Parkinson’s Foundation. The causes of this neurodegenerative disorder also remain largely unknown.
But, artificial intelligence is helping expand scientists’ understanding of this complex condition and how to treat it.
Using machine learning techniques, researchers at Weill Cornell Medicine have identified three new distinct subtypes of Parkinson’s disease based on the rate of symptom progression. The discovery could lead to more tailored treatments based on individual patient symptoms.
“Parkinson’s disease is highly heterogenous, which means that people with the same disease can have very different symptoms,” explained Dr. Fei Wang, the study’s senior author.
“This indicates there is not likely to be a one-size-fits-all approach to treating it. We may need to consider customized treatment strategies based on a patient’s disease subtype.”
The three new subtypes are known as Inching Pace, Moderate Pace, and Rapid Pace.
The Inching Pace (PD-I) subtype affects approximately 36% of patients and has mild symptoms that progress gradually. The Moderate Pace (PD-M) subtype affects approximately 51% of patients and begins with milder symptoms that progress at a moderate pace. Lastly, the Rapid Pace (PD-R) subtype progresses the quickest.
The researchers used deep learning – a form of artificial intelligence capable of analyzing massive datasets to uncover patterns that might elude human detection – to discover these subtypes.
By examining anonymous clinical records from two different sizable databases, the researchers identified these three distinct patterns of Parkinson’s progression.
Coetzee/peopleimages.com – stock.adobe.com – illustrative purposes only, not the actual people
Perhaps most notably, each subtype also appeared to have its very own molecular and genetic fingerprint.
The Rapid Pace subtype, for instance, exhibited increased activity in pathways associated with brain inflammation, metabolism, and oxidative stress – or cell damage caused by unstable molecules.
So, researchers can begin to target these pathways with new or existing drugs by understanding each subtype’s specific biological processes.
The team has already started making some strides in this area, leveraging their research to find drug candidates that could potentially be repurposed for treating Parkinson’s subtypes. Metformin, a medication commonly used to treat diabetes, is one example.
“By examining these databases, we found that people taking the diabetes drug metformin appeared to have improved disease symptoms – especially symptoms related to cognition and falls – compared with those who did not take metformin,” said Dr. Chang Su, the study’s first author.
Furthermore, this was especially pronounced among patients with the Rapid Pace subtype.
This study is just one example of how the advent of artificial intelligence is transforming medical research.
Further study is still needed to confirm the researcher’s findings. But, the potential implications are undeniable – paving the way for customized Parkinson’s disease intervention and treatment.
To read the study’s complete findings, which have since been published in npj Digital Medicine, visit the link here.
Sign up for Chip Chick’s newsletter and get stories like this delivered to your inbox.
More About:Science