AI System Can Detect Parkinson's Disease from Brain Waves, Study Finds

Researchers found a new AI system that analyzes brain wave data can detect Parkinson's disease with high accuracy

Ben Wodecki, Junior Editor - AI Business

April 18, 2024

2 Min Read
Hands holding brain with puzzle paper cutout

Researchers have created an AI-powered system capable of detecting early signs of Parkinson's disease from brain wave recordings.

Researchers from universities in the U.K., Denmark and Australia developed an AI system that analyzes electroencephalograms (EEGs), which measure the brain’s electrical activity.

Parkinson's is a progressive neurological condition where nerve cells in the brain become damaged over time, leading to reduced motor control.

According to the Parkinson’s Foundation, more than 10 million people worldwide are living with Parkinson's, including one million in the U.S., with that number expected to rise to 1.2 million by 2030.

There is currently no cure for Parkinson's. Current diagnosis methods rely on a physician's judgment in evaluating symptoms and medical tests. Earlier Parkinson's diagnoses allow caregivers to provide a better quality of life to those suffering.

The new AI system can detect Parkinson's disease from brain wave scans, enabling clinicians to achieve earlier diagnosis compared to previous techniques.

The system can pick up abnormalities in EEG scans, providing clinicians with insights into the presence and severity of the disease in a patient.

“The findings of this research will assist to create an essential technology for efficient Parkinson's disease diagnosis, enhancing patient care and quality of life,” according to the paper.

Related:AI-Powered Health Assistant Unveiled by World Health Organization

The team behind the model tested it across two tests in San Diego and Iowa, monitoring the brain waves of Parkinson's patients and healthy individuals.

In tests, the AI model achieved impressive accuracy, recording 95.79% accuracy for the Iowa dataset and 99.83% accuracy for the San Diego dataset in classifying Parkinson’s disease patients versus healthy controls.

Results from the experiments showed that the front and central points of the brain provided the best results for detecting signs of Parkinson's.

“The proposed model holds promising potential as a valuable and enduring aid for experts and clinicians in diagnosing Parkinson’s disease,” according to the paper.

The researchers propose that the AI system can be extended to other medical signals, like an electrocardiogram, which monitors the heart and electromyography for measuring muscle stimulation.

“This milestone marks a significant step forward in Parkinson's disease diagnosis, showcasing the potential of our innovative approach,” Muhammad Tariq Sadiq, assistant professor at the University of Essex, wrote on LinkedIn.

This article first appeared in IoT World Today's sister site, AI Business.

Related:Generative AI Health Care Startup Raises $53M, Brings Valuation to $500M

About the Author(s)

Ben Wodecki

Junior Editor - AI Business

Ben Wodecki is the junior editor of AI Business, covering a wide range of AI content. Ben joined the team in March 2021 as assistant editor and was promoted to junior editor. He has written for The New Statesman, Intellectual Property Magazine, and The Telegraph India, among others.

Sign Up for the Newsletter
The most up-to-date news and insights into the latest emerging technologies ... delivered right to your inbox!

You May Also Like