Brain-age estimation with a low-cost EEG-headset: effectiveness and implications for large-scale screening and brain...

Area of Science:

• Neuroscience
• Artificial Intelligence
• Biotechnology

Background:

• Brain aging is influenced by pathological, genetic, environmental, and lifestyle factors.
• Early detection of brain aging is challenging due to late-stage symptomatic diagnosis.
• Current diagnostic methods are often difficult or ineffective by the time symptoms appear.

Purpose of the Study:

• To develop a cost-effective and widely applicable method for assessing age-related brain health and function.
• To utilize machine learning and resting-state electroencephalography (RS-EEG) for brain-age estimation.
• To create a tool for early detection and monitoring of brain aging.

Main Methods:

• Trained a machine-learning algorithm on RS-EEG recordings from healthy individuals.
• Utilized the low-cost EMOTIV EPOC X headset for data acquisition.
• Validated the model against an independent test set of healthy participants.

Main Results:

• Achieved a correlation coefficient of 0.582 between chronological and estimated brain ages (r = 0.963 after bias-correction).
• Demonstrated a test-retest correlation of 0.750 (0.939 after bias-correction) over one week.
• The model shows strong performance in estimating brain age from RS-EEG data.

Conclusions:

• The developed RS-EEG based brain-age estimation technique is a promising tool for assessing general brain health.
• The low cost and ease of implementation suggest potential for widespread clinical, workplace, and home use.
• This technique can effectively monitor the impact of interventions on brain health over time.