Research based on EEG for addiction level assessment methods and parietal/occipital lobes brain function analysis

Area of Science:

• Neuroscience
• Artificial Intelligence
• Public Health

Background:

• Methamphetamine use disorder (MUD) presents a significant global health challenge.
• Accurate and efficient diagnostic methods for MUD are crucial for effective treatment and intervention.
• Current diagnostic approaches may lack the precision and efficiency needed for widespread application.

Purpose of the Study:

• To develop and validate an advanced assessment method for MUD.
• To integrate electroencephalography (EEG) deep learning with advanced analytical techniques for improved diagnostic accuracy.
• To identify specific brain channels and EEG patterns indicative of MUD.

Main Methods:

• Utilized electroencephalography (EEG) data from individuals with and without MUD.
• Employed an enhanced compact convolutional neural network (ECCN-Net) for accurate EEG data classification.
• Validated classification results using time-domain, frequency-domain analysis, and Class Activation Mapping (CAM) visualization.

Main Results:

• The ECCN-Net model achieved high classification accuracy for MUD.
• The PO3 brain channel demonstrated the highest diagnostic accuracy at 85.15%.
• Individuals with MUD exhibited significantly higher relative power in the delta frequency band.

Conclusions:

• The proposed EEG-based deep learning method offers a promising, accurate, and efficient approach for MUD assessment.
• Specific EEG patterns, particularly in the delta band and at the PO3 channel, are strong indicators of MUD.
• This methodology can aid in early detection and personalized treatment strategies for MUD.