Default Mode Network Detection using EEG in Real-time.

Area of Science:

• Neuroscience
• Medical Imaging
• Computational Psychiatry

Background:

• Mental health disorders pose a significant global challenge to healthcare systems.
• The Default Mode Network (DMN) is implicated in depression and recovery, making it a potential therapeutic target.
• Functional magnetic resonance imaging (fMRI) has been used to study DMN connectivity, but electroencephalography (EEG) offers a more scalable alternative.

Purpose of the Study:

• To validate the accuracy of real-time Default Mode Network (DMN) detection using electroencephalogram (EEG) data.
• To assess the feasibility of using EEG for monitoring patient recovery from mental health disorders.
• To establish a cost-effective method for analyzing DMN connectivity.

Main Methods:

• Utilized a Hidden Markov Model (HMM) to identify a 12-state resting-state network from EEG data.
• Employed a publicly available EEG dataset for validation.
• Calculated the correlation between baseline and fractional occupancy of the DMN.

Main Results:

• Achieved a high overall DMN detection accuracy of 95% using the developed EEG-based methods.
• Demonstrated a significant correlation of 0.617 between baseline and calculated DMN fractional occupancy.
• Confirmed the efficacy of real-time analysis for DMN identification through EEG.

Conclusions:

• Real-time EEG analysis is a viable and accurate method for detecting the Default Mode Network (DMN).
• This approach provides a scalable and cost-effective avenue for monitoring and potentially treating mental health disorders.
• Further applications in clinical settings for mental health diagnostics and therapeutics are warranted.