Related Experiment Video
Updated: Jul 24, 2025
05:19
Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment
Published on: July 7, 2023
2.3K
The Three-Lead EEG Sensor: Introducing an EEG-Assisted Depression Diagnosis System Based on Ant Lion Optimization
IEEE Transactions on Biomedical Circuits and Systems
|July 4, 2023
Summary
A new wearable Electroencephalogram (EEG) sensor offers a practical approach to depression diagnosis. Combined with AI algorithms, it achieved over 90% accuracy in detecting depression, overcoming limitations of traditional methods.
Area of Science:
- Neuroscience
- Biomedical Engineering
- Artificial Intelligence
Background:
- Traditional depression diagnosis relies on subjective, time-intensive methods like interviews and clinical scales.
- Existing Electroencephalogram (EEG)-based depression detection research often overlooks practical applications and relies on cumbersome equipment.
- There is a need for accessible, portable, and accurate EEG devices for depression screening.
Purpose of the Study:
- To develop a wearable, user-friendly three-lead EEG sensor for prefrontal lobe data acquisition.
- To evaluate the performance of the developed EEG sensor in terms of noise, SNR, and impedance.
- To assess the efficacy of AI algorithms, specifically the Ant Lion Optimization (ALO) and k-NN classifier, for depression detection using the collected EEG data.
Main Methods:
- A novel wearable three-lead EEG sensor with flexible electrodes was designed and fabricated.
- Experimental measurements were conducted to validate the sensor's technical specifications (noise, SNR, impedance).
- EEG data was collected from 70 depressed patients and 108 healthy controls; features were extracted and optimized using the ALO algorithm for k-NN classification.
Main Results:
- The wearable EEG sensor demonstrated excellent performance with low noise (≤0.91 μVpp), high SNR (26–48 dB), and low impedance (<1 K Ω).
- The optimized feature set using ALO significantly improved classification accuracy.
- The k-NN classifier achieved high diagnostic performance: 90.70% accuracy, 96.53% specificity, and 81.79% sensitivity.
Conclusions:
- The developed wearable three-lead EEG sensor is a practical and effective tool for prefrontal EEG data acquisition.
- The combination of the wearable EEG sensor, ALO algorithm, and k-NN classifier shows significant potential for accurate, AI-assisted depression diagnosis.
- This approach offers a promising alternative to traditional diagnostic methods, enhancing accessibility and efficiency in mental health assessment.
