Related Experiment Video
Updated: Jan 16, 2026
05:19
Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment
Published on: July 7, 2023
3.2K
Predicting Depression Therapy Outcomes Using EEG-Derived Amplitude Polar Maps
Hesam Akbari1, Wael Korani2, Sadiq Muhammad3
1Department of Information Science, University of North Texas, Denton, TX 76205, USA.
Brain Sciences
|September 27, 2025
Summary
A new computer-aided decision (CAD) system accurately predicts patient response to depression treatments like SSRIs and rTMS. This AI tool helps psychiatrists select the most effective therapies, improving patient outcomes for mental health conditions.
Area of Science:
- Neuroscience
- Artificial Intelligence
- Psychiatry
Background:
- Depression treatment response rates for SSRIs and rTMS are around 50%, necessitating improved therapeutic selection.
- Identifying effective depression treatments is challenging for psychiatrists, impacting patient outcomes.
Purpose of the Study:
- To develop and validate a computer-aided decision (CAD) system for predicting patient response to selective serotonin reuptake inhibitors (SSRIs) and repetitive transcranial magnetic stimulation (rTMS).
- To enhance clinical decision-making for depression treatment selection using EEG-based AI.
Main Methods:
- Utilized amplitude polar maps (APMs) to extract features from EEG signals across different channels.
- Employed neighborhood component analysis for feature selection and a feed-forward neural network for classification.
- Implemented a 10-fold cross-validation strategy for robust performance evaluation.
Main Results:
- The CAD system achieved high prediction accuracy: 98.06% for SSRI response and 97.19% for rTMS response.
- Identified key EEG channels predictive of SSRI response (prefrontal/parietal) and rTMS response (frontal/temporal/occipital).
Conclusions:
- The proposed CAD framework shows significant potential as a clinical decision-support tool for personalized depression therapy.
- This AI-driven approach can assist mental health professionals in optimizing treatment selection for depressed patients.
