Related Experiment Video
Updated: Jun 13, 2026
Developing Neuroimaging Phenotypes of the Default Mode Network in PTSD: Integrating the Resting State, Working Memory, and Structural Connectivity
Published on: July 1, 2014
Multi-state neural dynamics encode antidepressant response: Fusion of resting and task networks
Yueheng Peng1, Yue Yu2, Nan Zhou2
1School of Electronic Information and Electrical Engineering, Chengdu University, Chengdu 610106, China; School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 611731, China; International Joint Research Center for Perception and Control of Intelligent Rehabilitation Systems of Sichuan Province, Chengdu 610106, China.
Predicting antidepressant response in major depressive disorder (MDD) is crucial. Combining resting and task electroencephalography (EEG) networks accurately identified responders and predicted outcomes, paving the way for personalized treatment.
Area of Science:
- Neuroscience
- Psychiatry
- Biomedical Engineering
Background:
- Major depressive disorder (MDD) treatment response varies significantly among individuals.
- Accurate prediction of antidepressant response is essential for effective clinical management.
- Current methods lack precision in identifying treatment responders versus non-responders.
Purpose of the Study:
- To develop a method for differentiating antidepressant responders (Res) from non-responders (Non) in MDD using electroencephalography (EEG).
- To predict patient-specific symptomatic improvement under antidepressant treatment.
- To leverage complementary information from resting-state and task-based EEGs for enhanced diagnostic and prognostic capabilities.
Main Methods:
- Pooled baseline EEG data from four centers, including resting and task conditions.
- Constructed brain networks to identify features distinguishing Res from Non.
- Extracted and fused spatial topological features from both EEG states.
- Classified Res versus Non and predicted long-term medication response.
Main Results:
- Baseline EEG features successfully distinguished Res from Non with 96.30% accuracy.
- The approach enabled reliable patient-specific prediction of eight-week treatment outcomes.
- Resting and task EEGs provided synergistic information, improving classification and prediction.
Conclusions:
- Combined resting and task EEG network analysis offers a powerful tool for MDD diagnosis and prognosis.
- This multidimensional approach shows promise for guiding personalized antidepressant selection.
- Further validation may accelerate treatment response and reduce healthcare costs in MDD management.
