Anxiety disorder Mental and Behavioural Disorders
Conditions
Interventions
Study 1:
The participants underwent two identical experimental procedures: Day 1: the first montreal imaging stress task (MIST) with EEG recording. Day 4: the second MIST task with EEG recording. The
Sponsors
Affiliated Psychological Hospital, Anhui Medical University
Eligibility
Sex/Gender
All
Age
17 Years to 30 Years
Inclusion criteria
Inclusion criteria: Anxiety disorder participants: 1. Age 17-30 years old college students; 2. Able to comprehend questionnaire content and complete all scales independently; 3. Currently experiencing only anxiety symptoms without other DSM-5-confirmed mental disorders; 4. No history of psychiatric medication use (within 6 months); 5. Normal vision and hearing or corrected vision/hearing; 6. No severe physical illnesses, no history of head trauma, no metal implants in the head, no epilepsy, no episodes of transient loss of consciousness; willing to participate and have signed an informed consent form. Healthy participants: 1. Age 17-30 years old college students 2. Normal hearing, normal or corrected vision 3. Right-handed 4. No previous diagnosis of mental or psychological illness 5. No history of major physical illness
Exclusion criteria
Exclusion criteria: Exclusion criteria for anxiety disorders: 1. The questionnaire results contain significant logical inconsistencies; 2. Confirmed diagnosis of mental illness or family history of psychiatric disorders; 3. History of head trauma or implanted devices in the head; 4. If participants show marked improvement in anxiety levels or nearly perfect scores during closed-loop training before the assessment, they may be preliminarily excluded from the anxiety group as they may not meet the diagnostic criteria for anxiety.
Design outcomes
Primary
| Measure | Time frame |
|---|---|
| Study 1: Prediction of cortisol and a-amylase levels using machine learning models based on electroencephalogram features. Study 2: 1. Change in amplitude of anxiety-specific Event-Related Potential (ERP) components (e.g., N2, P3, or Late Positive Potential (LPP)) during the emotional regulation task. Timepoint: From baseline (pre-intervention) to immediately after the completion of the closed-loop training sessions. 2. Change in high-frequency beta wave power during the emotional regulation task. Timepoint: From baseline (pre-intervention) to immediately after the completion of the closed-loop training sessions. | — |
Secondary
| Measure | Time frame |
|---|---|
| Study 1: 1. Performance comparison of different machine learning models in predictive tasks: Specific metrics include accuracy, which evaluates the performance of multilayer perceptrons, support vector machines, and linear discriminant analysis in predicting elevated/low cortisol and a-amylase levels. 2. Importance contribution of EEG features to predictive models: Quantification of relative contributions from different frequency bands (e.g., Delta, Theta, Alpha, Beta, Gamma) to cortisol and a-amylase prediction using SHAP values. Quantification of relative contributions from different brain regions (e.g., right prefrontal cortex, occipital cortex, parietal cortex) to predicting these biomarker levels through SHAP values. 3. Regression prediction accuracy of machine learning models for cortisol and a-amylase levels: Evaluation metrics include R² (coefficient of determination) and mean absolute error to measure models' ability to predict continuous physiological parameter values. 4. Differences in EEG feature model prediction effectiveness across time points (first and second MIST tasks): Assess whether temporal factors during stress task interventions affect the classification performance of EEG feature-based models. Study 2: 1. Change in self-reported anxiety scores as measured by standardized anxiety scales (e.g., GAD-7, SAS). Timepoint: From baseline (pre-intervention) to immediately after the completion of the training sessions. 2. Change in behavioral performance during the emotional regulation task, including: Reaction time to positive and negative stimuli. Accuracy of emotion identification. Timepoint: From baseline to post-intervention. 3.Change in scores from the closed-loop training task (where a higher score indicates better ability to suppress negative emotions and greater emotional stability). Timepoint: Measured after each training block and compared across the training course. 4.Changes in other EEG/ERP components not listed as primary outcomes, s | — |
Countries
China
Contacts
Public ContactLi;Qinghui Wan;Zhang
;
Outcome results
None listed