Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology · 2026
Resting-state EEG biomarkers predict serotonin-norepinephrine reuptake inhibitor response in depression.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Ma Jing, Li Renren, Yang Dan, Pan Chenxi, Yuan Xiao, Li Fangyun, Yang Hualan, Bie Zhi, Li Yunxia
Аннотация
OBJECTIVE: To develop an objective model using resting-state EEG biomarkers to predict individual response to serotonin-norepinephrine reuptake inhibitors (SNRIs) in depression, addressing the limitations of subjective traditional methods.
METHODS: Baseline resting-state EEG was recorded in 118 patients with depression. After data preprocessing, 26 patients were excluded (21 due to unusable EEG data and 5 due to missed follow-ups), leaving 92 patients for final analysis. Key predictive features identified were left temporal delta power spectral density (PSD), right temporal alpha-beta cross-frequency coupling (CFC), and occurrence of microstate D. A binary logistic regression model incorporating these features was built. A nomogram was developed for clinical use. Model validation used the area under the ROC curve (AUC), C-index, and clinical decision curve analysis (DCA).
RESULTS: The model demonstrated strong predictive power (AUC = 0.876; C-index = 0.876). DCA indicated significant clinical net benefit across decision thresholds. Key EEG features (PSD, CFC, microstate patterns) significantly differed between SNRI responders and non-responders.
CONCLUSIONS: Resting-state EEG biomarkers provide a promising objective tool for predicting SNRI response, advancing precision medicine in depression treatment.
SIGNIFICANCE: This EEG-based model offers a novel, objective approach to personalize antidepressant selection, potentially improving treatment outcomes and efficiency over current subjective methods. Future integration with other neuroimaging could further enhance prediction.
METHODS: Baseline resting-state EEG was recorded in 118 patients with depression. After data preprocessing, 26 patients were excluded (21 due to unusable EEG data and 5 due to missed follow-ups), leaving 92 patients for final analysis. Key predictive features identified were left temporal delta power spectral density (PSD), right temporal alpha-beta cross-frequency coupling (CFC), and occurrence of microstate D. A binary logistic regression model incorporating these features was built. A nomogram was developed for clinical use. Model validation used the area under the ROC curve (AUC), C-index, and clinical decision curve analysis (DCA).
RESULTS: The model demonstrated strong predictive power (AUC = 0.876; C-index = 0.876). DCA indicated significant clinical net benefit across decision thresholds. Key EEG features (PSD, CFC, microstate patterns) significantly differed between SNRI responders and non-responders.
CONCLUSIONS: Resting-state EEG biomarkers provide a promising objective tool for predicting SNRI response, advancing precision medicine in depression treatment.
SIGNIFICANCE: This EEG-based model offers a novel, objective approach to personalize antidepressant selection, potentially improving treatment outcomes and efficiency over current subjective methods. Future integration with other neuroimaging could further enhance prediction.