{"title":"脑电图微状态作为青少年重度抑郁障碍的指标和4 周治疗反应的预测因子。","authors":"Yaru Zhang, Tingyu Yang, Xilong Cui, Chunxiang Huang, Guangrong Xie, Xuerong Luo, Yuqiong He","doi":"10.1016/j.jad.2025.119511","DOIUrl":null,"url":null,"abstract":"<p><strong>Objectives: </strong>This study sought to identify alterations in electroencephalography (EEG) microstates among adolescents with first-episode and drug-naive major depressive disorder (MDD). Additionally, it aimed to explore the association of EEG microstates with clinical characteristics and patient response to antidepressant treatment over a period of 4 weeks.</p><p><strong>Methods: </strong>A total of 81 first-episode and drug-naive adolescents with MDD and 60 healthy controls (HCs) were recruited. General demographic information and resting EEG data were collected from all participants. Depression symptoms were evaluated using the Hamilton Depression Scale (HAMD) at baseline and following 4 weeks of antidepressant treatment. The study employed EEG microstates and support vector machine (SVM) techniques for data interpretation.</p><p><strong>Results: </strong>Adolescents with first-episode and drug-naive MDD exhibited a significant reduction in the duration of microstate D and an increase in the occurrence of microstate A compared to the HCs (p < 0.05).When comparing treatment responders and non-responders, treatment responders demonstrated an elevated occurrence and coverage of microstate A and transition probabilities of A-C. Conversely, treatment responders showed decreased occurrence and coverage of microstate B and transition probabilities of BD (all p < 0.05). Upon feature selection, five distinct micro-state parameters were utilized as features. Subsequently, the SVM model demonstrated its capability to distinguish between treatment responders and non-responders, achieving an average accuracy of 75.29 %. Notably, the model's peak performance was characterized by a classification accuracy of 82.35%, accompanied by an AUC of 0.819, a sensitivity of 75.00%, and a specificity of 88.89%.</p><p><strong>Conclusions: </strong>Microstate A may be associated with the severity of depressive symptoms, while microstate B might serve as a potent predictor of antidepressant response in adolescents with first-episode and drug-naive MDD.</p>","PeriodicalId":14963,"journal":{"name":"Journal of affective disorders","volume":" ","pages":"119511"},"PeriodicalIF":4.9000,"publicationDate":"2025-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"EEG microstates as indicators and predictors of response through 4 weeks of treatment in adolescents with major depressive disorder.\",\"authors\":\"Yaru Zhang, Tingyu Yang, Xilong Cui, Chunxiang Huang, Guangrong Xie, Xuerong Luo, Yuqiong He\",\"doi\":\"10.1016/j.jad.2025.119511\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Objectives: </strong>This study sought to identify alterations in electroencephalography (EEG) microstates among adolescents with first-episode and drug-naive major depressive disorder (MDD). Additionally, it aimed to explore the association of EEG microstates with clinical characteristics and patient response to antidepressant treatment over a period of 4 weeks.</p><p><strong>Methods: </strong>A total of 81 first-episode and drug-naive adolescents with MDD and 60 healthy controls (HCs) were recruited. General demographic information and resting EEG data were collected from all participants. Depression symptoms were evaluated using the Hamilton Depression Scale (HAMD) at baseline and following 4 weeks of antidepressant treatment. The study employed EEG microstates and support vector machine (SVM) techniques for data interpretation.</p><p><strong>Results: </strong>Adolescents with first-episode and drug-naive MDD exhibited a significant reduction in the duration of microstate D and an increase in the occurrence of microstate A compared to the HCs (p < 0.05).When comparing treatment responders and non-responders, treatment responders demonstrated an elevated occurrence and coverage of microstate A and transition probabilities of A-C. Conversely, treatment responders showed decreased occurrence and coverage of microstate B and transition probabilities of BD (all p < 0.05). Upon feature selection, five distinct micro-state parameters were utilized as features. Subsequently, the SVM model demonstrated its capability to distinguish between treatment responders and non-responders, achieving an average accuracy of 75.29 %. Notably, the model's peak performance was characterized by a classification accuracy of 82.35%, accompanied by an AUC of 0.819, a sensitivity of 75.00%, and a specificity of 88.89%.</p><p><strong>Conclusions: </strong>Microstate A may be associated with the severity of depressive symptoms, while microstate B might serve as a potent predictor of antidepressant response in adolescents with first-episode and drug-naive MDD.</p>\",\"PeriodicalId\":14963,\"journal\":{\"name\":\"Journal of affective disorders\",\"volume\":\" \",\"pages\":\"119511\"},\"PeriodicalIF\":4.9000,\"publicationDate\":\"2025-12-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of affective disorders\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1016/j.jad.2025.119511\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2025/8/21 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q1\",\"JCRName\":\"CLINICAL NEUROLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of affective disorders","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1016/j.jad.2025.119511","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/8/21 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}
EEG microstates as indicators and predictors of response through 4 weeks of treatment in adolescents with major depressive disorder.
Objectives: This study sought to identify alterations in electroencephalography (EEG) microstates among adolescents with first-episode and drug-naive major depressive disorder (MDD). Additionally, it aimed to explore the association of EEG microstates with clinical characteristics and patient response to antidepressant treatment over a period of 4 weeks.
Methods: A total of 81 first-episode and drug-naive adolescents with MDD and 60 healthy controls (HCs) were recruited. General demographic information and resting EEG data were collected from all participants. Depression symptoms were evaluated using the Hamilton Depression Scale (HAMD) at baseline and following 4 weeks of antidepressant treatment. The study employed EEG microstates and support vector machine (SVM) techniques for data interpretation.
Results: Adolescents with first-episode and drug-naive MDD exhibited a significant reduction in the duration of microstate D and an increase in the occurrence of microstate A compared to the HCs (p < 0.05).When comparing treatment responders and non-responders, treatment responders demonstrated an elevated occurrence and coverage of microstate A and transition probabilities of A-C. Conversely, treatment responders showed decreased occurrence and coverage of microstate B and transition probabilities of BD (all p < 0.05). Upon feature selection, five distinct micro-state parameters were utilized as features. Subsequently, the SVM model demonstrated its capability to distinguish between treatment responders and non-responders, achieving an average accuracy of 75.29 %. Notably, the model's peak performance was characterized by a classification accuracy of 82.35%, accompanied by an AUC of 0.819, a sensitivity of 75.00%, and a specificity of 88.89%.
Conclusions: Microstate A may be associated with the severity of depressive symptoms, while microstate B might serve as a potent predictor of antidepressant response in adolescents with first-episode and drug-naive MDD.
期刊介绍:
The Journal of Affective Disorders publishes papers concerned with affective disorders in the widest sense: depression, mania, mood spectrum, emotions and personality, anxiety and stress. It is interdisciplinary and aims to bring together different approaches for a diverse readership. Top quality papers will be accepted dealing with any aspect of affective disorders, including neuroimaging, cognitive neurosciences, genetics, molecular biology, experimental and clinical neurosciences, pharmacology, neuroimmunoendocrinology, intervention and treatment trials.