Assessing the Predictive Utility of Quantitative Electroencephalography Coherence in Adolescent Major Depressive Disorder: A Machine Learning Approach.

IF 2.2 4区 医学 Q2 PEDIATRICS
Molly McVoy, Serhiy Chumachenko, Maia Gersten, Benjamin Wade, Oscar Corcelles, Joy Yala, Mikaila Gray, Alla Morris, Asif Jamil, Paolo Cassono, Farhad Kaffashi, Kenneth Loparo, Farren Briggs, Martha Sajatovic
{"title":"Assessing the Predictive Utility of Quantitative Electroencephalography Coherence in Adolescent Major Depressive Disorder: A Machine Learning Approach.","authors":"Molly McVoy, Serhiy Chumachenko, Maia Gersten, Benjamin Wade, Oscar Corcelles, Joy Yala, Mikaila Gray, Alla Morris, Asif Jamil, Paolo Cassono, Farhad Kaffashi, Kenneth Loparo, Farren Briggs, Martha Sajatovic","doi":"10.1177/10445463251358742","DOIUrl":null,"url":null,"abstract":"<p><p><b><i>Background:</i></b> Improving early recognition and accurate diagnosis of major depressive disorder (MDD) in childhood is a pressing concern. Quantitative electroencephalogram (qEEG) may be an effective, noninvasive diagnostic biomarker for MDD. Prior work by our team demonstrated decreased resting connectivity, as measured by qEEG coherence, in a heterogeneous group of adolescents with MDD compared with age and gender-matched healthy controls (HCs). This study explored qEEG coherence as a predictor of MDD diagnosis in a prospective, longitudinal sample of medication-free, adolescents with MDD versus HCs. <b><i>Methods:</i></b> Twenty-eight adolescents with MDD (Children's Depression Rating Scale score ≥40) and 27 age and gender-matched HCs (age 14-17, 78% female) received a baseline resting 32-channel EEG. Brain-wide coherence between channel pairs was calculated for the frequency bands (alpha, beta, theta, and delta) and compared between MDD youth and HC. Random forest classifiers were used to predict individual MDD status using baseline qEEG coherence. Models were trained and tested using 10-repeated, 10-fold cross-validation, and performance was evaluated with the area under the receiver operating characteristic curve (AUC-ROC). The contribution of individual predictors was assessed using permutation importance. Model significance was assessed using permutation testing (B = 1000 resamples). <b><i>Results:</i></b> Random forest models predicted depression status with a trend-level of significance (mean AUC-ROC = 0.65, <i>p</i> = 0.08). Among the most predictive channel pairs, adolescent MDD was characterized by lower coherence in T7-P7 (<i>p</i> < 0.05), Fz-Cz, and Fp2-F8 as well as higher coherence in P4-O2 and Cz-Pz. <b><i>Conclusions:</i></b> This study provides preliminary evidence that multivariate patterns of qEEG may inform the diagnosis of adolescent MDD. Specific aberrant patterns of coherence within the default mode network and cognitive control network were characteristic of adolescent MDD. Ongoing work will seek to replicate these findings in a larger cohort.</p>","PeriodicalId":15277,"journal":{"name":"Journal of child and adolescent psychopharmacology","volume":" ","pages":""},"PeriodicalIF":2.2000,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of child and adolescent psychopharmacology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1177/10445463251358742","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"PEDIATRICS","Score":null,"Total":0}
引用次数: 0

Abstract

Background: Improving early recognition and accurate diagnosis of major depressive disorder (MDD) in childhood is a pressing concern. Quantitative electroencephalogram (qEEG) may be an effective, noninvasive diagnostic biomarker for MDD. Prior work by our team demonstrated decreased resting connectivity, as measured by qEEG coherence, in a heterogeneous group of adolescents with MDD compared with age and gender-matched healthy controls (HCs). This study explored qEEG coherence as a predictor of MDD diagnosis in a prospective, longitudinal sample of medication-free, adolescents with MDD versus HCs. Methods: Twenty-eight adolescents with MDD (Children's Depression Rating Scale score ≥40) and 27 age and gender-matched HCs (age 14-17, 78% female) received a baseline resting 32-channel EEG. Brain-wide coherence between channel pairs was calculated for the frequency bands (alpha, beta, theta, and delta) and compared between MDD youth and HC. Random forest classifiers were used to predict individual MDD status using baseline qEEG coherence. Models were trained and tested using 10-repeated, 10-fold cross-validation, and performance was evaluated with the area under the receiver operating characteristic curve (AUC-ROC). The contribution of individual predictors was assessed using permutation importance. Model significance was assessed using permutation testing (B = 1000 resamples). Results: Random forest models predicted depression status with a trend-level of significance (mean AUC-ROC = 0.65, p = 0.08). Among the most predictive channel pairs, adolescent MDD was characterized by lower coherence in T7-P7 (p < 0.05), Fz-Cz, and Fp2-F8 as well as higher coherence in P4-O2 and Cz-Pz. Conclusions: This study provides preliminary evidence that multivariate patterns of qEEG may inform the diagnosis of adolescent MDD. Specific aberrant patterns of coherence within the default mode network and cognitive control network were characteristic of adolescent MDD. Ongoing work will seek to replicate these findings in a larger cohort.

评估定量脑电图一致性在青少年重度抑郁症中的预测效用:一种机器学习方法。
背景:提高儿童重度抑郁障碍(MDD)的早期识别和准确诊断是一个迫切需要关注的问题。定量脑电图(qEEG)可能是一种有效的、无创的MDD诊断生物标志物。我们团队先前的工作表明,与年龄和性别匹配的健康对照组(hc)相比,异质组MDD青少年的静息连通性(通过qEEG一致性测量)降低。本研究探讨了qEEG一致性作为MDD诊断的预测因子,在前瞻性,纵向样本中,无药物治疗的MDD青少年与hc。方法:28名MDD青少年(儿童抑郁评定量表得分≥40)和27名年龄和性别匹配的hc(14-17岁,78%为女性)接受基线静息32通道脑电图。计算频带(alpha, beta, theta和delta)通道对之间的全脑相干性,并比较MDD青年和HC之间的相干性。随机森林分类器使用基线qEEG一致性预测个体MDD状态。采用10次重复、10倍交叉验证对模型进行训练和检验,并用受试者工作特征曲线下面积(AUC-ROC)评估模型的性能。使用排列重要性评估个体预测因子的贡献。采用置换检验评估模型显著性(B = 1000个样本)。结果:随机森林模型预测抑郁状态具有趋势显著性(平均AUC-ROC = 0.65, p = 0.08)。在最具预测性的通道对中,青少年MDD的特征是T7-P7、Fz-Cz和Fp2-F8的一致性较低(p < 0.05),而P4-O2和Cz-Pz的一致性较高。结论:本研究为qEEG的多变量模式可能为青少年MDD的诊断提供了初步证据。默认模式网络和认知控制网络内特定的一致性异常模式是青少年重度抑郁症的特征。正在进行的工作将寻求在更大的人群中复制这些发现。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
3.60
自引率
5.30%
发文量
61
审稿时长
>12 weeks
期刊介绍: Journal of Child and Adolescent Psychopharmacology (JCAP) is the premier peer-reviewed journal covering the clinical aspects of treating this patient population with psychotropic medications including side effects and interactions, standard doses, and research on new and existing medications. The Journal includes information on related areas of medical sciences such as advances in developmental pharmacokinetics, developmental neuroscience, metabolism, nutrition, molecular genetics, and more. Journal of Child and Adolescent Psychopharmacology coverage includes: New drugs and treatment strategies including the use of psycho-stimulants, selective serotonin reuptake inhibitors, mood stabilizers, and atypical antipsychotics New developments in the diagnosis and treatment of ADHD, anxiety disorders, schizophrenia, autism spectrum disorders, bipolar disorder, eating disorders, along with other disorders Reports of common and rare Treatment Emergent Adverse Events (TEAEs) including: hyperprolactinemia, galactorrhea, weight gain/loss, metabolic syndrome, dyslipidemia, switching phenomena, sudden death, and the potential increase of suicide. Outcomes research.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信