Diagnostic deep learning algorithms that use resting EEG to distinguish major depressive disorder, bipolar disorder, and schizophrenia from each other and from healthy volunteers

双相情感障碍 重性抑郁障碍 精神分裂症(面向对象编程) 心理学 脑电图 精神科 心情 情绪障碍 听力学 焦虑 医学
作者
Maryam Ravan,Amin Noroozi,Mary Margarette Sanchez,Lee Borden,Nafia Alam,Pierre Flor-Henry,Sinisa Colic,Ahmad Khodayari-Rostamabad,Luciano Minuzzi,Gary Hasey
出处
期刊:Journal of Affective Disorders [Elsevier BV]
卷期号:346: 285-298 被引量:31
标识
DOI:10.1016/j.jad.2023.11.017
摘要

Mood disorders and schizophrenia affect millions worldwide. Currently, diagnosis is primarily determined by reported symptomatology. As symptoms may overlap, misdiagnosis is common, potentially leading to ineffective or destabilizing treatment. Diagnostic biomarkers could significantly improve clinical care by reducing dependence on symptomatic presentation. We used deep learning analysis (DLA) of resting electroencephalograph (EEG) to differentiate healthy control (HC) subjects (N = 239), from those with major depressive disorder (MDD) (N = 105), MDD-atypical (MDD-A) (N = 27), MDD-psychotic (MDD-P) (N = 35), bipolar disorder-depressed episode (BD-DE) (N = 71), BD-manic episode (BD-ME) (N = 49), and schizophrenia (SCZ) (N = 122) and also differentiate subjects with mental disorders on a pair-wise basis. DSM-III-R diagnoses were determined and supplemented by computerized Quick Diagnostic Interview Schedule. After EEG preprocessing, robust exact low-resolution electromagnetic tomography (ReLORETA) computed EEG sources for 82 brain regions. 20 % of all subjects were then set aside for independent testing. Feature selection methods were then used for the remaining subjects to identify brain source regions that are discriminating between diagnostic categories. Pair-wise classification accuracies between 90 % and 100 % were obtained using independent test subjects whose data were not used for training purposes. The most frequently selected features across various pairs are in the postcentral, supramarginal, and fusiform gyri, the hypothalamus, and the left cuneus. Brain sites discriminating SCZ from HC were mainly in the left hemisphere while those separating BD-ME from HC were on the right. The use of superseded DSM-III-R diagnostic system and relatively small sample size in some disorder categories that may increase the risk of overestimation. DLA of EEG could be trained to autonomously classify psychiatric disorders with over 90 % accuracy compared to an expert clinical team using standardized operational methods.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
CarryLJR的应助被刘大大采纳,获得10
刚刚
1秒前
1秒前
1秒前
草莓酱发布了新的文献求助10
1秒前
1秒前
1秒前
慕青的应助被cwm采纳,获得10
3秒前
DW的应助被寒冷白萱采纳,获得10
3秒前
藏羚羊发布了新的文献求助10
4秒前
英俊的铭的应助被xiao采纳,获得10
4秒前
唐璜发布了新的文献求助10
4秒前
唐璜发布了新的文献求助10
4秒前
唐璜发布了新的文献求助10
4秒前
唐璜发布了新的文献求助10
4秒前
哈哈完成签到,获得积分10
4秒前
脑洞疼的应助被778采纳,获得10
5秒前
Lizhe发布了新的文献求助10
5秒前
双人余发布了新的文献求助10
5秒前
taotao发布了新的文献求助10
5秒前
孜然味的拜拜肉完成签到,获得积分10
6秒前
脑洞疼的应助被PhDL1采纳,获得10
6秒前
华仔的应助被王坤采纳,获得10
7秒前
高登登关注了科研通微信公众号
7秒前
赘婿的应助被Lizhe采纳,获得10
9秒前
HKgryifho发布了新的文献求助10
9秒前
qzy完成签到,获得积分10
9秒前
摩登C位发布了新的文献求助10
10秒前
草莓酱完成签到,获得积分10
11秒前
11秒前
Owen的应助被xxxx采纳,获得10
11秒前
11秒前
11秒前
11秒前
上官若男的应助被太清采纳,获得10
11秒前
12秒前
13秒前
taotao完成签到,获得积分10
13秒前
13秒前
circusZ发布了新的文献求助10
14秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
Grapes 1000
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8178617
求助须知:如何正确求助?哪些是违规求助? 9569413
关于积分的说明 21804370
捐赠科研通 7773649
什么是DOI,文献DOI怎么找? 3432878
关于科研通互助平台的介绍 2556873
邀请新用户注册赠送积分活动 2478478