Cargando…

Automatic depression diagnosis through hybrid EEG and near-infrared spectroscopy features using support vector machine

Depression is a common mental disorder that seriously affects patients’ social function and daily life. Its accurate diagnosis remains a big challenge in depression treatment. In this study, we used electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) and measured the whole...

Descripción completa

Detalles Bibliográficos
Autores principales: Yi, Li, Xie, Guojun, Li, Zhihao, Li, Xiaoling, Zhang, Yizheng, Wu, Kai, Shao, Guangjian, Lv, Biliang, Jing, Huan, Zhang, Chunguo, Liang, Wenting, Sun, Jinyan, Hao, Zhifeng, Liang, Jiaquan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10483285/
https://www.ncbi.nlm.nih.gov/pubmed/37694121
http://dx.doi.org/10.3389/fnins.2023.1205931
_version_ 1785102343442792448
author Yi, Li
Xie, Guojun
Li, Zhihao
Li, Xiaoling
Zhang, Yizheng
Wu, Kai
Shao, Guangjian
Lv, Biliang
Jing, Huan
Zhang, Chunguo
Liang, Wenting
Sun, Jinyan
Hao, Zhifeng
Liang, Jiaquan
author_facet Yi, Li
Xie, Guojun
Li, Zhihao
Li, Xiaoling
Zhang, Yizheng
Wu, Kai
Shao, Guangjian
Lv, Biliang
Jing, Huan
Zhang, Chunguo
Liang, Wenting
Sun, Jinyan
Hao, Zhifeng
Liang, Jiaquan
author_sort Yi, Li
collection PubMed
description Depression is a common mental disorder that seriously affects patients’ social function and daily life. Its accurate diagnosis remains a big challenge in depression treatment. In this study, we used electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) and measured the whole brain EEG signals and forehead hemodynamic signals from 25 depression patients and 30 healthy subjects during the resting state. On one hand, we explored the EEG brain functional network properties, and found that the clustering coefficient and local efficiency of the delta and theta bands in patients were significantly higher than those in normal subjects. On the other hand, we extracted brain network properties, asymmetry, and brain oxygen entropy as alternative features, used a data-driven automated method to select features, and established a support vector machine model for automatic depression classification. The results showed the classification accuracy was 81.8% when using EEG features alone and increased to 92.7% when using hybrid EEG and fNIRS features. The brain network local efficiency in the delta band, hemispheric asymmetry in the theta band and brain oxygen sample entropy features differed significantly between the two groups (p < 0.05) and showed high depression distinguishing ability indicating that they may be effective biological markers for identifying depression. EEG, fNIRS and machine learning constitute an effective method for classifying depression at the individual level.
format Online
Article
Text
id pubmed-10483285
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-104832852023-09-08 Automatic depression diagnosis through hybrid EEG and near-infrared spectroscopy features using support vector machine Yi, Li Xie, Guojun Li, Zhihao Li, Xiaoling Zhang, Yizheng Wu, Kai Shao, Guangjian Lv, Biliang Jing, Huan Zhang, Chunguo Liang, Wenting Sun, Jinyan Hao, Zhifeng Liang, Jiaquan Front Neurosci Neuroscience Depression is a common mental disorder that seriously affects patients’ social function and daily life. Its accurate diagnosis remains a big challenge in depression treatment. In this study, we used electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) and measured the whole brain EEG signals and forehead hemodynamic signals from 25 depression patients and 30 healthy subjects during the resting state. On one hand, we explored the EEG brain functional network properties, and found that the clustering coefficient and local efficiency of the delta and theta bands in patients were significantly higher than those in normal subjects. On the other hand, we extracted brain network properties, asymmetry, and brain oxygen entropy as alternative features, used a data-driven automated method to select features, and established a support vector machine model for automatic depression classification. The results showed the classification accuracy was 81.8% when using EEG features alone and increased to 92.7% when using hybrid EEG and fNIRS features. The brain network local efficiency in the delta band, hemispheric asymmetry in the theta band and brain oxygen sample entropy features differed significantly between the two groups (p < 0.05) and showed high depression distinguishing ability indicating that they may be effective biological markers for identifying depression. EEG, fNIRS and machine learning constitute an effective method for classifying depression at the individual level. Frontiers Media S.A. 2023-08-24 /pmc/articles/PMC10483285/ /pubmed/37694121 http://dx.doi.org/10.3389/fnins.2023.1205931 Text en Copyright © 2023 Yi, Xie, Li, Li, Zhang, Wu, Shao, Lv, Jing, Zhang, Liang, Sun, Hao and Liang. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Yi, Li
Xie, Guojun
Li, Zhihao
Li, Xiaoling
Zhang, Yizheng
Wu, Kai
Shao, Guangjian
Lv, Biliang
Jing, Huan
Zhang, Chunguo
Liang, Wenting
Sun, Jinyan
Hao, Zhifeng
Liang, Jiaquan
Automatic depression diagnosis through hybrid EEG and near-infrared spectroscopy features using support vector machine
title Automatic depression diagnosis through hybrid EEG and near-infrared spectroscopy features using support vector machine
title_full Automatic depression diagnosis through hybrid EEG and near-infrared spectroscopy features using support vector machine
title_fullStr Automatic depression diagnosis through hybrid EEG and near-infrared spectroscopy features using support vector machine
title_full_unstemmed Automatic depression diagnosis through hybrid EEG and near-infrared spectroscopy features using support vector machine
title_short Automatic depression diagnosis through hybrid EEG and near-infrared spectroscopy features using support vector machine
title_sort automatic depression diagnosis through hybrid eeg and near-infrared spectroscopy features using support vector machine
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10483285/
https://www.ncbi.nlm.nih.gov/pubmed/37694121
http://dx.doi.org/10.3389/fnins.2023.1205931
work_keys_str_mv AT yili automaticdepressiondiagnosisthroughhybrideegandnearinfraredspectroscopyfeaturesusingsupportvectormachine
AT xieguojun automaticdepressiondiagnosisthroughhybrideegandnearinfraredspectroscopyfeaturesusingsupportvectormachine
AT lizhihao automaticdepressiondiagnosisthroughhybrideegandnearinfraredspectroscopyfeaturesusingsupportvectormachine
AT lixiaoling automaticdepressiondiagnosisthroughhybrideegandnearinfraredspectroscopyfeaturesusingsupportvectormachine
AT zhangyizheng automaticdepressiondiagnosisthroughhybrideegandnearinfraredspectroscopyfeaturesusingsupportvectormachine
AT wukai automaticdepressiondiagnosisthroughhybrideegandnearinfraredspectroscopyfeaturesusingsupportvectormachine
AT shaoguangjian automaticdepressiondiagnosisthroughhybrideegandnearinfraredspectroscopyfeaturesusingsupportvectormachine
AT lvbiliang automaticdepressiondiagnosisthroughhybrideegandnearinfraredspectroscopyfeaturesusingsupportvectormachine
AT jinghuan automaticdepressiondiagnosisthroughhybrideegandnearinfraredspectroscopyfeaturesusingsupportvectormachine
AT zhangchunguo automaticdepressiondiagnosisthroughhybrideegandnearinfraredspectroscopyfeaturesusingsupportvectormachine
AT liangwenting automaticdepressiondiagnosisthroughhybrideegandnearinfraredspectroscopyfeaturesusingsupportvectormachine
AT sunjinyan automaticdepressiondiagnosisthroughhybrideegandnearinfraredspectroscopyfeaturesusingsupportvectormachine
AT haozhifeng automaticdepressiondiagnosisthroughhybrideegandnearinfraredspectroscopyfeaturesusingsupportvectormachine
AT liangjiaquan automaticdepressiondiagnosisthroughhybrideegandnearinfraredspectroscopyfeaturesusingsupportvectormachine