基于静息态脑电图的抑郁症患者支持向量机分类。

IF 0.4 4区 医学 Q4 MEDICINE, RESEARCH & EXPERIMENTAL
Asian Biomedicine Pub Date : 2024-10-31 eCollection Date: 2024-10-01 DOI:10.2478/abm-2024-0029
Chia-Yen Yang, Yin-Zhen Chen
{"title":"基于静息态脑电图的抑郁症患者支持向量机分类。","authors":"Chia-Yen Yang, Yin-Zhen Chen","doi":"10.2478/abm-2024-0029","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Depression is one of the most common mental disorders. Although depression is typically diagnosed by identifying specific symptoms and through history, no recognized standard for depression diagnosis exists. This assures the development of objective diagnostic tools for depression.</p><p><strong>Objectives: </strong>We investigated the differences in the resting-state electroencephalograms (EEGs) of patients with depression and healthy controls (HCs) to distinguish patients from HCs by using a support vector machine (SVM) classifier with the following two feature selection approaches: t test and receiver operating characteristic analysis.</p><p><strong>Methods: </strong>We used the EEG data from the Patient Repository of EEG Data + Computational Tools; this study included 21 patients with depressive disorder (MDD) and 21 HCs. The relative frequency power, alpha interhemispheric asymmetry, left-right coherence, strength, clustering coefficient (CC), shortest path length, sample entropy (SampEn), multiscale entropy (MSE), and detrended fluctuation analysis (DFA) data were extracted to determine candidate EEG features associated with depression.</p><p><strong>Results: </strong>With the t-test selection, the SVM classifier demonstrated the highest performance with the accuracy, sensitivity, and specificity of 96.66%, 95.93%, and 97.550% for the eye-open condition and 91.33%, 90.59%, and 91.81% for the eye-closed condition, respectively. For comparisons of features in the 2 selection approaches, the most influential features were relative frequency power and left-right coherence.</p><p><strong>Conclusion: </strong>Using this information to distinguish patients with MDD from HC subjects with the SVM classifier resulted in a mean accuracy over 90%. Although this result may not be robust enough for clinical applications, further exploration is necessary given the simplicity, objectivity, and efficiency of the classifier.</p>","PeriodicalId":8501,"journal":{"name":"Asian Biomedicine","volume":null,"pages":null},"PeriodicalIF":0.4000,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11524675/pdf/","citationCount":"0","resultStr":"{\"title\":\"Support vector machine classification of patients with depression based on resting-state electroencephalography.\",\"authors\":\"Chia-Yen Yang, Yin-Zhen Chen\",\"doi\":\"10.2478/abm-2024-0029\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>Depression is one of the most common mental disorders. Although depression is typically diagnosed by identifying specific symptoms and through history, no recognized standard for depression diagnosis exists. This assures the development of objective diagnostic tools for depression.</p><p><strong>Objectives: </strong>We investigated the differences in the resting-state electroencephalograms (EEGs) of patients with depression and healthy controls (HCs) to distinguish patients from HCs by using a support vector machine (SVM) classifier with the following two feature selection approaches: t test and receiver operating characteristic analysis.</p><p><strong>Methods: </strong>We used the EEG data from the Patient Repository of EEG Data + Computational Tools; this study included 21 patients with depressive disorder (MDD) and 21 HCs. The relative frequency power, alpha interhemispheric asymmetry, left-right coherence, strength, clustering coefficient (CC), shortest path length, sample entropy (SampEn), multiscale entropy (MSE), and detrended fluctuation analysis (DFA) data were extracted to determine candidate EEG features associated with depression.</p><p><strong>Results: </strong>With the t-test selection, the SVM classifier demonstrated the highest performance with the accuracy, sensitivity, and specificity of 96.66%, 95.93%, and 97.550% for the eye-open condition and 91.33%, 90.59%, and 91.81% for the eye-closed condition, respectively. For comparisons of features in the 2 selection approaches, the most influential features were relative frequency power and left-right coherence.</p><p><strong>Conclusion: </strong>Using this information to distinguish patients with MDD from HC subjects with the SVM classifier resulted in a mean accuracy over 90%. Although this result may not be robust enough for clinical applications, further exploration is necessary given the simplicity, objectivity, and efficiency of the classifier.</p>\",\"PeriodicalId\":8501,\"journal\":{\"name\":\"Asian Biomedicine\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.4000,\"publicationDate\":\"2024-10-31\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11524675/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Asian Biomedicine\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.2478/abm-2024-0029\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/10/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"Q4\",\"JCRName\":\"MEDICINE, RESEARCH & EXPERIMENTAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Asian Biomedicine","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.2478/abm-2024-0029","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/10/1 0:00:00","PubModel":"eCollection","JCR":"Q4","JCRName":"MEDICINE, RESEARCH & EXPERIMENTAL","Score":null,"Total":0}
引用次数: 0

摘要

背景介绍抑郁症是最常见的精神疾病之一。虽然抑郁症的诊断通常是通过识别特定症状和病史来进行的,但目前还没有公认的抑郁症诊断标准。这就需要开发客观的抑郁症诊断工具:我们研究了抑郁症患者和健康对照组(HCs)静息状态脑电图(EEGs)的差异,通过使用支持向量机(SVM)分类器和以下两种特征选择方法来区分抑郁症患者和健康对照组:t 检验和接受者操作特征分析:我们使用了 "患者脑电图数据存储库+计算工具 "中的脑电图数据;该研究包括 21 名抑郁障碍(MDD)患者和 21 名健康对照者。我们提取了相对频率功率、α半球间不对称性、左右相干性、强度、聚类系数(CC)、最短路径长度、样本熵(SampEn)、多尺度熵(MSE)和去趋势波动分析(DFA)数据,以确定与抑郁症相关的候选脑电图特征:在 t 检验选择中,SVM 分类器表现最佳,睁眼状态下的准确率、灵敏度和特异性分别为 96.66%、95.93% 和 97.550%,闭眼状态下的准确率、灵敏度和特异性分别为 91.33%、90.59% 和 91.81%。在两种选择方法的特征比较中,影响最大的特征是相对频率功率和左右一致性:结论:使用 SVM 分类器将 MDD 患者与 HC 受试者区分开来的平均准确率超过了 90%。尽管这一结果在临床应用中可能不够稳健,但考虑到分类器的简便性、客观性和高效性,进一步的探索还是很有必要的。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Support vector machine classification of patients with depression based on resting-state electroencephalography.

Background: Depression is one of the most common mental disorders. Although depression is typically diagnosed by identifying specific symptoms and through history, no recognized standard for depression diagnosis exists. This assures the development of objective diagnostic tools for depression.

Objectives: We investigated the differences in the resting-state electroencephalograms (EEGs) of patients with depression and healthy controls (HCs) to distinguish patients from HCs by using a support vector machine (SVM) classifier with the following two feature selection approaches: t test and receiver operating characteristic analysis.

Methods: We used the EEG data from the Patient Repository of EEG Data + Computational Tools; this study included 21 patients with depressive disorder (MDD) and 21 HCs. The relative frequency power, alpha interhemispheric asymmetry, left-right coherence, strength, clustering coefficient (CC), shortest path length, sample entropy (SampEn), multiscale entropy (MSE), and detrended fluctuation analysis (DFA) data were extracted to determine candidate EEG features associated with depression.

Results: With the t-test selection, the SVM classifier demonstrated the highest performance with the accuracy, sensitivity, and specificity of 96.66%, 95.93%, and 97.550% for the eye-open condition and 91.33%, 90.59%, and 91.81% for the eye-closed condition, respectively. For comparisons of features in the 2 selection approaches, the most influential features were relative frequency power and left-right coherence.

Conclusion: Using this information to distinguish patients with MDD from HC subjects with the SVM classifier resulted in a mean accuracy over 90%. Although this result may not be robust enough for clinical applications, further exploration is necessary given the simplicity, objectivity, and efficiency of the classifier.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Asian Biomedicine
Asian Biomedicine 医学-医学:研究与实验
CiteScore
1.20
自引率
0.00%
发文量
24
审稿时长
6-12 weeks
期刊介绍: Asian Biomedicine: Research, Reviews and News (ISSN 1905-7415 print; 1875-855X online) is published in one volume (of 6 bimonthly issues) a year since 2007. [...]Asian Biomedicine is an international, general medical and biomedical journal that aims to publish original peer-reviewed contributions dealing with various topics in the biomedical and health sciences from basic experimental to clinical aspects. The work and authorship must be strongly affiliated with a country in Asia, or with specific importance and relevance to the Asian region. The Journal will publish reviews, original experimental studies, observational studies, technical and clinical (case) reports, practice guidelines, historical perspectives of Asian biomedicine, clinicopathological conferences, and commentaries Asian biomedicine is intended for a broad and international audience, primarily those in the health professions including researchers, physician practitioners, basic medical scientists, dentists, educators, administrators, those in the assistive professions, such as nurses, and the many types of allied health professionals in research and health care delivery systems including those in training.
×
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:481959085
Book学术官方微信