性别、脑区和脑电图频带复杂度分析在帕金森病递归图和机器学习分类中的意义

IF 2.4 4区 医学 Q3 ENGINEERING, BIOMEDICAL
Divya Sasidharan, V Sowmya, E A Gopalakrishnan
{"title":"性别、脑区和脑电图频带复杂度分析在帕金森病递归图和机器学习分类中的意义","authors":"Divya Sasidharan, V Sowmya, E A Gopalakrishnan","doi":"10.1007/s13246-025-01521-5","DOIUrl":null,"url":null,"abstract":"<p><p>Parkinson Disease (PD) is a complex neurological disorder attributed by loss of neurons generating dopamine in the SN per compacta. Electroencephalogram (EEG) plays an important role in diagnosing PD as it offers a non-invasive continuous assessment of the disease progression and reflects these complex patterns. This study focuses on the non-linear analysis of resting state EEG signals in PD, with a gender-specific, brain region-specific, and EEG band-specific approach, utilizing recurrence plots (RPs) and machine learning (ML) algorithms for classification. For this an open EEG dataset consisting of 14 PD and 14 healthy (HC) subjects is utilized. Recurrence plots and cross-recurrence plots (CRPs) were constructed for each frequency band and brain region, extracting complexity measures such as determinism (DET) and entropy (ENT). The interpretability of the ML model decisions is investigated using explainability technique. The scattered distribution of points in RPs of male PD individuals reflects the complex and dynamic nature of abnormal brain function. Also, CRPs confirms the enhanced effect of Beta Gamma synchronization during PD in the Parietal region. Low DET and high ENT corresponds to the complex non-linear characteristics of EEG signals and brain neuronal circuits during PD condition in male subjects. The extracted recurrence features served as inputs to the ML models, which achieved high classification performance, across all the scenarios. This study demonstrates the potential of recurrence plot-based complexity analysis combined with machine learning for the gender-specific, region-specific, and band-specific assessment of EEG signals during resting state in Parkinson's disease.</p>","PeriodicalId":48490,"journal":{"name":"Physical and Engineering Sciences in Medicine","volume":" ","pages":""},"PeriodicalIF":2.4000,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Significance of gender, brain region and EEG band complexity analysis for Parkinson's disease classification using recurrence plots and machine learning algorithms.\",\"authors\":\"Divya Sasidharan, V Sowmya, E A Gopalakrishnan\",\"doi\":\"10.1007/s13246-025-01521-5\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Parkinson Disease (PD) is a complex neurological disorder attributed by loss of neurons generating dopamine in the SN per compacta. Electroencephalogram (EEG) plays an important role in diagnosing PD as it offers a non-invasive continuous assessment of the disease progression and reflects these complex patterns. This study focuses on the non-linear analysis of resting state EEG signals in PD, with a gender-specific, brain region-specific, and EEG band-specific approach, utilizing recurrence plots (RPs) and machine learning (ML) algorithms for classification. For this an open EEG dataset consisting of 14 PD and 14 healthy (HC) subjects is utilized. Recurrence plots and cross-recurrence plots (CRPs) were constructed for each frequency band and brain region, extracting complexity measures such as determinism (DET) and entropy (ENT). The interpretability of the ML model decisions is investigated using explainability technique. The scattered distribution of points in RPs of male PD individuals reflects the complex and dynamic nature of abnormal brain function. Also, CRPs confirms the enhanced effect of Beta Gamma synchronization during PD in the Parietal region. Low DET and high ENT corresponds to the complex non-linear characteristics of EEG signals and brain neuronal circuits during PD condition in male subjects. The extracted recurrence features served as inputs to the ML models, which achieved high classification performance, across all the scenarios. This study demonstrates the potential of recurrence plot-based complexity analysis combined with machine learning for the gender-specific, region-specific, and band-specific assessment of EEG signals during resting state in Parkinson's disease.</p>\",\"PeriodicalId\":48490,\"journal\":{\"name\":\"Physical and Engineering Sciences in Medicine\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":2.4000,\"publicationDate\":\"2025-01-27\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Physical and Engineering Sciences in Medicine\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1007/s13246-025-01521-5\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENGINEERING, BIOMEDICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Physical and Engineering Sciences in Medicine","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s13246-025-01521-5","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, BIOMEDICAL","Score":null,"Total":0}
引用次数: 0

摘要

帕金森氏病(PD)是一种复杂的神经系统疾病,其病因是神经突触中产生多巴胺的神经元缺失。脑电图(EEG)在诊断PD中发挥着重要作用,因为它提供了对疾病进展的非侵入性连续评估,并反映了这些复杂的模式。本研究主要针对PD患者静息状态脑电图信号进行非线性分析,采用性别、脑区和频段特异性方法,利用递归图(RPs)和机器学习(ML)算法进行分类。为此,使用了由14名PD和14名健康(HC)受试者组成的开放EEG数据集。在每个频带和脑区构建递归图和交叉递归图,提取确定性(DET)和熵(ENT)等复杂性度量。利用可解释性技术研究机器学习模型决策的可解释性。男性PD个体RPs点的分散分布反映了异常脑功能的复杂性和动态性。此外,crp证实了PD期间顶叶区β - γ同步的增强作用。低DET和高ENT对应了男性PD状态下脑电图信号和脑神经回路的复杂非线性特征。提取的递归特征作为ML模型的输入,在所有场景中都取得了很高的分类性能。这项研究证明了基于递归图的复杂性分析结合机器学习在帕金森病静息状态下对脑电信号进行性别、区域和频带特异性评估的潜力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Significance of gender, brain region and EEG band complexity analysis for Parkinson's disease classification using recurrence plots and machine learning algorithms.

Parkinson Disease (PD) is a complex neurological disorder attributed by loss of neurons generating dopamine in the SN per compacta. Electroencephalogram (EEG) plays an important role in diagnosing PD as it offers a non-invasive continuous assessment of the disease progression and reflects these complex patterns. This study focuses on the non-linear analysis of resting state EEG signals in PD, with a gender-specific, brain region-specific, and EEG band-specific approach, utilizing recurrence plots (RPs) and machine learning (ML) algorithms for classification. For this an open EEG dataset consisting of 14 PD and 14 healthy (HC) subjects is utilized. Recurrence plots and cross-recurrence plots (CRPs) were constructed for each frequency band and brain region, extracting complexity measures such as determinism (DET) and entropy (ENT). The interpretability of the ML model decisions is investigated using explainability technique. The scattered distribution of points in RPs of male PD individuals reflects the complex and dynamic nature of abnormal brain function. Also, CRPs confirms the enhanced effect of Beta Gamma synchronization during PD in the Parietal region. Low DET and high ENT corresponds to the complex non-linear characteristics of EEG signals and brain neuronal circuits during PD condition in male subjects. The extracted recurrence features served as inputs to the ML models, which achieved high classification performance, across all the scenarios. This study demonstrates the potential of recurrence plot-based complexity analysis combined with machine learning for the gender-specific, region-specific, and band-specific assessment of EEG signals during resting state in Parkinson's disease.

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
CiteScore
8.40
自引率
4.50%
发文量
110
×
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