卒中病灶特异性脑电特征:融合振荡、连接与不对称性的多尺度机器学习解码框架
研究纳入57例亚急性卒中患者(基底节、额颞/半卵圆中心、脑干病灶)和22名匹配对照,构建融合局部振荡、区域间连接与半球不对称性的多尺度静息脑电框架,结合机器学习解码病灶亚型。结果显示病灶相关脑电特征可区分卒中与对照及不同病灶亚型,支持脑电生物标志物用于客观分层与精准神经康复。
要点
- 多尺度脑电框架可识别不同卒中病灶的神经生理特征。
- CSP+LDA对卒中检测及病灶亚型分类获得较高准确率。
- 脑电-行为相关性未通过FDR校正,临床解释需谨慎。
核心结论
- 融合振荡、连接与不对称性的多尺度脑电框架可识别病灶相关神经生理特征,并实现可行的病灶亚型解码。
研究设计与样本
- 记录57例亚急性卒中患者(P1=22、P2=18、P3=17)与22名匹配对照的5分钟睁眼128通道静息脑电,计算ROI平均功率谱密度、电流源密度幅值平方相干及方向性脑对称指数。
- 采用CSP特征与LDA分类器,以留一受试者交叉验证评估,并设EEGNet基线比较。
主要发现
- FDR校正前,θ频段额-运动连接增强,α/β频段后部顶-枕连接减弱。
- 脑电-行为相关性未通过FDR校正。
关键数值与推荐
- CSP+LDA分类准确率:HC vs P为92.41%,P1 vs P3为94.87%,P2 vs P3为85.71%,P1 vs P2为82.50%;所有二分类AUC均超过0.85;三分类准确率达85.96%。
临床怎么用
- 该框架可作为卒中后神经生理异质性的分层工具,辅助病灶亚型解码与精准神经康复评估。
- 脑电-行为关联未通过校正,临床解读脑电特征与行为的关系时应谨慎。
局限性
- 脑电-行为相关性未通过FDR校正,关联证据有限。
- 样本量较小(57例患者、22名对照),结果需外部验证。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: Lesion location is a major source of post-stroke neurophysiological heterogeneity, yet most electroencephalography (EEG) studies analyze patients as a single group, limiting lesion-specific biomarkers and translation. We proposed a lesion-centric, multi-scale EEG framework integrating local oscillations, inter-regional connectivity, and hemispheric asymmetry with machine learning to characterize and decode basal ganglia (P1), fronto-temporal/centrum semiovale (P2), and brainstem (P3) lesions. METHODS: Five-minute eyes-open, 128-channel resting EEG ([Formula: see text]) was recorded in 57 subacute stroke patients (P1 = 22, P2 = 18, P3 = 17) and 22 matched controls. From artifact-minimized [Formula: see text] segments, ROI-averaged power spectral density (PSD) (θ: 4–[Formula: see text]; α: 7–[Formula: see text]; [Formula: see text]: 12–[Formula: see text]; peak α frequency), current source density (CSD)-based magnitude-squared coherence, and directional BSI (dirBSI) were computed. Between-group and subgroup differences were assessed using t-tests/Wilcoxon and ANOVA/Kruskal–Wallis with Benjamini–Hochberg FDR ([Formula: see text]). EEG–behavior associations were examined with Spearman correlations. For machine learning, common spatial patterns (CSP) features were classified using linear discriminant analysis (LDA) with leave-one-subject-out cross-validation. To align with clinical workflow, we report HC vs P as “stroke detection/screening” and patient-only P1/P2/P3 classification as “lesion subtype decoding for stratification” (along with pairwise P1 vs P2, P1 vs P3, and P2 vs P3 models). An EEGNet baseline was evaluated for comparison. RESULTS: Increased α power and a leftward peak α shift were observed in patients (HC: [Formula: see text]; P: [Formula: see text]; [Formula: see text]). Pre-FDR, θ-band frontal–motor connectivity was strengthened, while posterior P–O connectivity in α/[Formula: see text] was weakened. Ipsilesional dominance in θ was indicated by dirBSI (HC: [Formula: see text]; P: [Formula: see text]; [Formula: see text]). Across lesions, [Formula: see text] power differences in central/parietal/occipital ROIs were detected pre-FDR, with higher parietal [Formula: see text] in P3; α-band asymmetry was stronger in P1/P2 and more symmetric in P3 ([Formula: see text]). EEG–behavior correlations did not survive FDR. Using CSP+LDA, accuracies of 92.41% (HC vs P), 94.87% (P1 vs P3), 85.71% (P2 vs P3), and 82.50% (P1 vs P2) were achieved; all binary AUCs exceeded 0.85; three-class accuracy reached 85.96%. CONCLUSION: This multi-scale EEG framework identifies lesion-associated neurophysiological signatures and demonstrates feasible lesion subtype decoding, supporting the potential of EEG biomarkers for objective stratification and precision neurorehabilitation.
引用
- Liu W, Wei C, Lan Y, et al. Lesion-specific EEG signatures in stroke: a multi-scale framework integrating oscillations, connectivity, and asymmetry for machine learning decoding. J Neuroeng Rehabil. 2026. PMID: 41917996. doi:10.1186/s12984-026-01947-2
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。