频域特征主导呼吸事件检测，为无感睡眠监测提供关键依据
Spectral Features Dominate BCG Respiratory-Event Detection: A Large-Scale Patient-Independent Comparison of Feature Groups in Sleep Apnea Patients
- 系统比较10类BCG特征，基于512传感器阵列与多导睡眠图同步数据
- 频域特征占30.3%判别力，结合时域特征达67%总判别信息
- 结果可指导未来无感睡眠监测系统中的特征筛选
无创球心动图（BCG）传感是长期睡眠呼吸暂停监测的有前景技术，但其信号特征中哪些最具区分性仍不明确。本研究基于文献指导，在155名接受住院评估的阻塞性睡眠呼吸暂停患者（52名女性，103名男性）中，使用512传感器电容压力垫同步采集BCG信号与多导睡眠图数据，对十类特征组进行患者无关的对比分析。从六个空间独立通道提取特征，构建了包含191维的特征向量，涵盖一般统计、时域、频域、小波、帧能量及非线性复杂度描述符。在严格的留一患者交叉验证下，随机森林与直方图梯度提升分别达到0.967和0.969的AUC-ROC，以及0.977和0.979的AUC-PR。特征重要性分析显示，频域特征主导判别：0.1–0.4 Hz呼吸频带功率贡献了全部空间通道30.3%的判别信息，自适应预处理后通道的傅里叶变换谱形描述符额外贡献15.1%。时域特征中的AUC与曲线长度提供主要补充证据（21.5%），而小波与非线性特征合计仅贡献10.4%。频域与时域特征共同占总判别信息的67%，表明一个精简、可解释的特征子集即可在患者无关验证中实现临床相关性能，为未来BCG系统中的特征选择提供了实证基础。
原文摘要 · Abstract (English)
Unobtrusive ballistocardiographic (BCG) sensing is a promising modality for long-term sleep-apnea monitoring, yet it remains unclear which signal features are most discriminative for respiratory-event detection. We present a literature-guided, patient-independent comparison of ten BCG feature groups using a 512-sensor capacitive pressure mat recorded simultaneously with respiratory polygraphy in 155 patients (52 female, 103 male) undergoing in-hospital evaluation for obstructive sleep apnea. Features were extracted from six spatially distinct signal channels, yielding a 191-dimensional feature vector spanning general statistical, time-domain, frequency-domain, wavelet, frame-energy, and nonlinear complexity descriptors. Under strict leave-one-patient-out cross-validation for binary classification of respiratory-event windows versus event-free reference windows, Random Forest and Histogram Gradient Boosting achieved AUC-ROC of 0.967 and 0.969 and AUC-PR of 0.977 and 0.979, respectively. Feature-importance analysis revealed that frequency-domain features dominate discrimination: breathing-band power in the 0.1-0.4 Hz range accounted for 30.3% of total discriminative information across all spatial channels, and Fast Fourier Transform spectral-shape descriptors of the adaptively preprocessed channel contributed a further 15.1%. AUC and curve-length features provided the main complementary time-domain evidence (21.5%), whereas wavelet-derived and nonlinear features contributed smaller secondary effects (10.4% combined across 59 features). Frequency-domain and time-domain features together accounted for 67% of total discriminative information, demonstrating that a compact, interpretable subset of the full feature library achieves clinically relevant performance under patient-independent validation and providing an empirical basis for feature selection in future BCG systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。