在间歇性SpO₂丢失下利用信号互补性的多模态呼吸事件检测

文献信息

中文摘要

研究目的： 当前用于自动睡眠呼吸暂停检测的多模态方法通常假设信号连续可用，尽管传感器脱落临床实践中很常见。我们评估了跨信号配置和缺失数据条件下的概率级晚期融合，以确定性能更多取决于信号互补性还是模态数量。
方法： 我们基于148例患者的EEG、ECG、SpO₂和腹部努力特征训练了随机森林基分类器。每个分类器生成三分类后验概率，将其拼接后输入元分类器以进行最终epoch级预测。不可靠的SpO₂ epoch仅从SpO₂基模型拟合中排除，但在元分类器训练和测试中保留，使用均匀占位概率[0.333, 0.333, 0.333]加上isBad质量标志。在37例留出患者中评估选定的单模态和多模态配置，以宏F1作为主要指标。按SpO₂质量分层的Bootstrap置信区间评估了脱落条件下的稳健性。
结果： 单独腹部努力达到宏F1 = 0.996。SpO₂ + 腹部努力达到最高宏F1 = 0.997，仅略高于单独腹部努力。ECG + EEG优于SpO₂ + ECG和SpO₂ + EEG，尽管缺乏直接的呼吸或氧合信息。SpO₂ + EEG表现下降（宏F1 = 0.739；低通气精确率 = 0.203）。将SpO₂加入ECG + EEG降低了性能（0.872 vs 0.899）。尽管SpO₂脱落率为30.7%，性能仍保持稳定。
结论： 在概率级晚期融合中，性能更多取决于信号互补性而非模态数量。质量感知的概率整合使得在真实SpO₂脱落条件下无需重新训练即可实现稳健分类，但固定epoch晚期融合限制了对时间错位血氧信息的利用。

英文摘要

STUDY OBJECTIVES: Current multimodal approaches for automated sleep apnea detection usually assume continuous signal availability, although sensor dropout is common in clinical practice. We evaluated probability-level late fusion across signal configurations and missing-data conditions to determine whether performance depends more on signal complementarity or modality count.
METHODS: We trained random forest base classifiers on EEG, ECG, SpO₂, and abdominal effort features from 148 patients. Each classifier generated three-class posterior probabilities, which were concatenated and input to a meta-classifier for final epoch-level prediction. Unreliable SpO₂ epochs were excluded only from SpO₂ base-model fitting but retained during meta-classifier training and testing using uniform placeholder probabilities [0.333, 0.333, 0.333] plus the isBad quality flag. Selected unimodal and multimodal configurations were evaluated in 37 held-out patients using macro-F1 as the primary metric. Bootstrap confidence intervals stratified by SpO₂ quality assessed robustness under dropout.
RESULTS: Abdominal effort alone achieved macro-F1 = 0.996. SpO₂ + abdominal effort achieved the highest macro-F1 = 0.997, only marginally above abdominal effort alone. ECG + EEG outperformed SpO₂ + ECG and SpO₂ + EEG despite lacking direct respiratory or oxygenation information. SpO₂ + EEG showed degraded performance (macro-F1 = 0.739; hypopnea precision = 0.203). Adding SpO₂ to ECG + EEG reduced performance (0.872 vs 0.899). Performance remained stable despite 30.7% SpO₂ dropout.
CONCLUSIONS: Within probability-level late fusion, performance depended more on signal complementarity than modality count. Quality-aware probability integration enabled robust classification under realistic SpO₂ dropout without retraining, but fixed-epoch late fusion limited exploitation of temporally misaligned oximetry information.