The obstructive sleep apnea-hypopnea (OSAH) syndrome is a very common and frequently undiagnosed sleep disorder. It is characterized by repeated events of partial (hypopnea) or total (apnea) obstruction of the upper airway while sleeping. This study makes use of a previously developed method called DAS-KSVD for multiclass structured dictionary learning to automatically detect individual events of apnea and hypopnea using only blood oxygen saturation signals. The method uses a combined discriminant measure which is capable of efficiently quantifying the degree of discriminability of each one of the atoms in a dictionary. DAS-KSVD was applied to detect and classify apnea and hypopnea events from signals obtained from the Sleep Heart Health Study database. For moderate to severe OSAH screening, a receiver operating characteristic curve analysis of the results shows an area under the curve of 0.957 and diagnostic sensitivity and specificity of 87.56% and 88.32%, respectively. These results represent improvements as compared to most state-of-the-art procedures. Hence, the method could be used for screening OSAH syndrome more reliably and conveniently, using only a pulse oximeter.

中文翻译：

---

使用血氧饱和度信号对呼吸暂停和呼吸不足事件进行自动评分

阻塞性睡眠呼吸暂停低通气 (OSAH) 综合征是一种非常常见且经常未被确诊的睡眠障碍。它的特点是睡眠时上呼吸道反复发生部分（呼吸不足）或完全（呼吸暂停）阻塞。本研究利用先前开发的称为 DAS-KSVD 的方法进行多类结构化字典学习，仅使用血氧饱和度信号自动检测呼吸暂停和呼吸不足的个体事件。该方法使用组合判别度量，该度量能够有效地量化字典中每个原子的可判别程度。DAS-KSVD 用于从睡眠心脏健康研究数据库中获得的信号中检测和分类呼吸暂停和呼吸不足事件。对于中度至重度 OSAH 筛查，结果的接受者操作特征曲线分析显示曲线下面积为0.957，诊断灵敏度和特异性分别为87.56%和88.32%。与大多数最先进的程序相比，这些结果代表了改进。因此，该方法可以更可靠、更方便地用于筛查 OSAH 综合征，仅使用脉搏血氧仪。