Lillini Davide, Aironi Carlo, Migliorelli Lucia, Gabrielli Leonardo, Squartini Stefano
Department of Information Engineering, Università Politecnica delle Marche, Via Brecce Bianche 12, 60131 Ancona, Italy.
Sensors (Basel). 2024 Dec 5;24(23):7782. doi: 10.3390/s24237782.
Sleep apnea syndrome (SAS) affects about 3-7% of the global population, but is often undiagnosed. It involves pauses in breathing during sleep, for at least 10 s, due to partial or total airway blockage. The current gold standard for diagnosing SAS is polysomnography (PSG), an intrusive procedure that depends on subjective assessment by expert clinicians. To address the limitations of PSG, we propose a decision support system, which uses a tracheal microphone for data collection and a deep learning (DL) approach-namely SiCRNN-to detect apnea events during overnight sleep recordings. Our proposed SiCRNN processes Mel spectrograms using a Siamese approach, integrating a convolutional neural network (CNN) backbone and a bidirectional gated recurrent unit (GRU). The final detection of events is performed using an unsupervised clustering algorithm, specifically . Multiple experimental runs were carried out to determine the optimal network configuration and the most suitable type and frequency range for the input data. Tests with data from eight patients showed that our method can achieve a Recall score of up to 95% for events. We also compared the proposed approach to a fully convolutional baseline, recently introduced in the literature, highlighting the effectiveness of the Siamese training paradigm in improving the identification of SAS.
睡眠呼吸暂停综合征（SAS）影响着全球约3%至7%的人口，但往往未被诊断出来。它涉及睡眠期间由于部分或完全气道阻塞导致的至少持续10秒的呼吸暂停。目前诊断SAS的金标准是多导睡眠图（PSG），这是一种侵入性程序，依赖于专家临床医生的主观评估。为了解决PSG的局限性，我们提出了一种决策支持系统，该系统使用气管麦克风进行数据收集，并采用深度学习（DL）方法——即SiCRNN——来检测夜间睡眠记录期间的呼吸暂停事件。我们提出的SiCRNN使用暹罗方法处理梅尔频谱图，集成了卷积神经网络（CNN）主干和双向门控循环单元（GRU）。事件的最终检测使用无监督聚类算法，具体来说是 。进行了多次实验运行以确定最佳网络配置以及输入数据的最合适类型和频率范围。对八名患者的数据进行测试表明，我们的方法对于 事件可以实现高达95%的召回率。我们还将所提出的方法与文献中最近引入的全卷积基线进行了比较，突出了暹罗训练范式在改善SAS识别方面的有效性。
