Leino Akseli, Nikkonen Sami, Kainulainen Samu, Korkalainen Henri, Töyräs Juha, Myllymaa Sami, Leppänen Timo, Ylä-Herttuala Salla, Westeren-Punnonen Susanna, Muraja-Murro Anu, Jäkälä Pekka, Mervaala Esa, Myllymaa Katja
Department of Clinical Neurophysiology, Diagnostic Imaging Center, Kuopio University Hospital, Kuopio, Finland; Department of Applied Physics, University of Eastern Finland, Kuopio, Finland.
Department of Clinical Neurophysiology, Diagnostic Imaging Center, Kuopio University Hospital, Kuopio, Finland; Department of Applied Physics, University of Eastern Finland, Kuopio, Finland.
Sleep Med. 2021 Mar;79:71-78. doi: 10.1016/j.sleep.2020.12.032. Epub 2020 Dec 31.
Current diagnostics of sleep apnea relies on the time-consuming manual analysis of complex sleep registrations, which is impractical for routine screening in hospitalized patients with a high probability for sleep apnea, e.g. those experiencing acute stroke or transient ischemic attacks (TIA). To overcome this shortcoming, we aimed to develop a convolutional neural network (CNN) capable of estimating the severity of sleep apnea in acute stroke and TIA patients based solely on the nocturnal oxygen saturation (SpO) signal. The CNN was trained with SpO signals derived from 1379 home sleep apnea tests (HSAT) of suspected sleep apnea patients and tested with SpO signals of 77 acute ischemic stroke or TIA patients. The CNN's performance was tested by comparing the estimated respiratory event index (REI) and oxygen desaturation index (ODI) with manually obtained values. Median estimation errors for REI and ODI in patients with stroke or TIA were 1.45 events/hour and 0.61 events/hour, respectively. Furthermore, based on estimated REI and ODI, 77.9% and 88.3% of these patients were classified into the correct sleep apnea severity categories. The sensitivity and specificity to identify sleep apnea (REI > 5 events/hour) were 91.8% and 78.6%, respectively. Moderate-to-severe sleep apnea was detected (REI > 15 events/hour) with sensitivity of 92.3% and specificity of 96.1%. The CNN analysis of the SpO signal has great potential as a simple screening tool for sleep apnea. This novel automatic method accurately detects sleep apnea in acute cerebrovascular disease patients and facilitates their referral for a differential diagnostic HSAT or polysomnography evaluation.
目前睡眠呼吸暂停的诊断依赖于对复杂睡眠记录进行耗时的人工分析，这对于住院的高概率睡眠呼吸暂停患者（例如经历急性中风或短暂性脑缺血发作 (TIA) 的患者）进行常规筛查是不切实际的。为了克服这一缺点，我们旨在开发一种卷积神经网络 (CNN)，该网络能够仅基于夜间血氧饱和度 (SpO) 信号来估计急性中风和 TIA 患者的睡眠呼吸暂停严重程度。该 CNN 使用来自 1379 例疑似睡眠呼吸暂停患者的家庭睡眠呼吸暂停测试 (HSAT) 的 SpO 信号进行训练，并使用 77 例急性缺血性中风或 TIA 患者的 SpO 信号进行测试。通过将估计的呼吸事件指数 (REI) 和氧去饱和指数 (ODI) 与人工获得的值进行比较来测试 CNN 的性能。中风或 TIA 患者中 REI 和 ODI 的中位数估计误差分别为 1.45 次/小时和 0.61 次/小时。此外，基于估计的 REI 和 ODI，这些患者中有 77.9% 和 88.3% 被分类到正确的睡眠呼吸暂停严重程度类别中。识别睡眠呼吸暂停（REI > 5 次/小时）的敏感性和特异性分别为 91.8% 和 78.6%。检测到中度至重度睡眠呼吸暂停（REI > 15 次/小时），敏感性为 92.3%，特异性为 96.1%。SpO 信号的 CNN 分析作为一种简单的睡眠呼吸暂停筛查工具具有很大潜力。这种新颖的自动方法能够准确检测急性脑血管疾病患者的睡眠呼吸暂停，并有助于他们转诊进行鉴别诊断 HSAT 或多导睡眠图评估。
