文献速递睡眠呼吸障碍

利用非接触式设备的声学数据预测氧减饱和度:一项概念验证研究

Prediction of Oxygen Desaturation by Using Sound Data From a Noncontact Device: A Proof-of-Concept Study.
PubMed 文献 · Laryngoscope · 2021-12-07

这项回顾性研究纳入116例因打鼾或睡眠呼吸暂停就诊睡眠中心的患者,在整夜多导睡眠监测期间用麦克风采集睡眠呼吸声,降噪后分割为5秒窗口提取特征,通过二分类和回归分析从声音数据估计氧减饱和度指数(ODI)。ODI截断值5、15、30次/小时对应的曲线下面积分别为0.88、0.93、0.91,准确率分别为85.34、86.21、87.07;回归分析相关系数为0.80、平均绝对误差9.60次/小时;加入BMI和年龄后模型2、3的相关系数和平均绝对误差分别为0.82、9.44次/小时和0.81、9.6次/小时。作者认为从睡眠声音预测ODI似乎是可行的,加入BMI等临床特征可能提高整体预测能力。

要点

  • ODI截断值5、15、30次/小时时曲线下面积分别为0.88、0.93、0.91,准确率分别为85.34、86.21、87.07。
  • 回归分析相关系数0.80、平均绝对误差9.60次/小时;加入BMI(模型2)后为0.82、9.44次/小时。
  • 作者认为从睡眠声音预测ODI似乎可行,加入BMI等临床特征可能提高整体预测能力。

核心结论

  • 从睡眠声音预测氧减饱和度指数似乎是可行的。
  • 加入BMI等额外临床特征可能提高整体预测能力。

研究设计与样本

  • 回顾性研究,纳入因打鼾或睡眠呼吸暂停就诊睡眠中心并接受整夜实验室多导睡眠监测的116例患者。
  • 监测期间用麦克风录制声音,降噪后分割为5秒窗口并提取特征。
  • 采用二分类和回归分析从睡眠声音估计氧减饱和度指数(模型1),并加入BMI(模型2)、BMI和年龄(模型3)重新测试。

主要发现

  • 全部患者平均年龄50.4±16.7岁,平均呼吸暂停低通气指数23.0±24.0次/小时。
  • 二分类分析中,ODI截断值5、15、30次/小时对应的曲线下面积分别为0.88、0.93、0.91,准确率分别为85.34、86.21、87.07。
  • 回归分析中相关系数为0.80,平均绝对误差为9.60次/小时。
  • 模型2的相关系数为0.82、平均绝对误差为9.44次/小时;模型3的相关系数为0.81、平均绝对误差为9.6次/小时。

关键数值与推荐

  • ODI截断值5次/小时:曲线下面积0.88,准确率85.34。
  • ODI截断值15次/小时:曲线下面积0.93,准确率86.21。
  • ODI截断值30次/小时:曲线下面积0.91,准确率87.07。

临床怎么用

  • 作者认为从睡眠声音估计ODI似乎可行。
  • 作者认为加入BMI等临床特征可能提高整体预测能力。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

OBJECTIVES/HYPOTHESIS: Prediction of the apnea-hypopnea index (AHI) from breathing sounds during sleep could be used to prescreen for obstructive sleep apnea (OSA). In addition, the oxygen desaturation index (ODI) is a known risk factor for developing cardiovascular disease in OSA patients. This study focused on estimation of ODI from a noncontact manner from sleep breathing sounds. STUDY DESIGN: Retrospective study. METHODS: Patients who visited the sleep center due to snoring or sleep apnea underwent polysomnography in lab overnight. Sound recordings were made during polysomnography using a microphone. After noise reduction, the sound data were segmented into 5 seconds windows and features were extracted. Binary classification and regression analyses were performed to estimate the ODI during sleep (model 1). This was re-tested after inclusion of body mass index (BMI) and age as additional features (model 2: BMI only, model 3: BMI and age). RESULTS: We included 116 patients. The mean age and AHI of all patients were 50.4 ± 16.7 years and 23.0 ± 24.0 events/hr. In binary classification, for ODI cutoff values of 5, 15, and 30 events/hr, the areas under the curve were 0.88, 0.93, 0.91, respectively, and accuracies were 85.34, 86.21, and 87.07, respectively. In regression analysis, the correlation coefficient and mean absolute error were 0.80 and 9.60 events/hr, respectively. In models 2 and 3, the correlation coefficient and mean absolute error were 0.82, 9.44 events/hr and 0.81, 9.6 events/hr, respectively. CONCLUSION: Prediction of ODI from sleep sound seems to be feasible. Additional clinical feature such as BMI may increase overall predictability. LEVEL OF EVIDENCE: 4 Laryngoscope, 132:901-905, 2022.

来源:Laryngoscope,查看原文。版权归原作者所有。

引用

  1. Kim JW, Shin J, Lee K, et al. Prediction of Oxygen Desaturation by Using Sound Data From a Noncontact Device: A Proof-of-Concept Study. Laryngoscope. 2021. PMID: 34873695. doi:10.1002/lary.29971

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。