基于智能手机记录的睡眠呼吸音评估睡眠呼吸暂停预测模型
该横断面研究纳入2015年8月至2019年8月于首尔大学盆唐医院睡眠中心就诊的423例患者,利用智能手机在整夜多导睡眠监测期间录音,以随机森林算法构建不同噪声处理和特征选择条件下的阻塞性睡眠呼吸暂停预测模型。结果显示,呼吸暂停低通气指数阈值为5、15、30事件/小时时准确率分别为88.2%、82.3%、81.7%,曲线下面积分别为0.90、0.89、0.90;未去噪且仅使用筛选特征的回归模型相关系数最高(r=0.78;95%CI,0.69-0.88)。
要点
- 智能手机睡眠呼吸音可构建较准确的阻塞性睡眠呼吸暂停预测模型
- 呼吸暂停低通气指数阈值5、15、30事件/小时下准确率分别为88.2%、82.3%、81.7%
- 未去噪且仅使用筛选特征的模型与实测呼吸暂停低通气指数相关性最高(r=0.78)
核心结论
- 利用智能手机记录的睡眠呼吸音可创建较准确的阻塞性睡眠呼吸暂停预测模型,未来研究应关注使用多种智能手机设备的真实生活录音。
研究设计与样本
- 横断面研究,纳入2015年8月至2019年8月于首尔大学盆唐医院睡眠中心因打鼾或睡眠呼吸暂停就诊的患者,共分析423例(平均[标准差]年龄48.1[12.8]岁;男性356例[84.1%])。
- 数据分为训练集256例(60.5%)和测试集167例(39.5%)。
- 在常规整夜实验室多导睡眠监测期间使用智能手机进行睡眠音频录制,采用随机森林算法分别按呼吸暂停低通气指数阈值5、15、30事件/小时进行二分类,并构建4种回归模型以预测实际呼吸暂停低通气指数。
- 数据分析时间为2019年9月至2020年9月。
主要发现
- 呼吸暂停低通气指数阈值为5、15、30事件/小时时,准确率分别为88.2%、82.3%、81.7%,曲线下面积分别为0.90、0.89、0.90。
- 在回归分析中,使用未去噪且仅使用筛选特征的录音获得最高相关系数(r=0.78;95%CI,0.69-0.88)。
- 呼吸暂停低通气指数(β=0.33;95%CI,0.24-0.42)和睡眠效率(β=-0.20;95%CI,-0.35至-0.05)与估计误差相关。
关键数值与推荐
- 呼吸暂停低通气指数阈值5事件/小时:准确率88.2%,曲线下面积0.90。
- 呼吸暂停低通气指数阈值15事件/小时:准确率82.3%,曲线下面积0.89。
- 呼吸暂停低通气指数阈值30事件/小时:准确率81.7%,曲线下面积0.90。
- 未去噪且仅使用筛选特征的回归模型:相关系数r=0.78(95%CI,0.69-0.88)。
临床怎么用
- 原文未据此给出推荐。
局限性
- 原文指出未来研究应关注使用多种智能手机设备的真实生活录音。
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
IMPORTANCE: Breathing sounds during sleep are an important characteristic feature of obstructive sleep apnea (OSA) and have been regarded as a potential biomarker. Breathing sounds during sleep can be easily recorded using a microphone, which is found in most smartphone devices. Therefore, it may be easy to implement an evaluation tool for prescreening purposes. OBJECTIVE: To evaluate OSA prediction models using smartphone-recorded sounds and identify optimal settings with regard to noise processing and sound feature selection. DESIGN, SETTING, AND PARTICIPANTS: A cross-sectional study was performed among patients who visited the sleep center of Seoul National University Bundang Hospital for snoring or sleep apnea from August 2015 to August 2019. Audio recordings during sleep were performed using a smartphone during routine, full-night, in-laboratory polysomnography. Using a random forest algorithm, binary classifications were separately conducted for 3 different threshold criteria according to an apnea hypopnea index (AHI) threshold of 5, 15, or 30 events/h. Four regression models were created according to noise reduction and feature selection from the input sound to predict actual AHI: (1) noise reduction without feature selection, (2) noise reduction with feature selection, (3) neither noise reduction nor feature selection, and (4) feature selection without noise reduction. Clinical and polysomnographic parameters that may have been associated with errors were assessed. Data were analyzed from September 2019 to September 2020. MAIN OUTCOMES AND MEASURES: Accuracy of OSA prediction models. RESULTS: A total of 423 patients (mean [SD] age, 48.1 [12.8] years; 356 [84.1%] male) were analyzed. Data were split into training (n = 256 [60.5%]) and test data sets (n = 167 [39.5%]). Accuracies were 88.2%, 82.3%, and 81.7%, and the areas under curve were 0.90, 0.89, and 0.90 for an AHI threshold of 5, 15, and 30 events/h, respectively. In the regression analysis, using recorded sounds that had not been denoised and had only selected attributes resulted in the highest correlation coefficient (r = 0.78; 95% CI, 0.69-0.88). The AHI (β = 0.33; 95% CI, 0.24-0.42) and sleep efficiency (β = -0.20; 95% CI, -0.35 to -0.05) were found to be associated with estimation error. CONCLUSIONS AND RELEVANCE: In this cross-sectional study, recorded sleep breathing sounds using a smartphone were used to create reasonably accurate OSA prediction models. Future research should focus on real-life recordings using various smartphone devices.
引用
- Cho SW, Jung SJ, Shin JH, et al. Evaluating Prediction Models of Sleep Apnea From Smartphone-Recorded Sleep Breathing Sounds. JAMA Otolaryngol Head Neck Surg. 2022. PMID: 35420648. doi:10.1001/jamaoto.2022.0244
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。