Hornero Roberto, Kheirandish-Gozal Leila, Gutiérrez-Tobal Gonzalo C, Philby Mona F, Alonso-Álvarez María Luz, Álvarez Daniel, Dayyat Ehab A, Xu Zhifei, Huang Yu-Shu, Tamae Kakazu Maximiliano, Li Albert M, Van Eyck Annelies, Brockmann Pablo E, Ehsan Zarmina, Simakajornboon Narong, Kaditis Athanasios G, Vaquerizo-Villar Fernando, Crespo Sedano Andrea, Sans Capdevila Oscar, von Lukowicz Magnus, Terán-Santos Joaquín, Del Campo Félix, Poets Christian F, Ferreira Rosario, Bertran Katalina, Zhang Yamei, Schuen John, Verhulst Stijn, Gozal David
1 Biomedical Engineering Group, University of Valladolid, Valladolid, Spain.
2 Section of Sleep Medicine, Department of Pediatrics, Pritzker School of Medicine, Biological Sciences Division, University of Chicago, Chicago, Illinois.
Am J Respir Crit Care Med. 2017 Dec 15;196(12):1591-1598. doi: 10.1164/rccm.201705-0930OC.
The vast majority of children around the world undergoing adenotonsillectomy for obstructive sleep apnea-hypopnea syndrome (OSA) are not objectively diagnosed by nocturnal polysomnography because of access availability and cost issues. Automated analysis of nocturnal oximetry (nSp), which is readily and globally available, could potentially provide a reliable and convenient diagnostic approach for pediatric OSA.
Deidentified nSp recordings from a total of 4,191 children originating from 13 pediatric sleep laboratories around the world were prospectively evaluated after developing and validating an automated neural network algorithm using an initial set of single-channel nSp recordings from 589 patients referred for suspected OSA.
The automatically estimated apnea-hypopnea index (AHI) showed high agreement with AHI from conventional polysomnography (intraclass correlation coefficient, 0.785) when tested in 3,602 additional subjects. Further assessment on the widely used AHI cutoff points of 1, 5, and 10 events/h revealed an incremental diagnostic ability (75.2, 81.7, and 90.2% accuracy; 0.788, 0.854, and 0.913 area under the receiver operating characteristic curve, respectively).
Neural network-based automated analyses of nSp recordings provide accurate identification of OSA severity among habitually snoring children with a high pretest probability of OSA. Thus, nocturnal oximetry may enable a simple and effective diagnostic alternative to nocturnal polysomnography, leading to more timely interventions and potentially improved outcomes.
由于可及性和成本问题，全球绝大多数因阻塞性睡眠呼吸暂停低通气综合征（OSA）接受腺样体扁桃体切除术的儿童未通过夜间多导睡眠图进行客观诊断。夜间脉搏血氧饱和度仪（nSp）的自动分析在全球范围内都很容易获得，有可能为儿童OSA提供一种可靠且便捷的诊断方法。
在使用来自589例疑似OSA患者的初始单通道nSp记录开发并验证自动神经网络算法后，对来自全球13个儿科睡眠实验室的总共4191名儿童的匿名nSp记录进行前瞻性评估。
在另外3602名受试者中进行测试时，自动估计的呼吸暂停低通气指数（AHI）与传统多导睡眠图的AHI显示出高度一致性（组内相关系数，0.785）。对广泛使用的AHI截断点1、5和10次/小时的进一步评估显示出递增的诊断能力（准确率分别为75.2%、81.7%和90.2%；受试者操作特征曲线下面积分别为0.788、0.854和0.913）。
基于神经网络的nSp记录自动分析能够准确识别习惯性打鼾且OSA预测试概率高的儿童的OSA严重程度。因此，夜间脉搏血氧饱和度测定可能成为夜间多导睡眠图的一种简单有效的诊断替代方法，从而实现更及时的干预并可能改善预后。
