Beijing Key Laboratory of Pediatric Diseases of Otolaryngology, Head and Neck Surgery, Beijing Pediatric Research Institute, Beijing Children's Hospital, Capital Medical University, National Center for Children's Health, 56 Nanlishi Road, Xicheng District, Beijing 100045, China; School of Instrumentation Science and Opto-electronics Engineering, Beihang University (BUAA), 37 Xueyuan Road, Haidian District, Beijing 100191, China.
School of Instrumentation Science and Opto-electronics Engineering, Beihang University (BUAA), 37 Xueyuan Road, Haidian District, Beijing 100191, China.
Methods. 2022 Aug;204:361-367. doi: 10.1016/j.ymeth.2022.04.017. Epub 2022 May 6.
This study was performed to develop and evaluate a method of detecting pediatric obstructive sleep apnea (OSA) using a multilayer perceptron (MLP) model based on single-channel nocturnal oxygen saturation (SpO) with or without clinical data.
Polysomnography data for 888 children with OSA and 417 unaffected children were included. An MLP model was proposed based on the features obtained from SpO and combined features of SpO and clinical data to screen symptomatic children for OSA. The performance of the overall classification was evaluated with the receiver operating characteristics curve and the metrics of sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), positive likelihood ratio (LR+), negative likelihood ratio (LR-), and accuracy.
The sensitivity, specificity, PPV, NPV, LR+, LR-, and accuracy of the MLP model for SpO of an obstructive apnea-hypopnea index (OAHI) cutoff value of 1, 5, and 10 were 0.62-0.96, 0.11-0.97, 0.70-0.81, 0.55-0.93, 1.08-21.0, 0.39-0.39, and 0.69-0.91, respectively. The area under the receiver operating characteristics curve of an OAHI cutoff value of 1, 5, and 10 was 0.720, 0.842, and 0.922, respectively. After adding the clinical data of age, sex, body mass index, weight category, adenoid grade, or tonsil scale, the performance of the MLP model was basically at the same level as only single-channel SpO.
Application of this MLP model using single-channel SpO in children with snoring has high accuracy in the diagnosis of moderate to severe OSA but a poor effect in the diagnosis of mild OSA. The combination of clinical data did not significantly improve the diagnostic performance of the MLP model.
本研究旨在开发和评估一种基于单通道夜间血氧饱和度（SpO2）并结合临床数据的多层感知器（MLP）模型来检测小儿阻塞性睡眠呼吸暂停（OSA）的方法。
纳入了 888 例 OSA 患儿和 417 例无异常患儿的多导睡眠图数据。提出了一种 MLP 模型，该模型基于从 SpO2 中获取的特征以及 SpO2 和临床数据的组合特征，用于筛查有症状的 OSA 患儿。通过受试者工作特征曲线和敏感度、特异度、阳性预测值（PPV）、阴性预测值（NPV）、阳性似然比（LR+）、阴性似然比（LR-）和准确度等指标来评估整体分类性能。
对于阻塞性呼吸暂停-低通气指数（OAHI）截断值为 1、5 和 10 的 SpO2 的 MLP 模型，其敏感度、特异度、PPV、NPV、LR+、LR-和准确度分别为 0.62-0.96、0.11-0.97、0.70-0.81、0.55-0.93、1.08-21.0、0.39-0.39 和 0.69-0.91。OAHI 截断值为 1、5 和 10 时，受试者工作特征曲线下面积分别为 0.720、0.842 和 0.922。在添加年龄、性别、体重指数、体重类别、腺样体等级或扁桃体分级等临床数据后，MLP 模型的性能基本与仅使用单通道 SpO2 相同。
在有打鼾症状的儿童中应用该 MLP 模型使用单通道 SpO2 对中重度 OSA 的诊断具有较高的准确性，但对轻度 OSA 的诊断效果较差。结合临床数据并未显著改善 MLP 模型的诊断性能。
