Support vector machine prediction of obstructive sleep apnea in a large-scale Chinese clinical sample
Support vector machine prediction of obstructive sleep apnea in a large-scale Chinese clinical sample
复制标题
DOI：
10.1093/sleep/zsz295
复制
发表时间：
2020-07-01
期刊：
影响因子：
5.6
通讯作者：
Lai, Feipei
中科院分区：
文献类型：
--
作者：
Huang, Wen-Chi;Lee, Pei-Lin;Lai, Feipei
研究目的：多导睡眠描记术是诊断阻塞性睡眠呼吸暂停（OSA）的金标准，但其费用昂贵，而且使用往往受到限制。本研究的目的是开发一个临床上有用的支持向量机（SVM）为基础的预测模型，以确定患者的高概率OSA的nonsleep专科医师在临床practice.Methods：SVM模型开发使用的功能，常规收集的临床评价从6,875例中国患者提到睡眠诊所疑似OSA。三个呼吸暂停低通气指数（AHI）临界值，>= 5/h，>= 15/h和>= 30/h用于定义OSA的严重程度。连续特征和分类特征分别进行选择，并通过逐步向前特征选择进一步选择。建模通过五重交叉验证实现。对整个数据集和按性别和年龄分类的四个亚组的模型判别能力进行了评价（= 65岁[y/o]）结果：选择两个特征预测AHI临界值>= 5/h，分别选择6个特征预测>= 15/h和6个特征预测>= 30/h，以达到受试者工作特征下的面积（AUROC）0.82，0.80和0.78。敏感性分别为74.14%、75.18%、70.26%，特异性分别为74.71%、68.73%、70.30%。与logistic回归、柏林问卷、NoSAS评分和超解析线性回归模型（SLIM）评分系统相比，SVM模型表现更好，敏感性和特异性更平衡。判别能力是最好的男性= 65 y/o。结论：我们的模型提供了一个简单而准确的模式，早期识别患者OSA，并可能有助于优先考虑他们的睡眠研究。
Study Objectives: Polysomnography is the gold standard for diagnosis of obstructive sleep apnea (OSA) but it is costly and access is often limited. The aim of this study is to develop a clinically useful support vector machine (SVM)-based prediction model to identify patients with high probability of OSA for nonsleep specialist physician in clinical practice.Methods: The SVM model was developed using the features routinely collected at the clinical evaluation from 6,875 Chinese patients referred to sleep clinics for suspected OSA. Three apnea-hypopnea index (AHI) cutoffs, >= 5/h, >= 15/h, and >= 30/h were used to define the severity of OSA. The continuous and categorized features were selected separately and were further selected through stepwise forward feature selection. The modeling was achieved through fivefold cross-validation. The model discriminative ability was evaluated for the whole data set and four subgroups categorized with gender and age (= 65 years old [y/o]).Results: Two features were selected to predict AHI cutoff >= 5/h with six features selected for >= 15/h, and six features selected for >= 30/h, respectively, to reach Area under the Receiver Operating Characteristic (AUROC) 0.82, 0.80, and 0.78, respectively. The sensitivity was 74.14%, 75.18%, and 70.26%, while the specificity was 74.71%, 68.73%, and 70.30%, respectively. Compared to logistic regression, Berlin questionnaire, NoSAS Score, and Supersparse Linear Integer Model (SLIM) scoring system, the SVM model performs better with a more balanced sensitivity and specificity. The discriminative ability was best for male = 65 y/o.Conclusion: Our model provides a simple and accurate modality for early identification of patients with OSA and may potentially help prioritize them for sleep study.