Neurology Department, Massachusetts General Hospital, 55 Fruit Street, Boston, MA 02114, USA.
J Sleep Res. 2012 Feb;21(1):101-12. doi: 10.1111/j.1365-2869.2011.00935.x. Epub 2011 Jul 14.
Identifying predictors of subjective sleepiness and severity of sleep apnea are important yet challenging goals in sleep medicine. Classification algorithms may provide insights, especially when large data sets are available. We analyzed polysomnography and clinical features available from the Sleep Heart Health Study. The Epworth Sleepiness Scale and the apnea-hypopnea index were the targets of three classifiers: k-nearest neighbor, naive Bayes and support vector machine algorithms. Classification was based on up to 26 features including demographics, polysomnogram, and electrocardiogram (spectrogram). Naive Bayes was best for predicting abnormal Epworth class (0-10 versus 11-24), although prediction was weak: polysomnogram features had 16.7% sensitivity and 88.8% specificity; spectrogram features had 5.3% sensitivity and 96.5% specificity. The support vector machine performed similarly to naive Bayes for predicting sleep apnea class (0-5 versus >5): 59.0% sensitivity and 74.5% specificity using clinical features and 43.4% sensitivity and 83.5% specificity using spectrographic features compared with the naive Bayes classifier, which had 57.5% sensitivity and 73.7% specificity (clinical), and 39.0% sensitivity and 82.7% specificity (spectrogram). Mutual information analysis confirmed the minimal dependency of the Epworth score on any feature, while the apnea-hypopnea index showed modest dependency on body mass index, arousal index, oxygenation and spectrogram features. Apnea classification was modestly accurate, using either clinical or spectrogram features, and showed lower sensitivity and higher specificity than common sleep apnea screening tools. Thus, clinical prediction of sleep apnea may be feasible with easily obtained demographic and electrocardiographic analysis, but the utility of the Epworth is questioned by its minimal relation to clinical, electrocardiographic, or polysomnographic features.
确定主观嗜睡和睡眠呼吸暂停严重程度的预测因素是睡眠医学中的重要而具有挑战性的目标。分类算法可能会提供一些见解，尤其是在有大量数据集可用的情况下。我们分析了睡眠心脏健康研究中的多导睡眠图和临床特征。嗜睡量表和呼吸暂停低通气指数是三种分类器的目标：k-最近邻、朴素贝叶斯和支持向量机算法。分类基于多达 26 个特征，包括人口统计学、多导睡眠图和心电图（频谱图）。尽管预测效果较弱，但朴素贝叶斯算法最适合预测异常嗜睡等级（0-10 与 11-24）：多导睡眠图特征的敏感性为 16.7%，特异性为 88.8%；频谱图特征的敏感性为 5.3%，特异性为 96.5%。支持向量机在预测睡眠呼吸暂停等级（0-5 与>5）方面与朴素贝叶斯表现相似：使用临床特征的敏感性为 59.0%，特异性为 74.5%，使用频谱特征的敏感性为 43.4%，特异性为 83.5%，而朴素贝叶斯分类器的敏感性为 57.5%，特异性为 73.7%（临床），敏感性为 39.0%，特异性为 82.7%（频谱图）。互信息分析证实，嗜睡评分对任何特征的依赖性都很小，而呼吸暂停低通气指数对体重指数、觉醒指数、氧合和频谱图特征有适度的依赖性。使用临床或频谱图特征，呼吸暂停分类的准确性适中，与常见的睡眠呼吸暂停筛查工具相比，敏感性较低，特异性较高。因此，使用易于获得的人口统计学和心电图分析来预测睡眠呼吸暂停可能是可行的，但嗜睡量表的实用性受到其与临床、心电图或多导睡眠图特征的最小关系的质疑。
