夜间脉搏血氧监测对OSAHS预测与分类的价值
回顾性分析580例打鼾患者,提取11个血氧指标联合性别、年龄、BMI,用多元线性回归预测AHI(r=0.901,r²=0.848),用BP神经网络分类OSAHS严重程度,特异度和阴性预测率约90%。
要点
- MLR模型预测AHI的相关系数r=0.901,拟合优度r²=0.848。
- BPNN分类非OSAHS组敏感度88.46%±4.50%,重度组94.74%±0.76%。
- BPNN分类特异度和阴性预测率均在90%左右。
核心结论
- 基于SpO2监测信号,MLR模型预测AHI和BPNN模型多分类可能对OSAHS有较高预测和分类价值。
研究设计与样本
- 回顾性分析2018年1月至2019年12月天津医科大学总医院睡眠中心580例打鼾患者,男418例、女162例,年龄13~85(49±14)岁。
- 所有患者接受整夜多导睡眠监测,AHI为0~101.4(43.06±27.47)次/h。
- 非OSAHS组(AHI<5次/h)52例,轻度组(5<AHI≤15次/h)69例,中度组(15<AHI≤30次/h)98例,重度组(AHI>30次/h)361例。
主要发现
- MLR方法预测相关系数r=0.901(P<0.05),拟合优度r²=0.848(P<0.05)。
- BPNN分类非OSAHS组(AHI<5次/h)敏感度88.46%±4.50%。
- BPNN分类重度OSAHS组(AHI>30次/h)敏感度94.74%±0.76%。
- BPNN分类特异度和阴性预测率均在90%左右,敏感度和阳性预测率也较高。
关键数值与推荐
- 从SpO2信号提取13个指标,经Pearson相关分析筛选11个与AHI相关的血氧指标。
- 11个血氧指标包括3%氧减饱和度回升指数、SpO2低于90%曲线下面积、最低SpO2平均值、最低SpO2、平均SpO2及SpO2低于95%、90%、85%、80%、75%、70%的时间百分比。
- 全部特征为11个血氧指标加性别、年龄、BMI。
临床怎么用
- 夜间脉搏血氧监测信号可用于辅助预测AHI和分类OSAHS严重程度。
- MLR模型适用于AHI数值预测,BPNN模型适用于OSAHS严重程度多分类。
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
Objective: To explore the value of night pulse oximetry monitoring in the prediction and classification of obstructive sleep apnea hypopnea syndrome (OSAHS). Methods: From January 2018 to December 2019, 580 snoring patients admitted to the Sleep Center of Tianjin Medical University General Hospital were analyzed retrospectively. There were 418 males and 162 females, aging 13-85(49±14) years. All subjects underwent polysomnography, and the apnea hypopnea index (AHI)was 0-101.4(43.06±27.47) times/hour. There were 52 cases in the non-OSAHS group (AHI<5 times/h), 69 cases in the mild OSAHS group (5 times/h<AHI≤15 times/h), 98 cases in the moderate OSAHS group (15 times/h<AHI≤30 times/h), and 361 cases in the severe OSAHS group (30 times/h<AHI).Correlation analysis was performed between indicators extracted from SpO2 signal and AHI, and 11 blood oxygen indicators related to AHI were selected (3% oxygen reduction recovery index, the area of SpO2 under the 90% curve, average lowest SpO2, lowest SpO2, the average SpO2, the percentage of time SpO2 under 95%, 90%, 85%, 80%, 75%, 70%). Finally, gender, age and body mass index (BMI) were added. We ysed multiple linear regression (MLR) method to achieve AHI prediction, and back propagation neural network (BPNN) multi-classification method to achieve OSAHS severity classification. Statistical analysis was performed based on SPSS 25.0. The measurement data were analyzed using Pearson correlation test. Results: The MLR method achieved high prediction performance, with a prediction correlation coefficient r=0.901 (P<0.05) and a goodness of fit r2 = 0.848 (P<0.05).The specificity and negative prediction rate of BPNN method classification results were both around 90%, and the sensitivity and positive prediction rates were also high. Among them, the sensitivity of the non-OSAHS group (AHI<5 times/h) was 88.46%±4.50%, and the sensitivity of the severe OSAHS group (AHI>30 times/h) was 94.74%±0.76%. Conclusion: Based on the signals recorded by the SpO2 monitor, the methods of using MLR model for AHI prediction and using BPNN model for multi-classification may have higher value for the prediction and classification of OSAHS. 目的: 探讨夜间脉搏血氧饱和度(SpO2)监测对阻塞性睡眠呼吸暂停低通气综合征(OSAHS)预测和分类的价值。 方法: 回顾性分析2018年1月至2019年12月就诊于天津医科大学总医院睡眠中心的580例打鼾患者的临床资料,男418例,女162例,年龄13~85(49±14)岁,所有患者均接受了整夜多导睡眠监测(PSG),睡眠呼吸暂停低通气指数(AHI)为0~101.4(43.06±27.47)次/h。其中,非OSAHS组(AHI<5次/h)52例,轻度OSAHS组(5次/h<AHI≤15次/h)69例,中度OSAHS组(15次/h<AHI≤30次/h)98例,重度OSAHS组(AHI>30次/h)361例。从SpO2信号中提取13个指标,与AHI做相关性分析后,最终筛选11个与AHI相关的SpO2指标(3%氧减饱和度回升指数,SpO2低于90%曲线下面积,最低SpO2平均值,最低SpO2,平均SpO2,SpO2分别低于95%、90%、85%、80%、75%、70%的时间百分比),加入3个人口学指标[性别、年龄、体质量指数(BMI)]作为全部特征。分别利用多元线性回归(MLR)方法和反向传播神经网络(BPNN)多分类方法,进行AHI预测和OSAHS严重程度分类。采用SPSS 25.0软件进行统计学分析,计量资料均采用Pearson相关检验。 结果: 对MLR方法和BPNN多分类方法进行评价。MLR方法获得了较高预测性能,其模型拟合优度r2=0.848(P<0.05),预测相关系数r=0.901(P<0.05)。BPNN多分类方法分类结果的特异度和阴性预测率均在90%左右,敏感度和阳性预测率也较高,其中非OSAHS组分类敏感度为88.46%±4.50%,重度OSAHS组分类的敏感度为94.74%±0.76%。 结论: 基于夜间SpO2监测仪记录的信号,利用MLR模型进行AHI预测以及利用BPNN模型进行多分类的方法,可能对OSAHS有较高的预测和分类价值。.
引用
- Zhang J, Zhao D, Zhou ZX, et al. [Value of night pulse oximetry monitoring in obstructive sleep apnea hypopnea syndrome prediction and classification]. Zhonghua Jie He He Hu Xi Za Zhi. 2021. PMID: 33535324. doi:10.3760/cma.j.cn112147-20200724-00843
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。