中国组织工程研究

中国组织工程研究 ›› 2010, Vol. 14 ›› Issue (52): 9798-9802.doi: 10.3969/j.issn.1673-8225.2010. 52.027

• 数字化骨科 digital orthopedics • 上一篇    下一篇

模糊支持向量分类判别睡眠呼吸暂停综合征　

江丽仪，刘素娟，吴效明   

  1. 华南理工大学生物医学工程系，广东省广州市   510006
  • 出版日期:2010-12-24 发布日期:2010-12-24
  • 作者简介:江丽仪★，女，1985年生，广东省广州市人，汉族，华南理工大学生物医学工程在读硕士，主要从事生物医学信号的检测与处理的研究。 jiangliyi5@126.com

Diagnosis algorithm of sleep apnea syndrome using fuzzy support vector classification

Jiang Li-yi, Liu Su-juan, Wu Xiao-ming   

  1. Department of Biomedical Engineering, South China University of Technology, Guangzhou  510006, Guangdong Province, China
  • Online:2010-12-24 Published:2010-12-24
  • About author:Jiang Li-yi★, Studying for master’s degree, Department of Biomedical Engineering, South China University of Technology, Guangzhou 510006, Guangdong Province, China jiangliyi5@126.com

PDF

568

摘要：

背景：目前，睡眠呼吸暂停综合征的诊断主要依赖多导睡眠分析仪，该测量方法不但操作复杂、费用昂贵、分析耗时，而且在一定程度上影响患者的睡眠状况。
目的：分析心率变异性与睡眠呼吸暂停综合征的关系，提出一种简便准确的睡眠呼吸暂停综合征的检测算法。
方法：对38名健康者和28例不同程度睡眠呼吸暂停综合征患者的心率数据，采用去趋势波动分析法和自回归模型谱分析法，分析心率变异性与睡眠时相的相关性，并选取患者的性别、年龄以及心率变异性在各个睡眠阶段的标度指数及低频/高频比例作为睡眠呼吸暂停综合征初筛的特征参数，应用模糊支持向量机对睡眠呼吸暂停综合征阳性和阴性进行分类判别。
结果与结论：实验结果表明，模糊支持向量机的分类正确率达到93.94%。与现有睡眠呼吸暂停综合征的诊断方法相比，该方法测量简单方便，具有较高的诊断准确率。

关键词: 睡眠呼吸暂停综合征, 心率变异性, 模糊支持向量机, 去趋势波动分析, 自回归模型谱分析

Abstract:

BACKGROUND: Sleep apnea syndrome (SAS) is monitored and examined clinically with polysomnography. However, it is expensive and complex to operate, which significantly affects the natural sleep of human.
OBJECTIVE: To evaluate the value of heart rate variability (HRV) in diagnosing SAS, and propose a new method for SAS classification based on fuzzy support vector machine (FSVM).
METHODS: Detrended fluctuation analysis and autoregressive model spectrum estimation were used to analyze R-R interval sequence of 38 healthy subjects and 28 SAS subjects during various sleep stages. Scaling exponents of age, gender and HRV at each sleep stage, as well as low/high frequency were selected as SAS characteristic parameters. FSVM was used to classify SAS.
RESULTS AND CONCLUSION: Results indicate that the proposed method can diagnose SAS effectively and the classification accuracy rate of SAS is 93.94%. Compared with current SAS diagnosis methods, this method is more simple and accurate.

中图分类号: