An Automatic Screening Approach for Obstructive Sleep Apnea Diagnosis Based on Single-Lead Electrocardiogram | |
Chen, Lili ; Zhang, Xi ; Song, Changyue | |
刊名 | ieee transactions on automation science and engineering |
2015 | |
关键词 | Obstructive sleep apnea RR interval signal segmentation support vector machine HEART-RATE-VARIABILITY OXYGEN-SATURATION RECORDINGS RECOGNITION CLASSIFIER SIGNALS |
DOI | 10.1109/TASE.2014.2345667 |
英文摘要 | Traditional approaches for obstructive sleep apnea (OSA) diagnosis are apt to using multiple channels of physiological signals to detect apnea events by dividing the signals into equal-length segments, which may lead to incorrect apnea event detection and weaken the performance of OSA diagnosis. This paper proposes an automatic-segmentation-based screening approach with the single channel of Electrocardiogram (ECG) signal for OSA subject diagnosis, and the main work of the proposed approach lies in three aspects: (i) an automatic signal segmentation algorithm is adopted for signal segmentation instead of the equal-length segmentation rule; (ii) a local median filter is improved for reduction of the unexpected RR intervals before signal segmentation; (iii) the designed OSA severity index and additional admission information of OSA suspects are plugged into support vector machine (SVM) for OSA subject diagnosis. A real clinical example from PhysioNet database is provided to validate the proposed approach and an average accuracy of 97.41% for subject diagnosis is obtained which demonstrates the effectiveness for OSA diagnosis. Note to Practitioners-Automatic diagnosis of obstructive sleep apnea based on physiological signals is critical for healthcare service improvement. Equal-length segmentation of signals is adopted in current OSA diagnosis, in which each segment of signal requires inferences from physicians to determine the apnea events. However, this equal-length segmentation may bring possible misdetected apnea events, and finally lead to an incorrect diagnosis. This paper aims to reduce the number of misdetected apnea events by proposing an automatic segmentation rule with consideration of reasonable physiological interpretation. An OSA severity index which can be obtained from signal segments of each subject is designed. An SVM is employed to implement the final diagnosis. To fully implement this approach, it is necessary (i) to preprocess the RR intervals and eliminate unexpected signal points; (ii) to embed individual information of OSA suspects into an SVM. A real world case study has shown that the proposed diagnosis approach provided a satisfactory diagnosis accuracy.; Automation & Control Systems; SCI(E); EI; 0; ARTICLE; chenlili@coe.pku.edu.cn; xi.zhang@coe.pku.edu.cn; 1; 106-115; 12 |
语种 | 英语 |
内容类型 | 期刊论文 |
源URL | [http://ir.pku.edu.cn/handle/20.500.11897/154122] |
专题 | 工学院 |
推荐引用方式 GB/T 7714 | Chen, Lili,Zhang, Xi,Song, Changyue. An Automatic Screening Approach for Obstructive Sleep Apnea Diagnosis Based on Single-Lead Electrocardiogram[J]. ieee transactions on automation science and engineering,2015. |
APA | Chen, Lili,Zhang, Xi,&Song, Changyue.(2015).An Automatic Screening Approach for Obstructive Sleep Apnea Diagnosis Based on Single-Lead Electrocardiogram.ieee transactions on automation science and engineering. |
MLA | Chen, Lili,et al."An Automatic Screening Approach for Obstructive Sleep Apnea Diagnosis Based on Single-Lead Electrocardiogram".ieee transactions on automation science and engineering (2015). |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论