Abstract

Sleep apnea (SA) is a common sleep-related breathing disorder that can occur hundreds of times per night and can lead to catastrophic cardiovascular and neurological disorders if it happens frequently enough. Polysomnography (PSG) is the standard diagnostic tool for sleep apnea. However, it requires suspected patients to spend one to two nights in the lab and capture roughly 16 signals under professional supervision. The broad use of PSG in public health applications is hampered by complex processes. Some researchers have recently advocated using a single-lead ECG signal to detect SA. These techniques are based on the assumption that SA only uses the current ECG signal segment. SA, on the other hand, is time-dependent; that is, the SA of the preceding ECG segment has an impact on the current SA diagnosis. The authors present a time window artificial neural network that takes advantage of the time dependence between ECG signal segments while requiring no prior assumptions regarding training data distribution. The proposed method's performance has been greatly improved when compared to classic on-time window machine learning approaches as well as previous work after being verified on a genuine ECG signal dataset.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.