Abstract
Sleep apnea (SA) is a ubiquitous sleep-related respiratory disease. It can occur hundreds of times at night, and its long-term occurrences can lead to some serious cardiovascular and neurological diseases. Polysomnography (PSG) is a commonly used diagnostic device for SA. But it requires suspected patients to sleep in the lab for one to two nights and records about 16 signals through expert monitoring. The complex processes hinder the widespread implementation of PSG in public health applications. Recently, some researchers have proposed using a single-lead ECG signal for SA detection. These methods are based on the hypothesis that the SA relies only on the current ECG signal segment. However, SA has time dependence; that is, the SA of the ECG segment at the previous moment has an impact on the current SA diagnosis. In this study, we develop a time window artificial neural network that can take advantage of the time dependence between ECG signal segments and does not require any prior assumptions about the distribution of training data. By verifying on a real ECG signal dataset, the performance of our method has been significantly improved compared to traditional non-time window machine learning methods as well as previous works.
Highlights
Sleep apnea (SA) is a ubiquitous sleep-related respiratory disease [1] that can be roughly divided into central sleep apnea (CSA) caused by lack of input of the central nervous system, obstructive sleep apnea (OSA) caused by collapse of the upper respiratory tract, and hypopnea caused by airflow reduction [2]
Each ECG signal of these recordings is segmented into a 1-minute segment, and the per-segment SA detection refers to determining whether each 1-minute segment is a SA or normal
It is an important basis for diagnosing SA for suspicious patients. erefore, we first analyze the performance of our proposed method as well as several non-time window methods including linear discriminant analysis (LDA), support vector machine (SVM), logistic regression (LR), and Multilayer Perceptron (MLP) in per-segment SA detection
Summary
Sleep apnea (SA) is a ubiquitous sleep-related respiratory disease [1] that can be roughly divided into central sleep apnea (CSA) caused by lack of input of the central nervous system, obstructive sleep apnea (OSA) caused by collapse of the upper respiratory tract, and hypopnea caused by airflow reduction [2]. Erefore, an alternative technique is needed that can be comfortably applied to SA detection To solve this problem, several researchers have proposed using a single-lead signal (i.e., pulse oximetry, snoring, electroencephalograph, or electrocardiogram) to automatically diagnose SA [5,6,7]. Existing studies mainly extract various features from the current ECG signal segment and use the traditional machine learning method to directly construct the SA detection model. E sensitivity and accuracy of their work are 88.9% and 84.7%, respectively These methods ignore the fact that HMM needs training data to satisfy a specific distribution [14, 15], resulting in limited performance improvements. Our study is the first study to use a time window for sleep apnea detection
Sign-in/Register to view highlights & summary 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 callDisclaimer: 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.
