Sleep apnea detection from a single-lead ECG signal with automatic feature-extraction through a modified LeNet-5 convolutional neural network.

Tao Wang,Guohao Shen,Feng Hong,Changhua Lu

doi:10.7717/peerj.7731

Abstract

Sleep apnea (SA) is the most common respiratory sleep disorder, leading to some serious neurological and cardiovascular diseases if left untreated. The diagnosis of SA is traditionally made using Polysomnography (PSG). However, this method requires many electrodes and wires, as well as an expert to monitor the test. Several researchers have proposed instead using a single channel signal for SA diagnosis. Among these options, the ECG signal is one of the most physiologically relevant signals of SA occurrence, and one that can be easily recorded using a wearable device. However, existing ECG signal-based methods mainly use features (i.e. frequency domain, time domain, and other nonlinear features) acquired from ECG and its derived signals in order to construct the model. This requires researchers to have rich experience in ECG, which is not common. A convolutional neural network (CNN) is a kind of deep neural network that can automatically learn effective feature representation from training data and has been successfully applied in many fields. Meanwhile, most studies have not considered the impact of adjacent segments on SA detection. Therefore, in this study, we propose a modified LeNet-5 convolutional neural network with adjacent segments for SA detection. Our experimental results show that our proposed method is useful for SA detection, and achieves better or comparable results when compared with traditional machine learning methods.

Highlights

Sleep apnea (SA) is the most common respiratory disorder, caused by partial or complete obstructions of the upper respiratory tract (Li et al, 2018; Punjabi, 2008)
Compared with the Support Vector Machine (SVM) that had the second highest accuracy, the overall performances were better by 6.0%, 6.2%, 6.2% and 0.063, respectively
It can be seen from the results that K-Nearest Neighbor (KNN) had the lowest prediction accuracy among the five methods, probably because the features extracted from the Method SVM Logistic Regression (LR) KNN Multi-Layer Perception (MLP) LeNet-5

Summary

Introduction

Sleep apnea (SA) is the most common respiratory disorder, caused by partial or complete obstructions of the upper respiratory tract (Li et al, 2018; Punjabi, 2008). SA events can occur hundreds of times, and, if repeated over a long period of time, can cause serious neurological and cardiovascular complications such as memory loss, high blood pressure, congestive heart failure, and poor cognitive ability during the day (Khandoker, Palaniswami & Karmakar, 2009; Sharma & Sharma, 2016; Varon et al, 2015; Young et al, 1997). Subjects with an AHI > 5 combined with other symptoms (i.e., excessive sleepiness and poor cognitive ability during the day) are diagnosed with SA (Marcus et al, 2012; Song et al, 2016)

Objectives

Methods

Results

Conclusion