A Novel Approach Osa Detection Using Single-Lead Ecg Scalogram Based on Deep Neural Network

Abstract

Obstructive sleep apnea (OSA) is the most common and severe breathing dysfunction which frequently freezes the breathing for longer than 10[Formula: see text]s while sleeping. Polysomnography (PSG) is the conventional approach concerning the treatment of OSA detection. But, this approach is a costly and cumbersome process. To overcome the above complication, a satisfactory and novel technique for interpretation of sleep apnea using ECG were recording is under development. The methods for OSA analysis based on ECG were analyzed for numerous years. Early work concentrated on extracting features, which depend entirely on the experience of human specialists. A novel approach for the prediction of sleep apnea disorder based on the convolutional neural network (CNN) using a pre-trained (AlexNet) model is analyzed in this study. After filtering per-minute segment of the single-lead ECG recording accompanied by continuous wavelet transform (CWT), the 2D scalogram images are generated. Finally, CNN based on deep learning algorithm is adopted to enhance the classification performance. The efficiency of the proposed model is compared with the previous methods that used the same datasets. Proposed method based on CNN is able to achieve the accuracy of 86.22% with 90% sensitivity in per-minute segment OSA classification. Based on per-recording OSA diagnosis, our works correctly classify all the abnormal apneic recording with 100% accuracy. Our OSA analysis model using time-frequency scalogram generates excellent independent validation performance with different state-of-the-art OSA classification systems. Experimental results proved that the proposed method produces excellent performance outcomes with low cost and less complexity.

A Sleep Apnea Detection System Based on a One-Dimensional Deep Convolution Neural Network Model Using Single-Lead Electrocardiogram

“…These studies all adopted the MIT PhysioNet apnea-ECG database, and the released and withheld datasets were used for training and validation, respectively. Our study and the studies of Singh and Majumder [15], Wang et al [16], Figure 7. Curves of the number of feature extraction layers vs.…”

“…Recently, several studies have proposed neural networks to automatically learn features. Singh and Majumder [15] proposed a pre-trained two-dimensional (2D) AlexNet model based on a convolutional neural network (CNN) to extract the features from 2D time-frequency images of ECG signals, and a decision fusion method consisting of the KNN, SVM, LDA, and Ensemble classifiers to improve the sensitivity for detecting apnea events. Wang et al [16] proposed a modified LeNet-5 CNN model to extract features from 1D ECG signals and RR intervals, and to classify the normal and apnea events.…”

IGRNet: A Deep Learning Model for Non-Invasive, Real-Time Diagnosis of Prediabetes through Electrocardiograms

“…AlexNet [31] has been widely used in the field of image recognition, having been successfully employed many times in the diagnostic study of ECGs [32,33]. In this study, the number of neurons in the output layer was changed to two, and the final layer was updated based on the initialization model.…”

A Deep Learning Approach for Featureless Robust Quality Assessment of Intermittent Atrial Fibrillation Recordings from Portable and Wearable Devices

“…In the present study, a Morlet function, composed of a complex exponential function multiplied by a Gaussian window, was used as mother wavelet. This function has been broadly used in other ECG-based applications [ 36 , 38 , 40 , 42 ], because it shows equal variance in time and frequency [ 51 ]. Moreover, the number of scales was determined by the energy spread of the wavelet in time and frequency when 48 voices per octave was used.…”

“…To jointly exploit time and frequency information in the single-lead ECG recording, the algorithm is fed with a 2-D image obtained by turning the raw signal into a scalogram through a continuous Wavelet transform (CWT). This approach has been successfully used in other ECG-based applications, such as classification of arrhythmias [ 35 , 36 ], automatic identification of AF [ 37 , 38 ], detection of diabetic subjects [ 39 ], detection of sleep apnea [ 40 ], estimation of systolic blood pressure [ 41 ], and biometric identification of individuals [ 42 ].…”