Electrocardiogram (ECG) is easily submerged in noise of the complex environment during remote medical treatment, and this affects the intelligent diagnosis of cardiovascular diseases. Considering this situation, this paper proposes an echo state network (ESN) denoising algorithm based on recursive least square (RLS) for ECG signals. The algorithm trains the ESN through the RLS method, and can automatically learn the deep nonlinear and differentiated characteristics in the noisy ECG data, and then the network can use these characteristic to separate out clear ECG signals automatically. In the experiment, the proposed method is compared with the wavelet transform with subband dependent threshold and the S-transform method by evaluating the signal-to-noise ratio and root mean square error. Experimental results show that the denoising accuracy is better and the low frequency component of the signal is well preserved. This method can effectively filter out complex noise and effectively preserve the effective information of ECG signals, which lays a foundation for the recognition of ECG signal feature waveform and the intelligent diagnosis of cardiovascular disease.
During long-term electrocardiogram (ECG) monitoring, various types of noise inevitably become mixed with the signal, potentially hindering doctors' ability to accurately assess and interpret patient data. Therefore, evaluating the quality of ECG signals before conducting analysis and diagnosis is crucial. This paper addresses the limitations of existing ECG signal quality assessment methods, particularly their insufficient focus on the 12-lead multi-scale correlation. We propose a novel ECG signal quality assessment method that integrates a convolutional neural network (CNN) with a squeeze and excitation residual network (SE-ResNet). This approach not only captures both local and global features of ECG time series but also emphasizes the spatial correlation among ECG signals. Testing on a public dataset demonstrated that our method achieved an accuracy of 99.5%, sensitivity of 98.5%, and specificity of 99.6%. Compared with other methods, our technique significantly enhances the accuracy of ECG signal quality assessment by leveraging inter-lead correlation information, which is expected to advance the development of intelligent ECG monitoring and diagnostic technology.
ObjectiveTo investigate the correlation between intima-media thickness (IMT) of carotid artery in color ultrasonography and the heart rate variability. MethodsA retrospective analysis was performed in 64 patients from West China Hospital of Sichuan University between March and May 2013. Carotid intima-media thickness was measured with color ultrasonography and dynamic electrocardiogram, and the heart rate variability was assayed at the same time. ResultsIMT in the cardiovascular disease group, combination group, coronary heart disease group and hypertension group was significantly thicker than the control group (P<0.05). The differences of SDNN and SDANN were statistically significant (P<0.05) between the combination group and the control group. There were 23 cases with IMT ≥ 1.0 mm in the cardiovascular disease group including 8 cases in the combination group, 10 cases in the coronary heart disease group and 5 cases in the hypertension group. IMT in those groups were all significantly higher than that in the control group with only 2 cases having IMT ≥ 1.0 mm (P<0.05). There were 18 cases with SDNN<100 ms in the cardiovascular disease group including 7 cases in the combination group, 6 cases in the coronary heart disease group and 5 cases in the hypertension group, but there was no statistically significant difference compared with that in the control group with only 11 cases (P>0.05). Negative correlation was found between IMT and SDNN, SDANN in the cardiovascular diseases group (r=-0.574, -0.544; P<0.01) and negative correlation was found between IMT and SDANN in the control group (r=-0.392, P<0.05). ConclusionThe carotid artery lesions and autonomic nerve especially sympathetic nerve dysfunction are obvious in patients with cardiovascular diseases and there is a negative correlation between them.
Sleep apnea (SA) detection method based on traditional machine learning needs a lot of efforts in feature engineering and classifier design. We constructed a one-dimensional convolutional neural network (CNN) model, which consists in four convolution layers, four pooling layers, two full connection layers and one classification layer. The automatic feature extraction and classification were realized by the structure of the proposed CNN model. The model was verified by the whole night single-channel sleep electrocardiogram (ECG) signals of 70 subjects from the Apnea-ECG dataset. Our results showed that the accuracy of per-segment SA detection was ranged from 80.1% to 88.0%, using the input signals of single-channel ECG signal, RR interval (RRI) sequence, R peak sequence and RRI sequence + R peak sequence respectively. These results indicated that the proposed CNN model was effective and can automatically extract and classify features from the original single-channel ECG signal or its derived signal RRI and R peak sequence. When the input signals were RRI sequence + R peak sequence, the CNN model achieved the best performance. The accuracy, sensitivity and specificity of per-segment SA detection were 88.0%, 85.1% and 89.9%, respectively. And the accuracy of per-recording SA diagnosis was 100%. These findings indicated that the proposed method can effectively improve the accuracy and robustness of SA detection and outperform the methods reported in recent years. The proposed CNN model can be applied to portable screening diagnosis equipment for SA with remote server.
Recently, deep neural networks (DNNs) have been widely used in the field of electrocardiogram (ECG) signal classification, but the previous models have limited ability to extract features from raw ECG data. In this paper, a deep residual network model based on pyramidal convolutional layers (PC-DRN) was proposed to implement ECG signal classification. The pyramidal convolutional (PC) layer could simultaneously extract multi-scale features from the original ECG data. And then, a deep residual network was designed to train the classification model for arrhythmia detection. The public dataset provided by the physionet computing in cardiology challenge 2017(CinC2017) was used to validate the classification experiment of 4 types of ECG data. In this paper, the harmonic mean F1 of classification accuracy and recall was selected as the evaluation indexes. The experimental results showed that the average sequence level F1 (SeqF1) of PC-DRN was improved from 0.857 to 0.920, and the average set level F1 (SetF1) was improved from 0.876 to 0.925. Therefore, the PC-DRN model proposed in this paper provided a promising way for the feature extraction and classification of ECG signals, and provided an effective tool for arrhythmia classification.
The diagnosis of hypertrophic cardiomyopathy (HCM) is of great significance for the early risk classification of sudden cardiac death and the screening of family genetic diseases. This research proposed a HCM automatic detection method based on convolution neural network (CNN) model, using single-lead electrocardiogram (ECG) signal as the research object. Firstly, the R-wave peak locations of single-lead ECG signal were determined, followed by the ECG signal segmentation and resample in units of heart beats, then a CNN model was built to automatically extract the deep features in the ECG signal and perform automatic classification and HCM detection. The experimental data is derived from 108 ECG records extracted from three public databases provided by PhysioNet, the database established in this research consists of 14,459 heartbeats, and each heartbeat contains 128 sampling points. The results revealed that the optimized CNN model could effectively detect HCM, the accuracy, sensitivity and specificity were 95.98%, 98.03% and 95.79% respectively. In this research, the deep learning method was introduced for the analysis of single-lead ECG of HCM patients, which could not only overcome the technical limitations of conventional detection methods based on multi-lead ECG, but also has important application value for assisting doctor in fast and convenient large-scale HCM preliminary screening.
Heart rate is the most common index to directly monitor the level of physical stress by comparing the subject's heart rate with an appropriate "target heart rate" during exercise. However, heart rate only reveals the cardiac rhythm of the complex cardiovascular changes that take place during exercise. It is essential to get the dynamic response of the heart to exercise with various indices instead of only one single measurement. Based on the rest-workload alternating pattern, this paper screens the sensitive indices of exercise load from electrocardiogram (ECG) rhythm and waveform, including 4 time domain indices and 4 frequency domain indices of heart rate variability (HRV), 3 indices of waveform similarity and 2 indices of high frequency noise. In conclusion, RR interval (heart rate) is a reliable index for the realtime monitoring of exercise intensity, which has strong linear correlation with load intensity. The ECG waveform similarity and HRV indices are useful for the evaluation of exercise load.
The judgment of the type of arrhythmia is the key to the prevention and diagnosis of early cardiovascular disease. Therefore, electrocardiogram (ECG) analysis has been widely used as an important basis for doctors to diagnose. However, due to the large differences in ECG signal morphology among different patients and the unbalanced distribution of categories, the existing automatic detection algorithms for arrhythmias have certain difficulties in the identification process. This paper designs a variable scale fusion network model for automatic recognition of heart rhythm types. In this study, a variable-scale fusion network model was proposed for automatic identification of heart rhythm types. The improved ECG generation network (EGAN) module was used to solve the imbalance of ECG data, and the ECG signal was reproduced in two dimensions in the form of gray recurrence plot (GRP) and spectrogram. Combined with the branching structure of the model, the automatic classification of variable-length heart beats was realized. The results of the study were verified by the Massachusetts institute of technology and Beth Israel hospital (MIT-BIH) arrhythmia database, which distinguished eight heart rhythm types. The average accuracy rate reached 99.36%, and the sensitivity and specificity were 96.11% and 99.84%, respectively. In conclusion, it is expected that this method can be used for clinical auxiliary diagnosis and smart wearable devices in the future.
Electrocardiogram (ECG) signals are easily disturbed by internal and external noise, and its morphological characteristics show significant variations for different patients. Even for the same patient, its characteristics are variable under different temporal and physical conditions. Therefore, ECG signal detection and recognition for the heart disease real-time monitoring and diagnosis are still difficult. Based on this, a wavelet self-adaptive threshold denoising combined with deep residual convolutional neural network algorithm was proposed for multiclass arrhythmias recognition. ECG signal filtering was implemented using wavelet adaptive threshold technology. A 20-layer convolutional neural network (CNN) containing multiple residual blocks, namely deep residual convolutional neural network (DR-CNN), was designed for recognition of five types of arrhythmia signals. The DR-CNN constructed by residual block local neural network units alleviated the difficulty of deep network convergence, the difficulty in tuning and so on. It also overcame the degradation problem of the traditional CNN when the network depth was increasing. Furthermore, the batch normalization of each convolution layer improved its convergence. Following the recommendations of the Association for the Advancements of Medical Instrumentation (AAMI), experimental results based on 94 091 2-lead heart beats from the MIT-BIH arrhythmia benchmark database demonstrated that our proposed method achieved the average detection accuracy of 99.034 9%, 99.498 0% and 99.334 7% for multiclass classification, ventricular ectopic beat (Veb) and supra-Veb (Sveb) recognition, respectively. Using the same platform and database, experimental results showed that under the comparable network complexity, our proposed method significantly improved the recognition accuracy, sensitivity and specificity compared to the traditional deep learning networks, such as deep Multilayer Perceptron (MLP), CNN, etc. The DR-CNN algorithm improves the accuracy of the arrhythmia intelligent diagnosis. If it is combined with wearable equipment, internet of things and wireless communication technology, the prevention, monitoring and diagnosis of heart disease can be extended to out-of-hospital scenarios, such as families and nursing homes. Therefore, it will improve the cure rate, and effectively save the medical resources.
In recent years, wearable devices grew up gradually and developed increasingly. Aiming at the problems of skin sensibility and the change of electrode impedance of Ag/AgCl electrode in the process of long-term electrocardiogram (ECG) signal monitoring and acquisition, this paper discussed in detail a new sensor technology–fabric electrode, which is used for ECG signal acquisition. First, the concept and advantages of fabric electrode were introduced, and then the common substrate materials and conductive materials for fabric electrode were discussed and evaluated. Next, we analyzed the advantages and disadvantages from the aspect of textile structure, putting forward the evaluation system of fabric electrode. Finally, the deficiencies of fabric electrode were analyzed, and the development prospects and directions were prospected.