In the extraction of fetal electrocardiogram (ECG) signal, due to the unicity of the scale of the U-Net same-level convolution encoder, the size and shape difference of the ECG characteristic wave between mother and fetus are ignored, and the time information of ECG signals is not used in the threshold learning process of the encoder’s residual shrinkage module. In this paper, a method of extracting fetal ECG signal based on multi-scale residual shrinkage U-Net model is proposed. First, the Inception and time domain attention were introduced into the residual shrinkage module to enhance the multi-scale feature extraction ability of the same level convolution encoder and the utilization of the time domain information of fetal ECG signal. In order to maintain more local details of ECG waveform, the maximum pooling in U-Net was replaced by Softpool. Finally, the decoder composed of the residual module and up-sampling gradually generated fetal ECG signals. In this paper, clinical ECG signals were used for experiments. The final results showed that compared with other fetal ECG extraction algorithms, the method proposed in this paper could extract clearer fetal ECG signals. The sensitivity, positive predictive value, and F1 scores in the 2013 competition data set reached 93.33%, 99.36%, and 96.09%, respectively, indicating that this method can effectively extract fetal ECG signals and has certain application values for perinatal fetal health monitoring.
Fetal electrocardiogram (ECG) signals provide important clinical information for early diagnosis and intervention of fetal abnormalities. In this paper, we propose a new method for fetal ECG signal extraction and analysis. Firstly, an improved fast independent component analysis method and singular value decomposition algorithm are combined to extract high-quality fetal ECG signals and solve the waveform missing problem. Secondly, a novel convolutional neural network model is applied to identify the QRS complex waves of fetal ECG signals and effectively solve the waveform overlap problem. Finally, high quality extraction of fetal ECG signals and intelligent recognition of fetal QRS complex waves are achieved. The method proposed in this paper was validated with the data from the PhysioNet computing in cardiology challenge 2013 database of the Complex Physiological Signals Research Resource Network. The results show that the average sensitivity and positive prediction values of the extraction algorithm are 98.21% and 99.52%, respectively, and the average sensitivity and positive prediction values of the QRS complex waves recognition algorithm are 94.14% and 95.80%, respectively, which are better than those of other research results. In conclusion, the algorithm and model proposed in this paper have some practical significance and may provide a theoretical basis for clinical medical decision making in the future.
Electrocardiogram (ECG) is a noninvasive, inexpensive, and convenient test for diagnosing cardiovascular diseases and assessing the risk of cardiovascular events. Although there are clear standardized operations and procedures for ECG examination, the interpretation of ECG by even trained physicians can be biased due to differences in diagnostic experience. In recent years, artificial intelligence has become a powerful tool to automatically analyze medical data by building deep neural network models, and has been widely used in the field of medical image diagnosis such as CT, MRI, ultrasound and ECG. This article mainly introduces the application progress of deep neural network models in ECG diagnosis and prediction of cardiovascular diseases, and discusses its limitations and application prospects.
Ballistocardiogram (BCG) and electrocardiogram (ECG) can realize the detection of cardiac function from mechanical and electrical dimensions respectively. By extracting the corresponding characteristic parameters of the two signals and carrying out joint analysis, an important cardiac physiological index such as cardiac contractility, can be reflected. To overcome the shortcomings of complication and heaviness of the existing acquisition equipment, a wearable BCG-ECG signal acquisition system is designed in this paper, which realizes BCG signal acquisition based on accelerometer and ECG signal acquisition based on conductive rubber electrodes. The signals of 6 healthy persons were collected, and BCG signals collected by piezoelectric films were used as reference signals. The waveform characteristics of signals were compared, and the difference of cardiac cycle acquisition was analyzed. The waveform characteristics of the two signals acquired by the device were consistent with the standard signals, and there was no significant difference in the acquisition of the cardiac cycle between the proposed method and the traditional method. The results show that the system can accurately collect human BCG signals and ECG signals. The system provides a basis for subsequent research on BCG signal formation mechanism and health applications.
Based on the capacitance coupling principle, we studied a capacitive way of non-contact electrocardiogram (ECG) monitoring, making it possible to obtain ECG on the condition that a patient is habilimented. Conductive fabric with a good electrical conductivity was used as electrodes. The electrodes fixed on a bed sheet is presented in this paper. A capacitance comes into being as long as the body gets close to the surface of electrode, sandwiching the cotton cushion, which acts as dielectric. The surface potential generated by heart is coupled to electrodes through the capacitance. After being processed, the signal is suitable for monitoring. The test results show that 93.5% of R wave could be detected for 9 volunteers and ECG with good signal quality could be acquired for 2 burnt patients. Non-contact ECG is harmless to skin, and it has advantages for those patients to whom stickup electrodes are not suitable. On the other hand, it is convenient to use and good for permanent monitoring.
In order to solve the problem that the early onset of paroxysmal atrial fibrillation is very short and difficult to detect, a detection algorithm based on sparse coding of Riemannian manifolds is proposed. The proposed method takes into account that the nonlinear manifold geometry is closer to the real feature space structure, and the computational covariance matrix is used to characterize the heart rate variability (RR interval variation), so that the data is in the Riemannian manifold space. Sparse coding is applied to the manifold, and each covariance matrix is represented as a sparse linear combination of Riemann dictionary atoms. The sparse reconstruction loss is defined by the affine invariant Riemannian metric, and the Riemann dictionary is learned by iterative method. Compared with the existing methods, this method used shorter heart rate variability signal, the calculation was simple and had no dependence on the parameters, and the better prediction accuracy was obtained. The final classification on MIT-BIH AF database resulted in a sensitivity of 99.34%, a specificity of 95.41% and an accuracy of 97.45%. At the same time, a specificity of 95.18% was realized in MIT-BIH NSR database. The high precision paroxysmal atrial fibrillation detection algorithm proposed in this paper has a potential application prospect in the long-term monitoring of wearable devices.
The dynamic electrocardiogram (ECG) collected by wearable devices is often corrupted by motion interference due to human activities. The frequency of the interference and the frequency of the ECG signal overlap with each other, which distorts and deforms the ECG signal, and then affects the accuracy of heart rate detection. In this paper, a heart rate detection method that using coarse graining technique was proposed. First, the ECG signal was preprocessed to remove the baseline drift and the high-frequency interference. Second, the motion-related high amplitude interference exceeding the preset threshold was suppressed by signal compression method. Third, the signal was coarse-grained by adaptive peak dilation and waveform reconstruction. Heart rate was calculated based on the frequency spectrum obtained from fast Fourier transformation. The performance of the method was compared with a wavelet transform based QRS feature extraction algorithm using ECG collected from 30 volunteers at rest and in different motion states. The results showed that the correlation coefficient between the calculated heart rate and the standard heart rate was 0.999, which was higher than the result of the wavelet transform method (r = 0.971). The accuracy of the proposed method was significantly higher than the wavelet transform method in all states, including resting (99.95% vs. 99.14%, P < 0.01), walking (100% vs. 97.26%, P < 0.01) and running (100% vs. 90.89%, P < 0.01). The absolute error [0 (0, 1) vs. 1 (0, 1), P < 0.05] and relative error [0 (0, 0.59) vs. 0.52 (0, 0.72), P < 0.05] of the proposed method were significantly lower than the wavelet transform method during running state. The method presented in this paper shows high accuracy and strong anti-interference ability, and is potentially used in wearable devices to realize real-time continuous heart rate monitoring in daily activities and exercise conditions.
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.
Lorenz plot (LP) method which gives a global view of long-time electrocardiogram signals, is an efficient simple visualization tool to analyze cardiac arrhythmias, and the morphologies and positions of the extracted attractors may reveal the underlying mechanisms of the onset and termination of arrhythmias. But automatic diagnosis is still impossible because it is lack of the method of extracting attractors by now. We presented here a methodology of attractor extraction and recognition based upon homogeneously statistical properties of the location parameters of scatter points in three dimensional LP (3DLP), which was constructed by three successive RR intervals as X, Y and Z axis in Cartesian coordinate system. Validation experiments were tested in a group of RR-interval time series and tags data with frequent unifocal premature complexes exported from a 24-hour Holter system. The results showed that this method had excellent effective not only on extraction of attractors, but also on automatic recognition of attractors by the location parameters such as the azimuth of the points peak frequency (APF) of eccentric attractors once stereographic projection of 3DLP along the space diagonal. Besides, APF was still a powerful index of differential diagnosis of atrial and ventricular extrasystole. Additional experiments proved that this method was also available on several other arrhythmias. Moreover, there were extremely relevant relationships between 3DLP and two dimensional LPs which indicate any conventional achievement of LPs could be implanted into 3DLP. It would have a broad application prospect to integrate this method into conventional long-time electrocardiogram monitoring and analysis system.
Valvular heart disease (VHD) ranks as the third most prevalent cardiovascular disease, following coronary artery disease and hypertension. Severe cases can lead to ventricular hypertrophy or heart failure, highlighting the critical importance of early detection. In recent years, the application of deep learning techniques in the auxiliary diagnosis of VHD has made significant advancements, greatly improving detection accuracy. This review begins by introducing the etiology, pathological mechanisms, and impact of common valvular heart diseases. It then explores the advantages and limitations of using electrocardiographic signals, phonocardiographic signals, and multimodal data in VHD detection. A comparison is made between traditional risk prediction methods and large language models (LLMs) for predicting cardiovascular disease risk, emphasizing the potential of LLMs in risk prediction. Lastly, the current challenges faced by deep learning in this field are discussed, and future research directions are proposed.