Arrhythmia is a kind of cardiovascular disease that seriously threats human health. Intelligent analysis of electrocardiogram (ECG) is an effective method for the early prevention and precise treatment to arrhythmia. In clinical ECG waveforms, it is common to see the multi-label phenomenon that one patient would be labeled with multiple types of arrhythmia. However, the current research is mainly to use the multiclass methods to solve the multi-label problem, ignoring the correlations between diseases and causing information loss. Therefore, this article aims: 1) to propose a multi-label feature selection method based on ECG (MS-ECG) and design an evaluation criterion of ECG features based on kernelized fuzzy rough sets so as to choose the optimal feature subset and optimize ECG feature space and 2) to propose the multi-label classification algorithm of arrhythmia based on ECG (MC-ECG) by establishing a multiobjective optimization model. This algorithm based on sparsity constraint explores the correlations between arrhythmia diseases and analyzes the mapping relationship between ECG features and arrhythmia diseases, so that one ECG signal would be automatically and accurately given multiple labels. Through sufficient experiments to prove the feasibility of our methods, we obtain the selected feature subset composed of 23 ECG features by MS-ECG. For the six evaluation criterions of MC-ECG, average precision is 0.8462, hamming loss is 0.1041, ranking loss is 0.1313, one-error is 0.2023, coverage is 0.4015, and micro-F1 is 0.6088. The outcome presents optimal to the current algorithms.

Fetal electrocardiography (ECG) monitoring during pregnancy can provide crucial information for assessing the fetus’s health status and making timely decisions. This paper proposes a portable ECG monitoring system to record the abdominal ECG (AECG) of the pregnant woman, comprising both maternal ECG (MECG) and fetal ECG (FECG), which could be applied to fetal heart rate (FHR) monitoring at the home setting. The ECG monitoring system is based on data acquisition circuits, data transmission module, and signal analysis platform, which consists of low input-referred noise, high input impedance, and high resolution. The combination of the adaptive dual threshold (ADT) and the independent component analysis (ICA) algorithm is employed to extract the FECG from the AECG signals. To validate the performance of the proposed system, AECG is recorded and analyzed of pregnant women in three different postures (supine, seated, and standing). The result shows that the proposed system can record the AECG in different postures with good signal quality and high accuracy in fetal ECG and heart rate information. Sensitivity (Se), positive predictive accuracy (PPV), accuracy (ACC), and their harmonic mean (F1) are utilized as the metrics to evaluate the performance of the fetal QRS (fQRS) complexes extraction. The average Se, PPV, ACC, and F1 score are 99.62%, 97.90%, 97.40%, and 98.66% for the fQRS complexes extraction,, respectively. This paper shows the proposed system has a promising application in fetal health monitoring.

Evaluation of sympathetic nerve activity (SNA) using skin sympathetic nerve activity (SKNA) signal has attracted interest in recent studies. However, signal noises may obstruct the accurate location for the burst of SKNA, leading to the quantification error of the signal. In this study, we use the Teager–Kaiser energy (TKE) operator to preprocess the SKNA signal, and then candidates of burst areas were segmented by an envelope-based method. Since the burst of SKNA can also be discriminated by the high-frequency component in QRS complexes of electrocardiogram (ECG), a strategy was designed to reject their influence. Finally, a feature of the SKNA energy ratio (SKNAER) was proposed for quantifying the SKNA. The method was verified by both sympathetic nerve stimulation and hemodialysis experiments compared with traditional heart rate variability (HRV) and a recently developed integral skin sympathetic nerve activity (iSKNA) method. The results showed that SKNAER correlated well with HRV features (r = 0.60 with the standard deviation of NN intervals, 0.67 with low frequency/high frequency, 0.47 with very low frequency) and the average of iSKNA (r = 0.67). SKNAER improved the detection accuracy for the burst of SKNA, with 98.2% for detection rate and 91.9% for precision, inducing increases of 3.7% and 29.1% compared with iSKNA (detection rate: 94.5% (p < 0.01), precision: 62.8% (p < 0.001)). The results from the hemodialysis experiment showed that SKNAER had more significant differences than aSKNA in the long-term SNA evaluation (p < 0.001 vs. p = 0.07 in the fourth period, p < 0.01 vs. p = 0.11 in the sixth period). The newly developed feature may play an important role in continuously monitoring SNA and keeping potential for further clinical tests.

This study designed a novel noncontact capacitive Electrocardiogram (cECG) system for long-term atrial fibrillation (AF) monitoring. Unlike conventional ECG monitoring, the proposed system can record ECG signals without touching a subject’s skin, avoiding the problem of skin allergy by using wet electrodes. The main contributions of this study include the two aspects. Firstly, a noncontact electrode based on a micro-humidity fabric structure is proposed, which can improve the noncontact cECG signal quality. Secondly, based on the proposed electrode, the possibility of its application in long-term AF monitoring was investigated. The micro-humidity fabric electrode can improve the micro-humidity of the skin-electrode interface and the noncontact cECG signal quality. This humidity is low and can hardly be felt by the human body, which can also ensure comfort. The experimental results show that compared with the conventional noncontact fabric electrode, the skin-electrode impedance decreases from 104.1±58.1 MΩ (when using the electrode without the micro-humidity structure) at 0.5 Hz to 2.8±1.79 MΩ (with the micro-humidity structure). In the long-term cECG recording experiment, the system has high consistency with the reference equipment. The RR interval correlation coefficient is 0.998, and the maximum error ≤ 18 ms. For the validation of AF monitoring, a designed AF analysis algorithm is integrated into the noncontact cECG system, including effective signal screening and AF recognition algorithm based on RR interval and SVM, with an average accuracy of 98.57% on the wearable database. The algorithm is verified on 3 healthy people and 1 PAF patient using the noncontact cECG system with an average accuracy of 98.12%, showing that our system has the potential for long-term AF monitoring.

Premature ventricular contraction (PVC) is one of the common ventricular arrhythmias, which may cause stroke or sudden cardiac death. Automatic long-term electrocardiogram (ECG) analysis algorithms could provide diagnosis suggestion and even early warning for physicians. However, they are mutually exclusive in terms of robustness, generalization and low complexity. In this study, a novel PVC recognition algorithm that combines deep learning-based heartbeat template clusterer and expert system-based heartbeat classifier is proposed. A long short-term memory-based auto-encoder (LSTM-AE) network was used to extract features from ECG heartbeats for K-means clustering. Thus, the templates were constructed and determined based on clustering results. Finally, the PVC heartbeats were recognized based on a combination of multiple rules, including template matching and rhythm characteristics. Three quantitative parameters, sensitivity (Se), positive predictive value (P+) and accuracy (ACC), were used to evaluate the performances of the proposed method on the MIT-BIH Arrhythmia database and the St. Petersburg Institute of Cardiological Technics database. Se on the two test databases was 87.51% and 87.92%, respectively; P+ was 92.47% and 93.18%, respectively; and ACC was 98.63% and 97.89%, respectively. The PVC scores on the third China Physiological Signal Challenge 2020 training set and hidden test set were 36,256 and 46,706, respectively, which could rank first in the open-source codes. The results showed that the combination strategy of expert system and deep learning can provide new insights for robust and generalized PVC identification from long-term single-lead ECG recordings.

Non-contact capacitive coupling ECG (cECG) is considered to have a broad application prospect for its comfort and non-invasive. As an important part of cECG transmission path, the characteristics of dielectric materials significantly affect the signal quality. This paper studies the influence on the dielectric properties of coupling capacitance, human body-electrode impedance, and cECG signal quality from the perspectives of cotton fabric humidity and thickness and gives suggestions on the application of cECG. Firstly, the effects of fabric humidity and thickness on human body-electrode impedance are analyzed theoretically. Then the human body-electrode impedance and cECG signal quality index (SQI) are recorded and calculated to evaluate how thickness and humidity affect the sensing performance of cECG. The results show that influenced by the fabric thickness and humidity, the impedance values reveal observable changes varying from 5.6 GΩ (thickness: 1.00 mm, moisture regain 3.2%) to 50.4 MΩ (thickness: 0.18mm, moisture regain 23.2%) at 0.5 Hz, and the impedance change will cause the impedance mismatch between the two electrodes, resulting in poor signal quality. According to the trend of SQI, the recommended moisture regain under different thicknesses is given. When the fabric thickness is 0.18 mm, 0.35 mm, and 1.00 mm, the moisture regain should be higher than 8.5%, 14.6%, and 23.2%, respectively so as to obtain a relatively high-quality cECG signal. The design parameters discussed in this paper could provide a supporting evidence for the design of efficient non-contact cECG systems in the future.