RESUMEN

The multi-lead electrocardiogram (ECG) is widely utilized in clinical diagnosis and monitoring of cardiac conditions. The advancement of deep learning has led to the emergence of automated multi-lead ECG diagnostic networks, which have become essential in the fields of biomedical engineering and clinical cardiac disease diagnosis. Intelligent ECG diagnosis techniques encompass Recurrent Neural Networks (RNN), Transformers, and Convolutional Neural Networks (CNN). While CNN is capable of extracting local spatial information from images, it lacks the ability to learn global spatial features and temporal memory features. Conversely, RNN relies on time and can retain significant sequential features. However, they are not proficient in extracting lengthy dependencies of sequence data in practical scenarios. The self-attention mechanism in the Transformer model has the capability of global feature extraction, but it does not adequately prioritize local features and cannot extract spatial and channel features. This paper proposes STFAC-ECGNet, a model that incorporates CAMV-RNN block, CBMV-CNN block, and TSEF block to enhance the performance of the model by integrating the strengths of CNN, RNN, and Transformer. The CAMV-RNN block incorporates a coordinated adaptive simplified self-attention module that adaptively carries out global sequence feature retention and enhances spatial-temporal information. The CBMV-CNN block integrates spatial and channel attentional mechanism modules in a skip connection, enabling the fusion of spatial and channel information. The TSEF block implements enhanced multi-scale fusion of image spatial and sequence temporal features. In this study, comprehensive experiments were conducted using the PTB-XL large publicly available ECG dataset and the China Physiological Signal Challenge 2018 (CPSC2018) database. The results indicate that STFAC-ECGNet surpasses other cutting-edge techniques in multiple tasks, showcasing robustness and generalization.

Asunto(s)

RESUMEN

The electrocardiogram (ECG) is a fundamental and widely used tool for diagnosing cardiovascular diseases. It involves recording cardiac electrical signals using electrodes, which illustrate the functioning of cardiac muscles during contraction and relaxation phases. ECG is instrumental in identifying abnormal cardiac activity, heart attacks, and various cardiac conditions. Arrhythmia detection, a critical aspect of ECG analysis, entails accurately classifying heartbeats. However, ECG signal analysis demands a high level of expertise, introducing the possibility of human errors in interpretation. Hence, there is a clear need for robust automated detection techniques. Recently, numerous methods have emerged for arrhythmia detection from ECG signals. In our research, we developed a novel one-dimensional deep neural network technique called linear deep convolutional neural network (LDCNN) to identify arrhythmias from ECG signals. We compare our suggested method with several state-of-the-art algorithms for arrhythmia detection. We evaluate our methodology using benchmark datasets, including the PTB Diagnostic ECG and MIT-BIH Arrhythmia databases. Our proposed method achieves high accuracy rates of 99.24% on the PTB Diagnostic ECG dataset and 99.38% on the MIT-BIH Arrhythmia dataset.

Asunto(s)

RESUMEN

Sudden cardiac arrest (SCA) is a lethal cardiac arrhythmia that poses a serious threat to human life and health. However, clinical records of sudden cardiac death (SCD) electrocardiogram (ECG) data are extremely limited. This paper proposes an early prediction and classification algorithm for SCA based on deep transfer learning. With limited ECG data, it extracts heart rate variability features before the onset of SCA and utilizes a lightweight convolutional neural network model for pre-training and fine-tuning in two stages of deep transfer learning. This achieves early classification, recognition and prediction of high-risk ECG signals for SCA by neural network models. Based on 16 788 30-second heart rate feature segments from 20 SCA patients and 18 sinus rhythm patients in the international publicly available ECG database, the algorithm performance evaluation through ten-fold cross-validation shows that the average accuracy (Acc), sensitivity (Sen), and specificity (Spe) for predicting the onset of SCA in the 30 minutes prior to the event are 91.79%, 87.00%, and 96.63%, respectively. The average estimation accuracy for different patients reaches 96.58%. Compared to traditional machine learning algorithms reported in existing literatures, the method proposed in this paper helps address the requirement of large training datasets for deep learning models and enables early and accurate detection and identification of high-risk ECG signs before the onset of SCA.

Asunto(s)

RESUMEN

S-Limonene (s-Lim) is a monocyclic monoterpene found in a variety of plants and has been shown to present antioxidant and cardioprotective activity in experimental models of myocardial infarction. The aim of this study was to evaluate the potential mechanism by which s-Lim exerts its antiarrhythmic effect, focusing on the blockade of ß-adrenoceptor (ß-AR) and its effects on various in vivo and in vitro parameters, including electrocardiogram (ECG) measurements, left ventricular developed pressure (LVDP), the ß-adrenergic pathway, sarcomeric shortening and L-type calcium current (ICa,L). In isolated hearts, 10 µM of s-Lim did not alter the ECG profile or LVPD. s-Lim increased the heart rate corrected QT interval (QTc) (10.8%) at 50 µM and reduced heart rate at the concentrations of 30 (12.4%) and 50 µM (16.6%). s-Lim (10 µM) also inhibited the adrenergic response evoked by isoproterenol (ISO) (1 µM) reducing the increased of heart rate, LVDP and ECG changes. In ventricular cardiomyocyte, s-Lim antagonized the effect of dobutamine by preventing the increase of sarcomeric shortening, demonstrating a similar effect to atenolol (blocker ß1-AR). In vivo, s-Lim antagonized the effect of ISO (agonists ß1-AR), presenting a similar effect to propranolol (a non-selective blocker ß-AR). In ventricular cardiomyocyte, s-Lim did not alter the voltage dependence for ICa,L activation or the ICa,L density. In addition, s-Lim did not affect changes in the ECG effect mediated by 5 µM forskolin (an activator of adenylate cyclase). In an in vivo caffeine/ISO-induced arrhythmia model, s-Lim (1 mg/kg) presented antiarrhythmic action verified by a reduced arrhythmia score, heart rate, and occurrence of ventricular premature beats and inappropriate sinus tachycardia. These findings indicate that the antiarrhythmic activity of s-Lim is related to blockade of ß-AR in the heart.

Asunto(s)

RESUMEN

Clinical conditions, including chronic obstructive pulmonary disease or pulmonary arterial hypertension (PAH), can lead to chronic right ventricle pressure overload and progressive right heart failure (RHF). RHF can be identified by right-sided cardiac hypertrophy and dilation associated with abnormal myocardial function affecting the RV and the right atrium (RA). We recently demonstrated that severe RHF is accompanied by an increased risk of atrial inflammation, atrial fibrosis, and atrial fibrillation (AF), the most common type of cardiac arrhythmia (CA). Recent studies have shown that RV and RA inflammation plays an important role in the arrhythmogenesis of CA, including AF. However, the impact of inflammation in the development of CA and AF in RHF is poorly described. Experimental models of RHF are required to better understand the association between right-sided myocardial inflammation and CA. The rat model of monocrotaline (MCT)-induced pulmonary hypertension (PH) is well-established to provoke RHF. However, MCT triggers severe pneumo-toxicity and pulmonary inflammation. Hence, MCT-induced RHF does not help to distinguish whether the subsequent myocardial inflammation originates from the RHF per se or circulating inflammatory signals secreted by the injured lung. In this article, a mechanical method involving pulmonary artery trunk banding (PAB) was used to provoke right-sided cardiac arrhythmogenesis. The PAB consists of performing a permanent suture of the pulmonary artery trunk for 3 weeks. Such an approach generates increased right-sided pressure overload. At D21 post-PAB, the suture results in hypertrophied, dilated, and inflamed RV and RA. The PAB-induced RHF is also accompanied by vulnerability to ventricular and atrial arrhythmias, including AF.

Asunto(s)

RESUMEN

Human-based modelling and simulation offer an ideal testbed for novel medical therapies to guide experimental and clinical studies. Myocardial infarction (MI) is a common cause of heart failure and mortality, for which novel therapies are urgently needed. Although cell therapy offers promise, electrophysiological heterogeneity raises pro-arrhythmic safety concerns, where underlying complex spatio-temporal dynamics cannot be investigated experimentally. Here, after demonstrating credibility of the modelling and simulation framework, we investigate cell therapy in acute versus chronic MI and the role of cell heterogeneity, scar size and the Purkinje system. Simulations agreed with experimental and clinical recordings from ionic to ECG dynamics in acute and chronic infarction. Following cell delivery, spontaneous beats were facilitated by heterogeneity in cell populations, chronic MI due to tissue depolarisation and slow sinus rhythm. Subsequent re-entrant arrhythmias occurred, in some instances with Purkinje involvement and their susceptibility was enhanced by impaired Purkinje-myocardium coupling, large scars and acute infarction. We conclude that homogeneity in injected ventricular-like cell populations minimises their spontaneous beating, which is enhanced by chronic MI, whereas a healthy Purkinje-myocardium coupling is key to prevent subsequent re-entrant arrhythmias, particularly for large scars.

Asunto(s)

RESUMEN

We propose a state-of-the-art deep learning approach for accurate electrocardiogram (ECG) signal analysis, addressing both waveform delineation and beat type classification tasks. For beat type classification, we integrated two novel schemes into the deep learning model, significantly enhancing its performance. The first scheme is an adaptive beat segmentation method that determines the optimal duration for each heartbeat based on RR-intervals, mitigating segmenting errors from conventional fixed-period segmentation. The second scheme incorporates relative heart rate information of the target beat compared to neighboring beats, improving the model's ability to accurately detect premature atrial contractions (PACs) that are easily confused with normal beats due to similar morphology. Extensive evaluations on the PhysioNet QT Database, MIT-BIH Arrhythmia Database, and real-world wearable device data demonstrated the proposed approach's superior capabilities over existing methods in both tasks. The proposed approach achieved sensitivities of 99.81% for normal beats, 99.08% for premature ventricular contractions, and 97.83% for PACs in beat type classification. For waveform delineation, we achieved F1-scores of 0.9842 for non-waveform, 0.9798 for P-waves, 0.9749 for QRS complexes, and 0.9848 for T-waves. It significantly outperforms existing methods in PAC detection while maintaining high performance across both tasks. The integration of aforementioned two schemes into the deep learning model improved the accuracy of normal sinus rhythms and arrhythmia detection.

Asunto(s)

RESUMEN

BACKGROUND: Ventricular repolarization time (ECG QT and JT intervals) is associated with malignant arrhythmia. Genome-wide association studies have identified 230 independent loci for QT and JT; however, 50% of their heritability remains unexplained. Previous work supports a causal effect of lower serum calcium concentrations on longer ventricular repolarization time. We hypothesized calcium interactions with QT and JT variant associations could explain a proportion of the missing heritability. METHODS AND RESULTS: We performed genome-wide calcium interaction analyses for QT and JT intervals. Participants were stratified by their calcium level relative to the study distribution (top or bottom 20%). We performed a 2-stage analysis (genome-wide discovery [N=62 532] and replication [N=59 861] of lead variants) and a single-stage genome-wide meta-analysis (N=122 393, [European ancestry N=117 581, African ancestry N=4812]). We also calculated 2-degrees of freedom joint main and interaction and 1-degree of freedom interaction P values. In 2-stage and single-stage analyses, 50 and 98 independent loci, respectively, were associated with either QT or JT intervals (2-degrees of freedom joint main and interaction P value <5×10-8). No lead variant had a significant interaction result after correcting for multiple testing and sensitivity analyses provided similar findings. Two loci in the single-stage meta-analysis were not reported previously (SPPL2B and RFX6). CONCLUSIONS: We have found limited support for an interaction effect of serum calcium on QT and JT variant associations despite sample sizes with suitable power to detect relevant effects. Therefore, such effects are unlikely to explain a meaningful proportion of the heritability of QT and JT, and factors including rare variation and other environmental interactions need to be considered.

Asunto(s)

Asunto(s)

RESUMEN

BACKGROUND: Atrial fibrillation (AF) is the most common type of arrhythmia. Heart rate variability (HRV) may be associated with AF risk. The aim of this study was to test HRV indices and arrhythmias as predictors of paroxysmal AF based on 24-hour dynamic electrocardiogram recordings of patients. METHODS: A total of 199 patients with paroxysmal AF (AF group) and 204 elderly volunteers over 60 years old (Control group) who underwent a 24-hour dynamic electrocardiogram from August 2022 to March 2023 were included. Time-domain indices, frequency-domain indices, and arrhythmia data of the two groups were classified and measured. Binary logistic regression analysis was performed on variables with significant differences to identify independent risk factors. A nomogram prediction model was established, and the sum of individual scores of each variable was calculated. RESULTS: Gender, age, body mass index and low-density lipoprotein (LDL) did not differ significantly between AF and Control groups (p > 0.05), whereas significant group differences were found for smoking, hypertension, diabetes, and high-density lipoprotein (HDL) (p < 0.05). The standard deviation of all normal to normal (NN) R-R intervals (SDNN), standard deviation of 5-minute average NN intervals (SDANN), root mean square of successive NN interval differences (rMSSD), 50 ms from the preceding interval (pNN50), low-frequency/high-frequency (LF/HF), LF, premature atrial contractions (PACs), atrial tachycardia (AT), T-wave index, and ST-segment index differed significantly between the two groups. Logistic regression analysis identified rMSSD, PACs, and AT as independent predictors of AF. For each unit increase in rMSSD and PACs, the odds of developing AF increased by 1.0357 and 1.0005 times, respectively. For each unit increase in AT, the odds of developing AF decreased by 0.9976 times. The total score of the nomogram prediction model ranged from 0 to 110. CONCLUSION: The autonomic nervous system (ANS) plays a pivotal role in the occurrence and development of AF. The individualized nomogram prediction model of AF occurrence contributes to the early identification of high-risk patients with AF.

Asunto(s)

RESUMEN

As the number of patients with cardiovascular diseases (CVDs) increases annually, a reliable and automated system for detecting electrocardiogram (ECG) abnormalities is becoming increasingly essential. Scholars have developed numerous methods of arrhythmia classification using machine learning or deep learning. However, the issue of low classification rates of individual classes in inter-patient heartbeat classification remains a challenge. This study proposes a method for inter-patient heartbeat classification by fusing dual-channel squeeze-and-excitation residual neural networks (SE-ResNet) and expert features. In the preprocessing stage, ECG heartbeats extracted from both leads of ECG signals are filtered and normalized. Additionally, nine features representing waveform morphology and heartbeat contextual information are selected to be fused with the deep neural networks. Using different filter and kernel sizes for each block, the SE-residual block-based model can effectively learn long-term features between heartbeats. The divided ECG heartbeats and extracted features are then input to the improved SE-ResNet for training and testing according to the inter-patient scheme. The focal loss is utilized to handle the heartbeat of the imbalance category. The proposed arrhythmia classification method is evaluated on three open-source databases, and it achieved an overall F1-score of 83.39 % in the MIT-BIH database. This system can be applied in the scenario of daily monitoring of ECG and plays a significant role in diagnosing arrhythmias.

Asunto(s)

RESUMEN

The 12-lead electrocardiogram (ECG) is widely used for diagnosing cardiovascular diseases in clinical practice. Recently, deep learning methods have become increasingly effective for automatically classifying ECG signals. However, most current research simply combines the 12-lead ECG signals into a matrix without fully considering the intrinsic relationships between the leads and the heart's structure. To better utilize medical domain knowledge, we propose a multi-branch network for multi-label ECG classification and introduce an intuitive and effective lead grouping strategy. Correspondingly, we design multi-branch networks where each branch employs a multi-scale convolutional network structure to extract more comprehensive features, with each branch corresponding to a lead combination. To better integrate features from different leads, we propose a feature weighting fusion module. We evaluate our method on the PTB-XL dataset for classifying 4 arrhythmia types and normal rhythm, and on the China Physiological Signal Challenge 2018 (CPSC2018) database for classifying 8 arrhythmia types and normal rhythm. Experimental results on multiple multi-label datasets demonstrate that our proposed multi-branch network outperforms state-of-the-art networks in multi-label classification tasks.

Asunto(s)

RESUMEN

OBJECTIVE: This study aimed to identify the incidence, risk factors, and outcomes of permanent pacemaker (PPM) implantation after transcatheter aortic valve implantation (TAVI) procedures. METHODS: A retrospective analysis was conducted on 70 patients who underwent TAVI at the Department of Cardiology, Fujian Provincial Hospital, from January 2018 to March 2022. Based on whether a new PPM was implanted after TAVI, all patients were divided into two groups: NEW PPM and NO PPM. Baseline characteristics and clinical data were compared between the two groups. Univariate analysis was used to analyze different variables between the two groups. A binary logistic regression analysis was used to evaluate independent correlates for PPM implantation after TAVI. RESULTS: The mean age of the 70 patients was 73.1 ± 8.8 years. The incidence of PPM implantation was 17.1%. Patients with diabetes and chronic kidney disease were more likely to require PPM (50% vs. 20.7%, p = 0.042, 25% vs. 5.2%, p = 0.042). Our study did not identify any significant differences in the incidence of electrocardiographic conduction disturbances except for the previous right bundle branch block (RBBB) (NO PPM 6.9% vs. NEW PPM 33.3%, p < 0.05). We found that prosthesis size, implantation depth, procedural duration, and length of hospital and intensive care unit (ICU) stays were comparable between the two groups. The leading independent predictors of PPM implantation were previous RBBB (odds ratio 10.129, p = 0.034). CONCLUSION: The previous RBBB was the leading independent predictor of PPM implantation. New PPM was not associated with significantly new-onset left BBB, extended post-procedure hospitalization, ICU stay, or procedural duration.

Asunto(s)

RESUMEN

A regular heartbeat is essential for maintaining the homeostasis of the vertebrate body. However, environmental pollutants, oxygen deficiency and extreme temperatures can impair heart function in fish. In this Review, we provide an integrative view of the molecular origins of cardiac arrhythmias and their functional consequences, from the level of ion channels to cardiac electrical activity in living fish. First, we describe the current knowledge of the cardiac excitation-contraction coupling of fish, as the electrical activity of the heart and intracellular Ca2+ regulation act as a platform for cardiac arrhythmias. Then, we compile findings on cardiac arrhythmias in fish. Although fish can experience several types of cardiac arrhythmia under stressful conditions, the most typical arrhythmia in fish - both under heat stress and in the presence of toxic substances - is atrioventricular block, which is the inability of the action potential to progress from the atrium to the ventricle. Early and delayed afterdepolarizations are less common in fish hearts than in the hearts of endotherms, perhaps owing to the excitation-contraction coupling properties of the fish heart. In fish hearts, Ca2+-induced Ca2+ release from the sarcoplasmic reticulum plays a smaller role than Ca2+ influx through the sarcolemma. Environmental changes and ion channel toxins can induce arrhythmias in fish and weaken their tolerance to environmental stresses. Although different from endotherm hearts in many respects, fish hearts can serve as a translational model for studying human cardiac arrhythmias, especially for human neonates.

Asunto(s)

RESUMEN

Without intervention, cardiac arrhythmias pose a risk of fatality. However, timely intervention can be challenging in environments where transporting a large, heavy defibrillator is impractical, or emergency surgery to implant cardiac stimulation devices is not feasible. Here, we introduce an injectable cardiac stimulator, a syringe loaded with a nanoparticle solution comprising a conductive polymer and a monomer that, upon injection, forms a conductive structure around the heart for cardiac stimulation. Following treatment, the electrode is cleared from the body, eliminating the need for surgical extraction. The mixture adheres to the beating heart in vivo without disrupting its normal rhythm. The electrofunctionalized injectable cardiac stimulator demonstrates a tissue-compatible Young's modulus of 21 kPa and a high conductivity of 55 S/cm. The injected electrode facilitates electrocardiogram measurements, regulates heartbeat in vivo, and rectifies arrhythmia. Conductive functionality is maintained for five consecutive days, and no toxicity is observed at the organism, organ, or cellular levels.

Asunto(s)

Asunto(s)

RESUMEN

Hypertrophic cardiomyopathy (HCM) is an inherited heart muscle disease that is characterised by left ventricular wall thickening, cardiomyocyte disarray and fibrosis, and is associated with arrhythmias, heart failure and sudden death. However, it is unclear to what extent the electrophysiological disturbances that lead to sudden death occur secondary to structural changes in the myocardium or as a result of HCM cardiomyocyte electrophysiology. In this study, we used an induced pluripotent stem cell model of the R403Q variant in myosin heavy chain 7 (MYH7) to study the electrophysiology of HCM cardiomyocytes in electrically coupled syncytia, revealing significant conduction slowing and increased spatial dispersion of repolarisation - both well-established substrates for arrhythmia. Analysis of rhythmonome protein expression in MYH7 R403Q cardiomyocytes showed reduced expression of connexin-43 (also known as GJA1), sodium channels and inward rectifier potassium channels - a three-way hit that reduces electrotonic coupling and slows cardiac conduction. Our data represent a previously unreported, biophysical basis for arrhythmia in HCM that is intrinsic to cardiomyocyte electrophysiology. Later in the progression of the disease, these proarrhythmic phenotypes may be accentuated by myocyte disarray and fibrosis to contribute to sudden death.

Asunto(s)

RESUMEN

Scn1b plays essential roles in the heart, where it encodes ß1-subunits that serve as modifiers of gene expression, cell surface channel activity, and cardiac conductivity. Reduced ß1 function is linked to electrical instability in various diseases with cardiac manifestations and increased susceptibility to arrhythmias. Recently, we demonstrated that loss of Scn1b in mice leads to compromised mitochondria energetics and reactive oxygen species (ROS) production. In this study, we examined the link between increased ROS and arrhythmia susceptibility in Scn1b-/- mice. In addition, ROS-scavenging capacity can be overwhelmed during prolonged oxidative stress, increasing arrhythmia susceptibility. Therefore, we isolated whole hearts and cardiomyocytes from Scn1b-/- and Scn1b+/+ mice and subjected them to an oxidative challenge with diamide, a glutathione oxidant. Next, we analyzed gene expression and activity of antioxidant enzymes in Scn1b-/- hearts. Cells isolated from Scn1b-/- hearts died faster and displayed higher rates of ROS accumulation preceding cell death compared with those from Scn1b+/+. Furthermore, Scn1b-/- hearts showed higher arrhythmia scores and spent less time free of arrhythmia. Lastly, we found that protein expression and enzymatic activity of glutathione peroxidase is increased in Scn1b-/- hearts compared with wild type. Our results indicate that Scn1b-/- mice have decreased capability to manage ROS during prolonged oxidative stress. ROS accumulation is elevated and appears to overwhelm ROS scavenging through the glutathione system. This imbalance creates the potential for altered cell energetics that may underlie increased susceptibility to arrhythmias or other adverse cardiac outcomes.NEW & NOTEWORTHY Using an oxidative challenge, we demonstrated that isolated cells from Scn1b-/- mice are more susceptible to cell death and surges in reactive oxygen species accumulation. At the whole organ level, they were also more susceptible to the formation of cardiac arrhythmias. This may in part be due to changes to the glutathione antioxidant system.

Asunto(s)

RESUMEN

Arrhythmogenic cardiomyopathy (AC) is a hereditary cardiac disorder characterized by the gradual replacement of cardiomyocytes with fibrous and adipose tissue, leading to ventricular wall thinning, chamber dilation, arrhythmias, and sudden cardiac death. Despite advances in treatment, disease management remains challenging. Animal models, particularly mice and zebrafish, have become invaluable tools for understanding AC's pathophysiology and testing potential therapies. Mice models, although useful for scientific research, cannot fully replicate the complexity of the human AC. However, they have provided valuable insights into gene involvement, signalling pathways, and disease progression. Zebrafish offer a promising alternative to mammalian models, despite the phylogenetic distance, due to their economic and genetic advantages. By combining animal models with in vitro studies, researchers can comprehensively understand AC, paving the way for more effective treatments and interventions for patients and improving their quality of life and prognosis.

Asunto(s)

Asunto(s)