Type Of Arrhythmia Research Articles

Atrial fibrillation: real-life experience of a rhythm control with electrical cardioversion in a community hospital

BackgroundAtrial fibrillation is the most prevalent sustained cardiac arrhythmia. Electrical cardioversion, a well-established part of the rhythm control strategy, is probably underused in community settings. Here, we describe its use, safety, and effectiveness in a cohort of patients with atrial fibrillation treated in rural settings.MethodsIt is a retrospective cohort study. Data on all procedures from January 1, 2016, till December 1, 2022, in Tarusa Hospital, serving mostly a rural population of 15,000 people, were extracted from electronic health records. Data on the procedure’s success, age, gender, body mass index, comorbidities, previous procedures, echocardiographic parameters, type and duration of arrhythmia, anticoagulation, antiarrhythmic drugs, transesophageal echocardiography, and settings were available.ResultsAltogether, 1,272 procedures in 435 patients were performed during the study period. The overall effectiveness of the procedure was 92%. Effectiveness was similar across all prespecified subgroups. Electrical cardioversion was less effective in patients undergoing the procedure for the first time (86%, 95% CI: 82-90) compared to repeated procedures (95%, 95% CI: 93-96), OR 0.39 (95% CI: 0.26-0.59). Complications were encountered in 13 (1.02%) procedures but were not serious.ConclusionsElectrical cardioversion is an immediately effective procedure that can be safely performed in community hospitals, both in inpatient and outpatient settings. Further studies with longer follow-up are needed to investigate the rate of sinus rhythm maintenance in these patients.

Bronchial Lavage in the Treatment of Severe Bronchopulmonary Pathology in Adults. Approaches to Classification

Introduction Currently, bronchial lavage (BL) is widely used in clinical practice for the treatment of severe bronchopulmonary lesion in adults. However, indications and contraindications for this procedure are not fully defined. In addition, it was not possible to find in the literature a classification of either BL in general or used for therapeutic purposes in particular, which significantly complicates the standardization of procedures for its use in various diseases.Aim of study To determine possible classification characteristics, as well as indications, contraindications for therapeutic BL in adults and possible complications that may arise, based on the analysis of literature data.Results Therapeutic BL can be carried out both as planned and for health reasons. Indications for planned BL are purulent bronchitis, pneumonia, purulentdestructive infiltration, as well as chronic lung diseases: bronchiectasis, interstitial lesions. In turn, the indication for emergency therapeutic BL is progressive acute or chronic respiratory failure, developing due to bronchial obstruction. Such conditions may include massive pulmonary hemorrhage, acute obstruction of the bronchi with mucus and pus, postoperative atelectasis and hypoventilation of the lungs, aspiration of gastric contents, severe bronchial asthma, purulent destruction of the lungs, acute respiratory distress syndrome, thermochemical lesions of the respiratory tract. Contraindications to therapeutic BL can be both absolute and relative. Absolute contraindications are intolerance to drugs used for local anesthesia; decompensated heart and (or) pulmonary failure; acute cerebrovascular accident; various types of arrhythmias; stenosis of the larynx and (or) trachea II–III degree; neuropsychiatric diseases; pain syndrome in the abdominal cavity; extremely serious condition of the patient, when clarification of the diagnosis can no longer affect treatment tactics. Relative contraindications include acute respiratory disease of the upper respiratory tract; coronary artery disease; severe diabetes mellitus; pregnancy (second half); chronic alcoholism; grade III enlargement of the thyroid gland. It should be noted that most of the absolute contraindications are conditional and are not taken into account when performing BL according to vital indications with appropriate medical and technical support. Classification of BL used for medicinal purposes can be carried out according to the following criteria: method of sanitation; access used; level of sanitation; sanitized area; volume and composition of the lavage solution. It is noteworthy that the methods of carrying out procedures for various conditions and diseases still remain unregulated. An exception is the final stage of the therapeutic BL procedure in the case of the use of surfactant preparations, which standardization is regulated by approved standard operating procedures. It should also be noted that bronchial lavage for therapeutic purposes is justified from a pathoanatomical and pathophysiological point of view, but is accompanied by serious, albeit temporary, changes in the lungs, which can be partially avoided by improving the lavage technique.Conclusion All of the above indicates that in order to solve existing problems, it is necessary to conduct systematic research in this direction with the involvement of all interested specialists.

A Deep Learning Approach for Detecting Atrial Fibrillation using RR Intervals of ECG

Purpose: Atrial Fibrillation (AF) is one of the most common types of heart arrhythmias observed in clinical practice. AF can be detected using an Electrocardiogram (ECG). ECG signals are time-varying and nonlinear in nature. Hence, it is very difficult for a physician to manually perform accurate and rapid classification of different heart rhythms. Materials and Methods: In this paper, we propose a method using Discrete Wavelet Transform (DWT) with db6 as the basis function for denoising ECG signal. Results: The denoised ECG is smoothened using the Savitzky- Golay filter. Deep learning methods, such as a combination of Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM) (CNN-LSTM) and ResNet18 are used for the accurate classification of ECG signals using Physionet Challenge 2017 database. Conclusion: With a 10-fold cross-validation method the model provided overall accuracy of 98.25% with the CNN-LSTM classifier.

Navigating the Incidence of Postoperative Arrhythmia and Hospitalization Length: The Role of Amiodarone and Other Antiarrhythmics in Prophylaxis.

Antiarrhythmic drugs play a pivotal role in managing and preventing arrhythmias. Amiodarone, classified as a class III antiarrhythmic, has been used prophylactically to effectively prevent atrial fibrillation postoperatively in cardiac surgeries. However, there is a lack of consensus on the use of amiodarone and other antiarrhythmic drugs as prophylaxis to reduce the occurrence of all types of postoperative arrhythmias in cardiac and non-cardiac surgeries. A comprehensive PubMed query yielded 614 relevant papers, of which 52 clinical trials were analyzed. The data collection included the class of antiarrhythmics, timing or method of drug administration, surgery type, type of arrhythmia and its incidence, and hospitalization length. Statistical analyses focused on prophylactic antiarrhythmics and their respective reductions in postoperative arrhythmias and hospitalization length. Prophylactic amiodarone alone compared to placebo demonstrated a significant reduction in postoperative arrhythmia incidence in cardiac and non-cardiac surgeries (24.01%, p<0.0001), and it was the only treatment group to significantly reduce hospitalization length versus placebo (p = 0.0441). Prophylactic use of class 4 antiarrhythmics versus placebo also demonstrated a significant reduction in postoperative arrhythmia incidence (28.01%, p<0.0001), and while there was no significant statistical reduction compared to amiodarone (4%, p=0.9941), a lack of abundant data provides a case for further research on the prophylactic use of class 4 antiarrhythmics for this indication. Amiodarone prophylaxis remains a prime cornerstone of therapy in reducing postoperative arrhythmia incidence and hospitalization length. Emerging data suggests a need for a broader exploration of alternative antiarrhythmic agents and combination therapies, particularly class 4 antiarrhythmics, in both cardiac and non-cardiac surgeries. This meta-analysis depicts the effectiveness of amiodarone, among other antiarrhythmics, in postoperative arrhythmia incidence and hospitalization length reduction in cardiac and non-cardiac surgeries.

Pattern of Arrhythmia among Hypertensive Patients in South-South, Nigeria: A 24-H Ambulatory ECG (Holter ECG) Study

Background: Regular 12-lead electrocardiogram (ECG) often fail to detect cardiac conduction abnormalities. Among hypertensive patients, conduction irregularities such as atrial fibrillation and ventricular tachycardia are recognized occurrences and these can be intermittent or asymptomatic. This study aims to evaluate the conduction abnormalities identified among hypertensives by Holter ECG in a private medical facility in South-South, Nigeria. Methods: This is a retrospective study of five hundred and thirteen patients consisting of 255 males and 258 females Holter ECG who presented at a private medical facility from January 2015- December 2016. Holter ECG data was acquired using Schiller type (MT-101) Holter ECG Machine. Results: Out of the 370 hypertensive patients reviewed, with a mean age of 55.18 ±.14.78, 205(55.41%) had tachycardia, 180(48.65%) had bradycardia, 184(49.73%) had ventricular ectopics while 169(45.68%) had supraventricular ectopics. The most common clinical indication was palpitation 150 (40.54%). The most prevalent age group was 41-60 years; 230 (44.83%) as compared to other age groups in the study. Tachycardia was the most common type of arrhythmia among the subjects. There was a higher incidence of arrhythmias in the female subjects than in the male. Conclusion: Tachycardia and ventricular ectopics were the most common conduction abnormalities observed. Beta blockers and anti-arrhythmics would be helpful for optimization of cardiovascular care. Holter ECG is beneficial in describing and characterizing arrhythmias in hypertensive patients in this population therefore, further studies on larger populations and diverse disease conditions are advocated.

Evaluation of cardiac pro-arrhythmic risks using the artificial neural network with ToR-ORd in silico model output.

Torsades de pointes (TdP) is a type of ventricular arrhythmia that can lead to sudden cardiac death. Drug-induced TdP has been an important concern for researchers and international regulatory boards. The Comprehensive in vitro Proarrhythmia Assay (CiPA) initiative was proposed that integrates in vitro testing and computational models of cardiac ion channels and human cardiomyocyte cells to evaluate the proarrhythmic risk of drugs. The TdP risk classification performance using only a single TdP metric may require some improvements because of information limitations and the instability of generalizing results. This study evaluates the performance of TdP metrics from the in silico simulations of the Tomek-O'Hara Rudy (ToR-ORd) ventricular cell model for classifying the TdP risk of drugs. We utilized these metrics as an input to an artificial neural network (ANN)-based classifier. The ANN model was optimized through hyperparameter tuning using the grid search (GS) method to find the optimal model. The study outcomes show an area under the curve (AUC) value of 0.979 for the high-risk category, 0.791 for the intermediate-risk category, and 0.937 for the low-risk category. Therefore, this study successfully demonstrates the capability of the ToR-ORd ventricular cell model in classifying the TdP risk into three risk categories, providing new insights into TdP risk prediction methods.

Intracardiac 3D navigation as a tool to improve the efficiency of ablation of idiopathic ventricular arrhythmias

Aim. Еvaluate the effect of 3D navigation on the effectiveness of ablation idiopathic ventricular arrhythmias. Materials and methods. The paper presents a retrospective postoperative analysis of 57 patients with idiopathic ventricular arrhythmias. Patients were divided into two groups. Group I included 30 (52.6 %) patients who used a 3D navigation system during mapping. Group II – 27 (47.4 %) patients in whom mapping was performed using classical methods. The effectiveness criteria were: frequency of acute suppression of arrhythmia, number of radiofrequency applications for suppression, and time of intervention. Results. Intraoperatively, complete suppression of the arrhythmia was successfully achieved in all cases in both groups. In group I average number of applications in patients with ventricular extrasystole was 5.5 (4.0; 8.0), while in group II – 6.5 (3,5; 9.0), without statistically significant difference (p = 0.414). A similar situation was observed with ventricular tachycardia. Іn group I number of applications was 3.2 (3.0; 4.3), and in group II – 5.0 (2.3; 11.0), which also had no statistically significant difference (р = 0.537). The duration of intervention for ventricular extrasystole in group I was 100.6 ± 26.6 min, while in group II – 136.4 ± 42.2 min, that has statistically significant difference (p = 0.007). During ablation of ventricular tachycardia in group I average duration was 89.3 ± 20.4 min, while in group II – 135.4 ± 55.5 min. The duration of intervention for ventricular tachycardia with the use of 3D navigation had a significantly shorter time compared to classical methods (p = 0.024). Conclusions. Based on the obtained data, we concluded that the use of 3D navigation significantly reduced the intervention time, regardless of the localization and type of arrhythmia. At the same time, no significant difference was found in the frequency of acute arrhythmia suppression and the number of applications to achieve the effect between the studied groups.

Adherence to adhesive patch electrocardiographic monitoring among adults with disabilities.

Individuals with developmental and/or intellectual disabilities (I/DD) are at a greater risk for atrial fibrillation (AF), the most common type of cardiac arrhythmia. AF is associated with heart failure, stroke, poor mental health, and reduced quality of life. Management and treatment decisions are based on the ability to detect AF; however, noninvasive, remote cardiac monitoring may not be tolerated by individuals with I/DD. To examine adherence to the placement of an ambulatory cardiac rhythm monitoring patch device by adult patients with I/DD. Investigators extracted chart data from a consecutive series of adult patients (18 years+) who received the patch device as part of standard treatment at an adult health center between November 1, 2015 and October 31, 2019. A total of 95 patients were included in data analysis. Average age of subjects was 53.8±13.9 years (range: 20.2-88.5); 66.7% were male. All subjects had intellectual disabilities as follows: mild, 37.9%; moderate, 29.5%; severe, 21.0%; and, profound, 11.6%. With a prescribed duration of 14 days, subjects wore the device a median (interquartile range [IQR]) of 12.2days (4.1-14.0); total analysis time was a median of 9.5 days (3.4-13.5). A total of 29 subjects (30.5%) received cardiac diagnoses not previously identified (median=1 new diagnosis; range: 1-5). This pilot study suggests the possible utility of an ambulatory monitoring patch device in an adult population with I/DD. Investigators recommend larger studies to confirm such preliminary findings to ultimately improve clinical management and patient quality of life.

Impact of artificial intelligence arrhythmia mapping on time to first ablation, procedure duration, and fluoroscopy use.

Artificial intelligence (AI) ECG arrhythmia mapping provides arrhythmia source localization using 12-lead ECG data; whether this information impacts procedural efficiency is unknown. We performed a retrospective, case-control study to evaluate the hypothesis that AI ECG mapping may reduce time to ablation, procedural duration, and fluoroscopy. Cases in which system output was used were retrospectively enrolled according to IRB-approved protocols at each site. Matched control cases were enrolled in reverse chronological order beginning on the last day for which the technology was unavailable. Controls were matched based upon physician, institution, arrhythmia, and a predetermined complexity rating. Procedural metrics, fluoroscopy data, and clinical outcomes were assessed from time-stamped medical records. The study group consisted of 28 patients (age 65 ± 11 years, 46% female, left atrialdimension 4.1 ± 0.9 cm, LVEF 50 ± 18%) and was similar to 28 controls. The most common arrhythmia types were atrial fibrillation (n = 10), premature ventricular complexes (n = 8), and ventricular tachycardia (n = 6). Use of the system was associated with a 19.0% reduction in time to ablation (133 ± 48 vs. 165 ± 49 min, p = 0.02), a 22.6% reduction in procedure duration (233 ± 51 vs. 301 ± 83 min, p < 0.001), and a 43.7% reduction in fluoroscopy (18.7 ± 13.3 vs. 33.2 ± 18.0 min, p < 0.001) versus controls. At 6 months follow-up, arrhythmia-free survival was 73.5% in the study group and 63.3% in the control group (p = 0.56). Use of forward-solution AI ECG mapping is associated with reductions in time to first ablation, procedure duration, and fluoroscopy without an adverse impact on procedure outcomes or complications.

Person identification with arrhythmic ECG signals using deep convolution neural network

Over the past decade, the use of biometrics in security systems and other applications has grown in popularity. ECG signals in particular are attracting increased attention due to their characteristics, which are required for a trustworthy identification system. The majority of ECG-based person identification systems are evaluated without considering the health-state of the individuals. Few person identification systems consider person-by-person health-state annotation. This paper proposes a person identification system considering the health-state annotated ECG signals where each person’s beats overlap among variant arrhythmia classes. This overlapping between the normal class and other arrhythmia classes grants the ability to isolate normal beats in the train set from the Arrhythmic beats in the test set. Therefore, this paper investigates the effect of arrhythmic heartbeats on biometric recognition. An effective lightweight CNN based on depth-wise separable convolution (DWSC) is proposed to enhance the performance of person identification for several common arrhythmia types using the MITBIH dataset. The proposed methodology has been tested on nine arrhythmia types and presents how different types of arrhythmia affect ECG-based biometric systems differently. The experimental results show excellent recognition performance (99.28%) on normal heartbeats and (93.81%) on arrhythmic heartbeats, outperforming other models in terms of mean accuracy.

Efficacy of dapagliflozin in improving arrhythmia-related outcomes after ablation for atrial fibrillation: a retrospective single-center study.

Atrial fibrillation (AF) is a widespread type of sustained arrhythmia that poses significant health risks. Catheter ablation is the preferred treatment; however, arrhythmia recurrence remains challenging. Sodium-glucose co-transporter 2 inhibitors, particularly dapagliflozin (DAPA), have exhibited cardiovascular benefits. However, to date, the influence of these inhibitors on AF post-ablation remains unclear. We analyzed the records of 272 patients who underwent catheter ablation for AF from January 2018 to December 2022. Patients were divided into the control (n = 199) and DAPA (n = 73) groups based on DAPA prescription post-ablation. The primary outcome was total atrial arrhythmia recurrence after a 3-month blanking period. The mean age was 72.19 ± 5.45years; 86.8% of the patients were men. At 18months post-ablation, 36.2% and 9.5% of the patients in the control and DAPA groups, respectively, reported atrial arrhythmia. Multivariate analysis revealed that DAPA use was associated with a significantly reduced risk of arrhythmia recurrence (adjusted hazard ratio [aHR]: 0.15, 95% confidence interval [CI]: 0.07-0.32, p < 0.001). After propensity score-matching (PSM) in 65 pairs, arrhythmia recurrence was lower in the DAPA group compared with the control (8.3% versus 30.8%, aHR: 0.17, 95% CI: 0.06-0.51, p = 0.002). Freedom from total arrhythmia recurrence was significantly higher in the DAPA group compared with the control group in both the overall and PSM population (log-rank test p < 0.01). DAPA administration post-ablation was associated with significantly reduced atrial arrhythmia recurrence rates, indicating its potential as an adjunct therapy for enhancing the success of AF ablation.

Unveiling the Role of Endothelial Dysfunction: A Possible Key to Enhancing Catheter Ablation Success in Atrial Fibrillation.

Atrial fibrillation, a prevalent type of arrhythmia, is increasingly contributing to the economic burden on healthcare systems. The development of innovative treatments, notably catheter ablation, has demonstrated both impressive and promising outcomes. However, these treatments have not yet fully replaced pharmaceutical approaches, primarily due to the relatively high incidence of atrial fibrillation recurrence post-procedure. Recent insights into endothelial dysfunction have shed light on its role in both the onset and progression of atrial fibrillation. This emerging understanding suggests that endothelial function might significantly influence the effectiveness of catheter ablation. Consequently, a deeper exploration into endothelial dynamics could potentially elevate the status of catheter ablation, positioning it as a primary treatment option for atrial fibrillation.

Res-BiANet: A Hybrid Deep Learning Model for Arrhythmia Detection Based on PPG Signal

Arrhythmias are among the most prevalent cardiac conditions and frequently serve as a direct cause of sudden cardiac death. Hence, the automated detection of arrhythmias holds significant importance for assisting in the diagnosis of heart conditions. Recently, the photoplethysmography (PPG) signal, capable of conveying heartbeat information, has found application in the field of arrhythmia detection research. This work proposes a hybrid deep learning model, Res-BiANet, designed for the detection and classification of multiple types of arrhythmias. The improved ResNet and BiLSTM models are connected in parallel, and spatial and temporal features of PPG signals are extracted using ResNet and BiLSTM, respectively. Subsequent to BiLSTM, a multi-head self-attention mechanism was incorporated to enhance the extraction of global temporal correlation features over long distances. The model classifies five types of arrhythmia rhythms (premature ventricular contractions, premature atrial contractions, ventricular tachycardia, supraventricular tachycardia, and atrial fibrillation) and normal rhythm (sinus rhythm). Based on this foundation, experiments were conducted utilizing publicly accessible datasets, encompassing a total of 46,827 PPG signal fragments from 91 patients with arrhythmias. The experimental results demonstrate that Res-BiANet achieved exceptional classification performance, including an F1 score of 86.88%, overall accuracy of 92.38%, and precision, sensitivity, and specificity of 88.46%, 85.15%, and 98.43%, respectively. The outstanding performance of the Res-BiANet model suggests significant potential in supporting the auxiliary diagnosis of multiple types of arrhythmias.

Polymorphic Variants of SCN5A Gene (rs41312433 and rs1805124) Associated with Coronary Artery Affliction in Patients with Severe Arrhythmias.

A group of 32 unrelated individuals, aged 63 ± 12 years, was included in the study. All the patients were examined, diagnosed and treated with an implantable cardioverter defibrillator at the Department of Internal Cardiology Medicine, Faculty Hospital Brno. The control group included 87 persons of similar age without afflicted coronary circulation, which was confirmed coronagraphically. Genomic DNA was extracted from samples of peripheral blood according to the standard protocol. Two SCN5A polymorphisms-IVS9-3C/A (rs41312433) and A1673G (rs1805124, H558R)-were examined in association with coronary artery stenosis in the patients. In the case-control study, no significant differences in genotype distribution/allelic frequencies were observed for IVS9-3c>a and A1673G gene polymorphisms between patients with severe arrhythmias and healthy persons. The distribution of SCN5A double genotypes was not significantly different among different types of arrhythmias according to their ejection fraction in arrhythmic patients (p = 0.396). The ventricular arrhythmias with an ejection fraction below 40% were found to be 10.67 times more frequent in patients with multiple coronary stenosis with clinically valid sensitivity, specificity and power tests. In the genotype-phenotype study, we observed a significant association of both SCN5A polymorphisms with the stenosis of coronary vessels in the patients with severe arrhythmia. The double genotype of polymorphisms IVS9-3C/A together with A1673G (CCAA) as well as their simple genotypes were associated with significant multiple stenosis of coronary arteries (MVS) with high sensitivity and specificity (p = 0.05; OR = 5 (95% CI 0.99-23.34); sensitivity 0.70; specificity 0.682; power test 0.359) Moreover, when a concrete stenotic coronary artery was associated with SCN5A genotypes, the CCAA double genotype was observed to be five times more frequent in patients with significant stenosis in the right coronary artery (RCA) compared to those without affliction of this coronary artery (p = 0.05; OR = 5 (95% CI 0.99-23.34); sensitivity 0.682; specificity 0.700; power test 0.359). The CCAA genotype was also more frequent in patients without RCA affliction with MVS (p = 0.008); in patients with ACD affliction but without MVS (p = 0.008); and in patients with both ACD affliction and MVS compared to those without ACD affliction and MVS (p = 0.005). Our study presents a highly sensitive and specific association of two polymorphisms in SCN5A with significant coronary artery stenoses in patients with potentially fatal ventricular arrhythmias. At the same time, these polymorphisms were not associated with arrhythmias themselves. Thus, SCN5A gene polymorphic variants may form a part of germ cell gene predisposition to ischemia.

The influence of cardiac arrhythmias on the detection of heartbeats in the photoplethysmogram: benchmarking open-source algorithms.

Objective.Cardiac arrhythmias are a leading cause of mortality worldwide. Wearable devices based on photoplethysmography give the opportunity to screen large populations, hence allowing for an earlier detection of pathological rhythms that might reduce the risks of complications and medical costs. While most of beat detection algorithms have been evaluated on normal sinus rhythm or atrial fibrillation recordings, the performance of these algorithms in patients with other cardiac arrhythmias, such as ventricular tachycardia or bigeminy, remain unknown to date.Approach.ThePPG-beatsopen-source framework, developed by Charlton and colleagues, evaluates the performance of the beat detectors namedQPPG,MSPTDandABDamong others. We applied thePPG-beatsframework on two newly acquired datasets, one containing seven different types of cardiac arrhythmia in hospital settings, and another dataset including two cardiac arrhythmias in ambulatory settings.Main Results.In a clinical setting, theQPPGbeat detector performed best on atrial fibrillation (with a medianF1score of 94.4%), atrial flutter (95.2%), atrial tachycardia (87.0%), sinus rhythm (97.7%), ventricular tachycardia (83.9%) and was ranked 2nd for bigeminy (75.7%) behindABDdetector (76.1%). In an ambulatory setting, theMSPTDbeat detector performed best on normal sinus rhythm (94.6%), and theQPPGdetector on atrial fibrillation (91.6%) and bigeminy (80.0%).Significance.Overall, the PPG beat detectorsQPPG,MSPTDandABDconsistently achieved higher performances than other detectors. However, the detection of beats from wrist-PPG signals is compromised in presence of bigeminy or ventricular tachycardia.

Classification of underlying paroxysmal supraventricular tachycardia types using deep learning of sinus rhythm electrocardiograms.

Obtaining tachycardia electrocardiograms (ECGs) in patients with paroxysmal supraventricular tachycardia (PSVT) is often challenging. Sinus rhythm ECGs are of limited predictive value for PSVT types in patients without preexcitation. This study aimed to explore the classification of atrioventricular nodal reentry tachycardia (AVNRT) and concealed atrioventricular reentry tachycardia (AVRT) using sinus rhythm ECGs through deep learning. This retrospective study included patients diagnosed with either AVNRT or concealed AVRT, validated through electrophysiological studies. A modified ResNet-34 deep learning model, pre-trained on a public ECG database, was employed to classify sinus rhythm ECGs with underlying AVNRT or concealed AVRT. Various configurations were compared using ten-fold cross-validation on the training set, and the best-performing configuration was tested on the hold-out test set. The study analyzed 833 patients with AVNRT and 346 with concealed AVRT. Among ECG features, the corrected QT intervals exhibited the highest area under the receiver operating characteristic curve (AUROC) of 0.602. The performance of the deep learning model significantly improved after pre-training, showing an AUROC of 0.726 compared to 0.668 without pre-training (p < 0.001). No significant difference was found in AUROC between 12-lead and precordial 6-lead ECGs (p = 0.265). On the test set, deep learning achieved modest performance in differentiating the two types of arrhythmias, with an AUROC of 0.708, an AUPRC of 0.875, an F1-score of 0.750, a sensitivity of 0.670, and a specificity of 0.649. The deep-learning classification of AVNRT and concealed AVRT using sinus rhythm ECGs is feasible, indicating potential for aiding in the non-invasive diagnosis of these arrhythmias.

Protocol for a multicentre and prospective follow-up cohort study of early detection of atrial fibrillation, silent stroke and cognitive impairment in high-risk primary care patients: the PREFA-TE study

BackgroundAtrial fibrillation (AF) is the most common type of cardiac arrhythmia. Future estimations suggest an increase in global burden of AF greater than 60% by 2050. Numerous studies provide growing...

Advancements in Artificial Intelligence for ECG Signal Analysis and Arrhythmia Detection: A Review

Context: With the widespread availability of portable electrocardiogram (ECG) devices, there is an increasing interest in utilizing artificial intelligence (AI) methods for ECG signal analysis and arrhythmia detection. The potential benefits of AI-assisted arrhythmia prognosis, early screening, and improved accuracy in arrhythmia classification are discussed. Evidence Acquisition: Artificial intelligence methods are a new way to classify different types of arrhythmias. For example, deep learning (DL) algorithms, including long short-term memory (LSTM) networks, convolutional neural networks (CNN), CNN-based autoencoders (AE), and convolutional recurrent neural networks (CRNN), have been extensively utilized for ECG signal analysis and arrhythmia detection. Results: This study explores different DL techniques for classifying arrhythmias. The two-dimensional (2D) CNN model achieved an accuracy of 97.42% in classifying five different arrhythmias. After classifying five types of ECG signals, an accuracy of 99.53% was achieved by the CNN-based AE and transfer learning (TL) models. The CNN-Bi-LSTM model achieved an accuracy of 98.0% in categorizing five categories of ECG signals. The CNN+LSTM model achieved an accuracy of 98.24% in classifying five classes of arrhythmias. The CNN-support vector machine (SVM) classifier model demonstrated an accuracy of 98.64% in detecting seventeen classes of heartbeats. The results indicated that the CNN-based AE and TL models perform exceptionally well with high accuracy in detecting ECG signals. Conclusions: The present study demonstrates the growing interest in utilizing DL for ECG signal detection in medical and healthcare applications over the past decade. Deep learning models have been shown to outperform experienced cardiologists, delivering state-of-the-art and more accurate results.

Implantable cardiac monitors: artificial intelligence and signal processing reduce remote ECG review workload and preserve arrhythmia detection sensitivity.

Implantable cardiac monitors (ICMs) provide long-term arrhythmia monitoring, but high rates of false detections increase the review burden. The new "SmartECG" algorithm filters false detections. Using large real-world data sets, we aimed to quantify the reduction in workload and any loss in sensitivity from this new algorithm. Patients with a BioMonitor IIIm and any device indication were included from three clinical projects. All subcutaneous ECGs (sECGs) transmitted via remote monitoring were classified by the algorithm as "true" or "false." We quantified the relative reduction in workload assuming "false" sECGs were ignored. The remote monitoring workload from five hospitals with established remote monitoring routines was evaluated. Loss in sensitivity was estimated by testing a sample of 2000 sECGs against a clinical board of three physicians. Of our population of 368 patients, 42% had an indication for syncope or pre-syncope and 31% for cryptogenic stroke. Within 418.5 patient-years of follow-up, 143,096 remote monitoring transmissions contained 61,517 sECGs. SmartECG filtered 42.8% of all sECGs as "false," reducing the number per patient-year from 147 to 84. In five hospitals, nine trained reviewers inspected on average 105 sECGs per working hour. This results in an annual working time per patient of 83 min without SmartECG, and 48 min with SmartECG. The loss of sensitivity is estimated as 2.6%. In the majority of cases where true arrhythmias were rejected, SmartECG classified the same type of arrhythmia as "true" before or within 3 days of the falsely rejected sECG. SmartECG increases efficiency in long-term arrhythmia monitoring using ICMs. The reduction of workload by SmartECG is meaningful and the risk of missing a relevant arrhythmia due to incorrect filtering by the algorithm is limited.

Unveiling the silent threat of new onset atrial fibrillation in covid-19 hospitalized patients: A retrospective cohort study.

COVID-19, a highly infectious respiratory disease, has been associated with a range of cardiovascular complications. One of the most commonly reported cardiovascular issues in COVID-19 patients is the development of arrhythmias. Among all types of arrhythmias, atrial fibrillation is the most frequently observed. Atrial fibrillation is characterized by an irregular and often rapid heartbeat, and it can be a serious and potentially life-threatening condition. To investigate the incidence and association of new onset atrial fibrillation in COVID-19 hospitalized patients and its impact on survival. A retrospective cross-sectional study that encompassed all patients, both positive and negative for COVID-19, who were consecutively admitted to the Aga Khan University Hospital in Karachi, a tertiary care facility, from June 2021 to December 2021. A total of 1,313 patients who met the inclusion criteria of our study were enrolled as participants. These patients were then stratified into two groups based on COVID-19 status: the study group (COVID-19 positive) comprised 626 (47.7%) patients and the control group (COVID-19 negative) consisted of 687 (52.3%) patients. The incidence of new-onset atrial fibrillation was 85 (13.6%) in COVID-19 positive compared to 43 (5.2%) in COVID-19 negative group. The study found a strong association between COVID-19 and new-onset atrial fibrillation in both univariate (unadjusted odd ratio 2.35 [95% CI, 1.60-3.45], p-value < 0.01) and a multiple-adjusted regression analysis (adjusted odd ratio 3.86 [95% CI, 2.31-6.44], p-value < 0.01). These findings highlight the importance of vigilant monitoring of cardiovascular complications in COVID-19 patients, especially those with pre-existing conditions that predispose them to the development of atrial fibrillation. The study underscores the need for prompt recognition and management of new onset atrial fibrillation in COVID-19 patients, as this may mitigate the risk of adverse outcomes and improve overall prognosis.