Type Of Arrhythmia Research Articles

Arrhythmia Burden in Congenitally Corrected Transposition of the Great Arteries (cc-TGA): Does Treatment Pathway Matter?

There is limited data comparing arrhythmia burden amongst patients with congenitally corrected transposition of the great arteries (cc-TGA) undergoing anatomic repair (AR), physiologic repair (PR), and non-surgical management (NS). To examine the difference in rate of brady- and tachyarrhythmias amongst patients with cc-TGA stratified by treatment pathway. A retrospective cohort study was conducted including all patients with cc-TGA followed at Cleveland Clinic Children's (1995-2021). A total of 170 patients were included with a median follow up of 11.8 years, 82 AR (median age 1.5 yrs), 46 PR (median age 25.2 yrs), and 42 NS (median age 35.7 yrs). Heart block/pacemaker implantation occurred in 49 (29%) patients, with higher prevalence in the PR group compared to AR and NS (50% vs. 22% vs. 19%, p = 0.001). Freedom from postoperative CHB/PPM implantation at 5 years was higher in patients who underwent AR vs. PR (85% vs. 68%, p = 0.02). Tachyarrhythmias affected 29% of patients, with varying prevalence of atrial fibrillation and atrial flutter based on treatment pathway. Atrial fibrillation was more prevalent in PR and NS groups compared to AR group (30% vs. 31% vs. 0%, p < 0.0001). Prevalence of atrial flutter was 9.8% vs. 13% vs. 0% in the AR, PR, and NS groups, respectively. Burden and type of arrhythmias in cc-TGA varied based on treatment pathway. Further studies assessing long-term follow up after AR are needed to identify the surgical approach that would yield the lowest arrhythmia morbidity.

Interventional Cardiac Electrophysiology for the Management of Adults With Congenital Heart Disease.

Congenital heart disease (CHD) is the most common congenital anomaly in newborns. Advances in catheter and surgical techniques led to the majority of these patients surviving into adulthood, leading to evolving challenges due to the emergence of long-term complications such as arrhythmias. Interventional electrophysiology (EP) has had remarkable advances over the last few decades, and various techniques and devices have been explored to treat adult patients with CHD. This comprehensive review aims to summarize findings from recent studies exploring advances in the use of interventional electrophysiology to manage adult patients with CHD. While pacemaker therapy has some indications in adults with CHD, various long-term consequences include pacing-induced cardiomyopathy and complications requiring reintervention. Cardiac resynchronization therapy has shown promising results in some studies to treat CHD patients with heart failure, although further research to clarify guidelines is encouraged. Implantable cardiac defibrillators have demonstrated clear benefits in CHD patients and are indicated for primary prevention of sudden cardiac death, although selection criteria for secondary prevention of sudden cardiac death are uncertain. Catheter ablation has also been used for various atrial and ventricular arrhythmias in patients with CHD with high success rates, although the likelihood of success depends on patient characteristics and the type of arrhythmia, and multidisciplinary assessment is encouraged to improve the chance of successful therapy.

Recurrent atrial fibrillation markers post radiofrequency catheter ablation.

Atrial fibrillation (AF), the most common type of heart arrhythmia, is recognized as an independent risk factor for stroke. Fortunately, catheter ablation (CA) offers an effective treatment option for AF patients. However, numerous studies have reported suboptimal outcomes, as AF recurrence rates often remain elevated even after CA. Consequently, there exists a need for early identification of patients prone to recurrence, necessitating anti-inflammatory and/or antiarrhythmic treatment post-CA. The discovery and application of markers associated with AF recurrence could significantly aid in this early identification process. In this review, we present an overview of AF recurrence markers from three distinct perspectives (biochemical, imaging, and electrocardiographic markers).

Classification of Cardiac Arrhythmias Based on Electrocardiogram Data Using a Convolutional Neural Network Model

Cardiac arrhythmias are a disease with considerable incidence and prevalence worldwide, and their diagnosis can be complex due to the existence of different types of arrhythmias that share similar characteristics and make an accurate diagnosis difficult. Making a correct diagnosis of the kind of arrhythmia that affects an individual is important to define the most appropriate type of treatment for the case. Machine Learning and Deep Learning techniques have been proposed to automate the diagnosis of arrhythmias to assist healthcare professionals in decision-making. This study proposes a Convolutional Neural Network model for classifying cardiac arrhythmias using electrocardiogram data. The objective is to present a model that achieves high accuracy rates in identifying types of arrhythmias and presents an adequate balance between performance and computational costs. The model was trained with a dataset composed of electrocardiogram exams with 32 types of arrhythmias. In the pre-processing phase, the dataset was restructured to allow the data to be treated as a time series to explore the potential of Convolutional Neural Networks in dealing with data organized in this way. Training was carried out using a state-of-the-art Deep Learning model and the model achieved an accuracy rate of 98.37% in its predictions. This excellent performance confirms the ability of Convolutional Neural Networks to efficiently deal with pattern learning in time series. The results obtained demonstrate the potential of Deep Learning techniques as aiding tools to provide improvements in medical processes.

Cardioattentionnet: advancing ECG beat characterization with a high-accuracy and portable deep learning model.

The risk of mortality associated with cardiac arrhythmias is considerable, and their diagnosis presents significant challenges, often resulting in misdiagnosis. This situation highlights the necessity for an automated, efficient, and real-time detection method aimed at enhancing diagnostic accuracy and improving patient outcomes. The present study is centered on the development of a portable deep learning model for the detection of arrhythmias via electrocardiogram (ECG) signals, referred to as CardioAttentionNet (CANet). CANet integrates Bi-directional Long Short-Term Memory (BiLSTM) networks, Multi-head Attention mechanisms, and Depthwise Separable Convolution, thereby facilitating its application in portable devices for early diagnosis. The architecture of CANet allows for effective processing of extended ECG patterns and detailed feature extraction without a substantial increase in model size. Empirical results indicate that CANet outperformed traditional models in terms of predictive performance and stability, as confirmed by comprehensive cross-validation. The model demonstrated exceptional capabilities in detecting cardiac arrhythmias, surpassing existing models in both cross-validation and external testing scenarios. Specifically, CANet achieved high accuracy in classifying various arrhythmic events, with the following accuracies reported for different categories: Normal (97.37 ± 0.30%), Supraventricular (98.09 ± 0.25%), Ventricular (92.92 ± 0.09%), Atrial Fibrillation (99.07 ± 0.13%), and Unclassified arrhythmias (99.68 ± 0.06%). In external evaluations, CANet attained an average accuracy of 94.41%, with the area under the curve (AUC) for each category exceeding 99%, thereby demonstrating its substantial clinical applicability and significant advancements over traditional models. The deep learning model proposed in this study has the potential to enhance the accuracy of early diagnosis for various types of arrhythmias. Looking ahead, this technology is anticipated to provide improved medical services for patients with heart disease through continuous, non-invasive monitoring and timely intervention.

Plasma Cardiac Troponin-I Concentration in Normal Horses and in Horses with Cardiac Abnormalities.

Cardiac troponin-I (cTnI) is a highly sensitive and specific marker of myocardial injury detectable in plasma by immunoassay techniques. Inclusion criteria over a 3-year period required a diagnosis of cardiac disease accompanied by electrocardiographic (ECG) and cardiac ultrasound examinations (n = 23) in adult horses (≥2 years of age). A second group of normal adult ponies (n = 12) was studied as a reference group. Heparinized jugular venous blood samples were collected and centrifuged within 30 min, and the plasma was separated and frozen at -70 °C for subsequent batched cTnI analysis. The lower limit of detection was 0.01 ng/mL, and the upper limit was 100 ng/mL of plasma. Normal equine plasma cTnI concentrations ranged from 0.01 to 0.03 ng/mL (n = 12). Horses with non-arrhythmogenic murmurs (n = 4) included tricuspid (0.05 ng/mL cTnI), mitral (0.07), and aortic insufficiencies (0.01, 0.02). Horses with benign atrial fibrillation (n = 8) had a cTnI range of <0.01-0.09 ng/mL, with four horses having cTnI concentrations falling slightly outside the reference range (0.04, 0.05, 0.06, and 0.09). Horses with ventricular arrhythmias (ventricular premature contractions or ventricular tachycardia) and documentable myocardial toxicities or immunological reactions (n = 5) had cTnI concentrations of 0.05, 0.21, 0.31, 15.18, and >100 ng/mL. Horses with ventricular arrhythmias but no documentation of myocardial toxicity (n = 3) had cTnI concentrations of 0.34, 0.46, and 80.42 ng/mL. When grouped by arrhythmia type and compared using the Mann-Whitney Rank Sum Test, the median ventricular arrhythmia cTnI (0.40 ng/mL) was significantly higher than the median atrial fibrillation cTnI (0.04 ng/mL, p < 0.001). It was concluded that horses with myocardial toxicities and ventricular arrhythmias often had severe elevations in plasma cTnI.

Prediction of self-terminating Ventricular Tachycardia in isolated rat heart experiments by using wavelet analysis

This study investigates whether self-terminating and prolonged ventricular tachycardias (VT) can be differentiated using cross-wavelet analysis. VT is a type of arrhythmia that may persist or transform into other arrhythmias. In this study, 40 VT samples from 7 isolated rat hearts are analyzed, including 19 prolonged VTs and 21 self-terminating VTs (STVTs). Bivariate timeseries of left ventricular and right atrium are analyzed using cross-wavelet analysis to find correlations between the signals. The results show that self-terminating VT occurs most frequently when there is a weak correlation between the signals, while prolonged VT is associated with a strong correlation between ventricular and atrial signals. The study suggests that mechano-electrical interaction between the right atrium and left ventricle may be the underlying mechanism for this connection. The findings may have implications for understanding the underlined mechanism and treatment of VT in clinical practice.

Accurate Arrhythmia Classification with Multi-Branch, Multi-Head Attention Temporal Convolutional Networks.

Electrocardiogram (ECG) signals contain complex and diverse features, serving as a crucial basis for arrhythmia diagnosis. The subtle differences in characteristics among various types of arrhythmias, coupled with class imbalance issues in datasets, often hinder existing models from effectively capturing key information within these complex signals, leading to a bias towards normal classes. To address these challenges, this paper proposes a method for arrhythmia classification based on a multi-branch, multi-head attention temporal convolutional network (MB-MHA-TCN). The model integrates three convolutional branch layers with different kernel sizes and dilation rates to capture features across varying temporal scales. A multi-head self-attention mechanism dynamically allocates weights, integrating features and correlations from different branches to enhance the recognition capability for difficult-to-classify samples. Additionally, the temporal convolutional network employs multi-layer dilated convolutions to progressively expand the receptive field for extracting long-term dependencies. To tackle data imbalance, a novel data augmentation strategy is implemented, and focal loss is utilized to increase the weight of minority classes, while Bayesian optimization is employed to fine-tune the model's hyperparameters. The results from five-fold cross-validation on the MIT-BIH Arrhythmia Database demonstrate that the proposed method achieves an overall accuracy of 98.75%, precision of 96.60%, sensitivity of 97.21%, and F1 score of 96.89% across five categories of ECG signals. Compared to other studies, this method exhibits superior performance in arrhythmia classification, significantly improving the recognition rate of minority classes.

Perioperative Cardiac Dysrhythmias In The Neonate – Bradycardia and Tachycardia

Managing neonates in a perioperative setting is a challenging task. Neonates differ from pediatric and adult patients in many ways. Anesthesiologists should have knowledge and skills in the recognition and prompt treatment of cardiac dysrhythmias in these babies. We emphasize the etiology, recognition, implications, and management of the most common types of arrhythmias, bradycardia, and tachycardia in neonates in the perioperative period.

Arrhythmias Following Patent Foramen Ovale Closure: An Unsolved Enigma.

Patent foramen ovale (PFO) closure has proven to be an effective method of reducing the risk of recurrent stroke in patients with embolic stroke of unknown origin (ESUS). One of the most recognized post-procedural complications is the de novo occurrence of supraventricular arrhythmias, mainly atrial fibrillation, in the first three months following PFO closure. Earlier studies reported the incidence to be around 3.4-7%; however, this percentage has risen in recent studies up to 21%. The pathogenesis behind this type of arrhythmia is complex and not clearly understood, although it seems that direct effects of the device on the atria, as well as an inflammatory response, are the two most prevalent mechanisms. Management of this complication might be challenging given the heterogenicity of patient characteristics, so an individualized approach is most wisely followed. This review aims to present the current data on the incidence, pathogenesis and therapeutic strategies behind this rather common concern in an era of increasing transcatheter interventions for PFO.

Machine Learning-Based Identification of High-Risk Patterns in Atrial Fibrillation Ablation Outcomes.

Atrial fibrillation (AF) is one of the most common types of cardiac arrhythmias, often leading to serious health issues such as stroke, heart failure, and higher mortality rates. Its global impact is rising due to aging populations and growing comorbidities, creating an urgent need for more effective treatment methods. AF ablation, a key treatment option, has success rates that vary widely among patients. Conventional predictors of ablation outcomes, which primarily rely on sociodemographic and clinical factors, fall short of capturing the heterogeneity within patient populations, highlighting the potential for data-driven methods to provide deeper insights into procedural success. To uncover meaningful patient subgroups based on AF ablation outcomes and identify diagnostic codes associated with failure. Machine learning clustering with must-link and cannot-link constraints was applied to electronic health records to discover meaningful clusters, revealing patient-specific factors influencing procedural success or failure. Statistical analyses, including chi-square tests, were used to identify diagnostic codes significantly associated with ablation failure. Out of the 145 diagnostic codes examined, thirteen significant codes were identified and categorized into four primary risk groups, ranked by their impact on procedural outcomes: (1) direct contributors affecting cardiovascular health, (2) indirect factors that contribute to systemic stress, (3) complications related to anticoagulation and hemorrhagic risks that can impact bleeding management, and (4) broader health indicators reflecting a general health burden that reduce patients resilience to procedural stress. This study shows the importance of cardiovascular and non-cardiovascular factors in AF ablation outcomes, emphasizing the need for a more comprehensive pre-procedural evaluation. It also contributes to the application of machine learning in personalized risk assessment for AF and advancing individualized care strategies that may improve ablation success.

A cross sectional study on prevalence of hypomagnesemia and hypokalemia in patients with STEMI and its relationship with occurrence of arrhythmias

Background: Cardiovascular disease is one of the leading causes of mortality, morbidity, and increased health-care cost. Magnesium and potassium has been implicated in the pathogenesis of acute myocardial infarction (AMI) and its complications. Magnesium ions and potassium ions are considered essential for the maintenance of functional integrity of myocardium. The serum magnesium and potassium concentration was found to have great significance in AMI. The present study was undertaken to evaluate the prognostic value of serum magnesium and potassium in AMI. Aim: This study aimed to assess the dynamic changes in serum magnesium and potassium levels in acute STEMI patients and evaluate whether these levels correlate with presence of arrhythmias. Materials and methods: A comprehensive analysis was conducted over 18 months on 100 patients with acute STEMI. ECG examination was done and blood sample was taken for evaluation of serum magnesium and serum potassium. Statistical analysis was performed to examine correlation with MI and arrhythmias. Results: In the present study 51-60 years of age were maximum, males were most commonly seen. Mean ±SD of serum magnesium in VPC was 1.900±.3232, sinus tachycardia was 1.850±.1195, maximum in RBBB was 2.200±.000 followed by RBBB/CHB was 2±0, and minimum in 1.288±.5621. Results were found to be significant when comparing type of arrhythmia with serum magnesium. Mean ±SD of serum potassium in VPC was 3.030±.9627, sinus tachycardia was 3.638±.4502, maximum in RBBB was 4.600±.000 and minimum VT/RBBB in 2.850±1.0344. Results were found to be significant. Conclusion: Patients of AMI with low serum magnesium and potassium levels are found to be more prone to develop arrhythmias as compared to those with normal serum magnesium and potassium levels. Hence, it can be concluded that measurement of serum magnesium and potassium level is of prognostic significance in AMI.

Blending Ensemble Learning Model for 12-Lead Electrocardiogram-Based Arrhythmia Classification

The increasing prevalence of heart diseases has driven the development of automated arrhythmia classification systems using machine learning and electrocardiograms (ECGs). This paper presents a novel ensemble learning method for classifying multiple arrhythmia types using 12-lead ECG signals through a blending technique. The framework employs a predetermined meta-model from foundation models, while the remaining models serve as potential base estimators, ranked by accuracy. Using sequential forward selection and meta-feature augmentation, the system determines an optimal base estimator set and creates a meta-dataset for the meta-model, which is optimized through grid search with k-fold cross-validation. Experiments conducted with seven diverse machine learning algorithms (Adaptive Boosting, Extreme Gradient Boosting, Decision Trees, k-Nearest Neighbors, Logistic Regression, Random Forest, and Support Vector Machine) demonstrate that the proposed blending solution, utilizing an LR meta-model with three optimal base models, achieves a superior classification accuracy of 96.48%, offering an effective tool for clinical decision support.

Метод класифікації аритмій на ЕКГ-сигналі

This paper proposes an improved arrhythmia classification method based on a convolutional neural network (CNN) applied to ECG signals. To improve the quality of classification, ECG signals were split into fragments containing three cardiac cycles with the current cardiac cycle in the center. The improved CNN architecture includes the addition of batch normalization layers, an additional convolutional layer, and a dropout layer, which improvs the model's accuracy. In addition, hyperparameters were optimized for new CNN architecture. The model was trained data of the MIT-BIH Arrhythmia Database to classify nine classes of ECG. The achieved average accuracy of 99.26% confirms the effectiveness of the proposed method in diagnosing various types of arrhythmias

Cardiac Ablation in the Pediatric Population at a Tertiary Care Center in a Developing Country.

The aim of this study was to describe our experience and outcome of ablation therapy for arrhythmias in pediatrics at a tertiary care center. Data was collected retrospectively from the hospital medical records. All pediatrics presenting to AUBMC between 2000 and 2020 who underwent cardiac ablation were included. The data collected included type of arrhythmia, ablation technique, age and weight at ablation, procedure complications, medications used, and outcome assessment. We had 67 patients who underwent cardiac ablation. Of those, 60% were males with a mean age of 15 years. Structural heart disease was present in 6% of patients. Wolff-Parkinson-White syndrome (WPW) was most prevalent at 31%, followed by atrioventricular nodal reentrant tachycardia (AVNRT) at 24%, atrioventricular reentrant tachycardia (AVRT) at 16%, ventricular tachycardia (VT) at 10%, atrial fibrillation (AF) at 3%, and atrial tachycardia (AT) at 1%. The remaining 15% of patients presented with less common types of arrhythmias, including other supraventricular tachycardias (SVTs), retrograde dual atrioventricular nodal reentry, and premature ventricular contractions (PVC). Antiarrhythmic medications were started before the procedure in 59% of our population. Medication regimens postablation included beta-blockers (68%), type 1c antiarrhythmics (25%), calcium channel blockers (3%), ivabradine (2%), and amiodarone (2%). The completed procedures showed a success rate of 93%. Ablation of arrhythmias in pediatrics is an effective procedure in the treatment of childhood arrhythmias. More studies are needed on cardiac ablation in this age group and those with structural heart disease in the Middle East region.

Association of coffee consumption and caffeine metabolism with arrhythmias and cardiac morphology: an observational, genetic and Mendelian Randomization study

The association of coffee intake and caffeine metabolism with arrhythmias and cardiac structure is not fully understood. We aim to explore the associations of coffee intake and caffeine metabolism with the risk of certain types of arrhythmias, a broad range of cardiovascular imaging phenotypes, and a potential gene-coffee interaction. On the basis of the UK Biobank imaging study, heart metrics were extracted via cardiovascular magnetic resonance using machine learning. Caffeine metabolism was determined by cytochrome P4501A2 gene (CYP1A2) or a polygenetic score of different genetic variants influencing caffeine metabolism. Genome-wide association data for 2-sample Mendelian randomization originated predominantly from individuals of European descent. A total of 34,992 individuals (mean age 63.5 ± 7.5 years; 52.9% female) were assessed in the principal imaging analysis. Higher daily consumption of coffee was independently associated with higher left ventricular mass, larger global ventricular volume, higher ventricular stroke volume, and larger atrial volume. The results were further supported by Mendelian randomization analysis. CYP1A2 and genetic score for caffeine metabolism were not associated with cardiovascular measurements (P>.053 for all tests). Coffee consumption was associated with a lower risk of sinus rhythm with short PR (per cup increase: odds ratio 0.90; 95% confidence interval 0.82-0.99) and atrial fibrillation (odds ratio 0.89; 95% confidence interval 0.84-0.93). Coffee consumption was associated with a lower risk of atrial fibrillation, increased left ventricular mass, elevated ventricular volume, and larger atrial volume. Caffeine metabolism did not significantly alter the association. Our results suggest that customary caffeine consumption limitations aimed at arrhythmia risk reduction might be unnecessary.

Desmin-related myopathy manifested by various types of arrhythmias: a case report and literature review.

Desmin is a type III intermediate filament protein specifically expressed in muscle cells, which is encoded by the DES gene. Defects in the desmin protein and cytoskeletal instability may interfere with cardiac muscle conduction signals, a fundamental mechanism for arrhythmias in patients with desmin-related myopathy. This current case report presents a female patient in her early 20s who presented with early-onset complete atrioventricular block and complete left bundle branch block over the previous decade. More recently, she had developed ventricular tachycardia, ventricular fibrillation, atrial fibrillation and other arrhythmias. Echocardiography revealed non-compaction of the ventricular myocardium and pulmonary hypertension. Whole-exome sequencing analysis identified a heterozygous missense mutation in the DES gene: c.1216C>T (p.Arg406Trp). She was eventually diagnosed with arrhythmias due to desmin-related myopathy. A literature review of international databases was undertaken to summarise the clinical characteristics of the cardiac involvement associated with this DES gene mutation.

Efficacy of percutaneous stellate ganglion block according to ventricular arrhythmia cycle length: A post hoc subanalysis of the STAR study

BackgroundData on the predictors of percutaneous stellate ganglion block (PSGB) efficacy in electrical storm are scanty. ObjectiveWe aimed to assess whether PSGB efficacy is influenced by the arrhythmia type and cycle length before the procedure. MethodsThis is a subanalysis of the multicenter STAR study. The population was stratified into 3 groups according to the median cycle length of the latest ventricular arrhythmia before PSGB: ventricular fibrillation (VF), fast ventricular tachycardia (VT), and slow VT. The primary outcome was the number of treated arrhythmic episodes (with antitachycardia pacing or direct current shocks) in the hour immediately after PSGB compared with the hour before. ResultsWe considered 139 PSGBs from 112 patients divided into VF (51 procedures), fast VT (44 procedures, VT cycle <375 ms), and slow VT (44 procedures, VT cycle ≥375 ms). The number of treated arrhythmic episodes in the hour after every PSGB was significantly lower compared with the hour before in all groups (VF: 0 [0–1] vs 5 [2–8], P < .001; fast VT: 0 [0–0] vs 1 [0–6.5], P < .001; slow VT: 0 [0–0] vs 1 [0–4.5], P = .001). In analyzing the reduction of the number of antitachycardia pacing sequences or direct current shocks from the hour before to the hour after PSGB, a significant trend was observed across the groups (Jonckheere-Terpstra trend P < .001), and a significant difference was observed in comparing slow VT vs VF and fast VT vs VF but not in comparing slow VT vs fast VT. VF was independently associated with the probability of reduction of treated events after PSGB. ConclusionPSGB is an effective treatment of electrical storm in patients with all types of ventricular arrhythmias. However, its effectiveness was more pronounced in patients with VF.

Efficacy of percutaneous stellate ganglion block according to ventricular arrhythmia cycle length: a post-hoc sub-analysis of the STAR study

Abstract Background Percutaneous stellate ganglion block (PSGB) is an effective treatment for patients with electrical storm (ES). However, literature is scarce about a possible relation between ventricular arrhythmias’ cycle length and the effectiveness extent of PSGB. Purpose To assess whether the PSGB efficacy is affected by the arrhythmias’ cycle length prior to the procedure. Methods This is a post-hoc sub-analysis of the STAR study (STellate ganglion block for Arrythmic stoRm), a multicentre observational study aimed to assess PSGB’s effectiveness and safety in ES patients [1]. According to both the type and the median cycle of the latest ventricular arrhythmia before PSGB we considered 3 groups: ventricular fibrillation (VF), fast ventricular tachycardia (VT) and slowVT. The primary outcome is the number of treated arrhythmic episodes (with ATPs and/or DC-shocks) in the hour immediately after the PSGB as compared to the hour immediately before. The secondary outcome was the extent of the reduction of the number of ATPs/DC-shocks delivered from the hour before to the hour immediately after the PSGB. Results The original study included 184 PSGBs performed on 131 patients. We excluded 32 PSGBs with a continuous infusion and 13 PSGBs with an unknown VT cycle. The median VT cycle was 375 msec, so the final dataset of 139 PSGBs from 112 patients was divided as follows: 51 VF; 44 fastVT (VT cycle &amp;lt;375 msec) and 44 slowVT (VT cycle ≥375 msec). The number of treated arrhythmic episodes in the first hour after every PSGB was significantly lower compared to the first hour before in all the three groups [VF: 0 (IQR, 0-1) vs 5 (IQR, 2-8), p&amp;lt;0.001; fastVT: 0 (IQR, 0-0) vs 1 (IQR, 0-6.5), p&amp;lt;0.001; slowVT: 0 (IQR, 0-0) vs 1 (IQR, 0-4.5), p=0.001] (Figure 1). The Hodges-Lehman median difference of treated arrhythmic episodes between the hour after and before the PSGB was significantly higher in VF group [-4 (-3 to -6)] than in the fast-VT [-2 (-1 to -4)] and slow-VT [-1 (0 to -2.5)] (Figure 2). Analysing the reduction (delta less than zero) of the number of ATPs/DC-shocks from the hour before to the hour immediately after the PSGB, a significant trend was observed across the three groups (Jonckheere-Terpstra trend p&amp;lt;0.001) and a significant difference was observed comparing slow-VT vs VF [0 (IQR, -3 to 0) vs -4 (IQR, -7 to -1)] and fast-VT versus VF [-1 (IQR, -4.5 to 0) vs -4 (IQR, -7 to -1)], but not comparing slow-VT versus fast-VT [0 (IQR, -3 to 0) vs -1 (IQR, -4.5 to 0)]. VF was a predictor of the reduction of treated arrhythmic episodes at univariable analysis and after correction for the number of treated arrhythmic episodes in the hour immediately before PSGB and of left ventricular ejection fraction (OR 7.8, 95%CI 2.1-28.6). Conclusion PSGB is an effective treatment for ES in patients with all type of ventricular arrhythmias. However, its effectiveness was more pronounced in patients with VF or rapid ventricular tachycardia.

Predicting atrial fibrillation within 7 years follow-up using machine learning models

Abstract Background The prevalence of atrial fibrillation (AF), the most common type of cardiac arrhythmia, has increased globally. AF is also the leading cardiac factor for several cardiovascular and cerebrovascular events. Early prediction and treatment of AF prevents major cardiovascular and cerebrovascular events. Purpose Our objective is to predict AF risk within 7-years follow-up using only twelve basic factors and applying machine learning (ML) models. Methods Data from the German epidemiological trial on ankle brachial index (getABI) were utilized in this work. GetABI includes 6,457 patients with mean age of 72.53 years. 3,985 individuals were assessed for AF of which 393 patients suffered from AF at 7-years follow-up. The feature selection was initially done manually, ending up in 45 features. The 10 best features were extracted from this dataset according to the SHAP (SHapley Additive exPlanations) values. The final features were body mass index, sensitive CRP, cholesterol, LDL-cholesterol, troponin I, NT-pro-BNP, glomerular filtration rate, ratio of triglycerides and HDL-cholesterol, gamma-GT, heart rate, including age and sex as major factors. The handling of missing values was achieved by SimpleImputer, estimating the mean values. XGBoost and Random Forest predicted AF. Logistic Regression was also used as a baseline model. The data were split into training and test set and ML models were applied for 100 iterative runs, extracting results with mean values. Results XGBoost was the most accurate model, predicting the AF with 71.19 % mean accuracy, 66.37 % mean sensitivity and 75.61 % mean specificity. Figure 1 depicts the performance of all models. Additionally, Receiver Operating Characteristic Curve (ROC) and Area Under Curve (AUC) for each model are presented in Figure 2. XGBoost also outperformed all the others models, achieving the highest mean AUC value, equal to 70.99 %. Contrariwise, logistic regression had the lowest overall performance. Conclusion ML models, specifically XGBoost, achieved accurate AF prediction in 3,985 individuals utilizing only twelve clinical-routine data.Evaluation results of each used model.ROC curve and AUC value of each model.