An improved method to detect arrhythmia using ensemble learning-based model in multi lead electrocardiogram (ECG).

Arrhythmia is a life-threatening cardiac condition characterized by irregular heart rhythm. Early and accurate detection is crucial for effective treatment. However, single-lead electrocardiogram (ECG) methods have limited sensitivity and specificity. This study propose an improved ensemble learning approach for arrhythmia detection using multi-lead ECG data. Proposed method, based on a boosting algorithm, namely Fine Tuned Boosting (FTBO) model detects multiple arrhythmia classes. For the feature extraction, introduce a new technique that utilizes a sliding window with a window size of 5 R-peaks. This study compared it with other models, including bagging and stacking, and assessed the impact of parameter tuning. Rigorous experiments on the MIT-BIH arrhythmia database focused on Premature Ventricular Contraction (PVC), Atrial Premature Contraction (PAC), and Atrial Fibrillation (AF) have been performed. The results showed that the proposed method achieved high sensitivity, specificity, and accuracy for all three classes of arrhythmia. It accurately detected Atrial Fibrillation (AF) with 100% sensitivity and specificity. For Premature Ventricular Contraction (PVC) detection, it achieved 99% sensitivity and specificity in both leads. Similarly, for Atrial Premature Contraction (PAC) detection, proposed method achieved almost 96% sensitivity and specificity in both leads. The proposed method shows great potential for early arrhythmia detection using multi-lead ECG data.

Pause-Dependent Paroxysmal Episode of Third-Degree Atrioventricular Block Triggered by Premature Atrial Contraction.

BACKGROUND Paroxysmal third-degree atrioventricular block (AVB) can exhibit a vast array of symptoms, but commonly, paroxysmal AVB leads to presyncope, syncope, or possibly sudden cardiac death. We present a rare case of pause-dependent paroxysmal AVB that was triggered by a premature atrial contraction. CASE REPORT A 65-year-old man with frequent episodes of presyncope and syncope for 3 weeks was admitted to our hospital for further diagnosis. A resting 12-lead electrocardiogram showed an incomplete right bundle branch block, and a 24-h Holter recording showed multiple episodes of third-degree AVB. Intracardiac tracing revealed that the block site was distal, at the infra-His-Purkinje system. CONCLUSIONS This case highlights a rare case of pause-dependent paroxysmal AVB that was triggered by a premature atrial contraction. This type of AVB is an abrupt, unexpected, repetitive block of atrial impulses as they propagate to the ventricles. It is relatively rare, and due to its transient nature, it is often under recognized and can lead to sudden cardiac death.

Higher Frequency of Premature Atrial Contractions Correlates With Atrial Fibrillation Detection after Cryptogenic Stroke.

BACKGROUND: Covert atrial fibrillation (AF) is a major cause of cryptogenic stroke. This study investigated whether a dose-dependent relationship exists between the frequency of premature atrial contractions (PACs) and AF detection in patients with cryptogenic stroke using an insertable cardiac monitor (ICM). METHODS: We enrolled consecutive patients with cryptogenic stroke who underwent ICM implantation between October 2016 and September 2020 at 8 stroke centers in Japan. Patients were divided into 3 groups according to the PAC count on 24-hour Holter ECG: ≤200 (group L), >200 to ≤500 (group M), and >500 (group H). We defined a high AF burden as above the median of the cumulative duration of AF episodes during the entire monitoring period. We evaluated the association of the frequency of PACs with AF detection using log-rank trend test and Cox proportional hazard model and with high AF burden using logistic regression model, adjusting for age, sex, CHADS2 score. RESULTS: Of 417 patients, we analyzed 381 patients with Holter ECG and ICM data. The median age was 70 (interquartile range, 59.5-76.5), 246 patients (65%) were males, and the median duration of ICM recording was 605 days (interquartile range, 397-827 days). The rate of new AF detected by ICM was higher in groups with more frequent PAC (15.5%/y in group L [n=277] versus 44.0%/y in group M [n=42] versus 71.4%/y in group H [n=62]; log-rank trend P<0.01). Compared with group L, the adjusted hazard ratios for AF detection in groups M and H were 2.11 (95% CI, 1.24-3.58) and 3.23 (95% CI, 2.07-5.04), respectively, and the adjusted odds ratio for high AF burden in groups M and H were 2.57 (95% CI, 1.14-5.74) and 4.25 (2.14-8.47), respectively. CONCLUSIONS: The frequency of PACs was dose-dependently associated with AF detection in patients with cryptogenic stroke.

Predicting risk of AF in ischaemic stroke using sinus rhythm ECG abnormalities: A meta-analysis.

OBJECTIVE: To identify ECG changes in sinus rhythm that may be used to predict subsequent development of new AF. METHOD: We identified prospective and retrospective cohort or case control studies evaluating ECG patterns from a 12-lead ECG in sinus rhythm taken in hospital or community predicting subsequent development of new AF. For each identified ECG predictor, we then identify absolute event rates and pooled risk ratios (RR) using an aggregate level random effects meta-analysis. RESULTS: We identified 609,496 patients from 22 studies. ECG patterns included P wave terminal force V1 (PTFV1), interatrial block (IAB) and advanced interatrial block (aIAB), abnormal P wave axis (aPWA), PR prolongation and atrial premature complexes (APCs). Pooled risk ratios reached significance for each of these; PTFV1 RR 1.48 (95% CI 1.04-2.10), IAB 2.54 (95% CI 1.64-3.93), aIAB 4.05 (95% CI 2.64-6.22), aPWA 1.89 (95% CI 1.25-2.85), PR prolongation 2.22 (95% CI 1.27-3.87) and APCs 3.71 (95% CI 2.23-6.16). Diabetes reduced the predictive value of PR prolongation. CONCLUSION: APC and aIAB were most predictive of AF, while IAB, PR prolongation, PTFV1 and aPWA were also significantly associated with development of AF. These support their use in a screening tool to identify at risk cohorts who may benefit from further investigation, or following stroke, with empirical anticoagulation.

Utility of short-time electrocardiogram to assess risk for atrial arrhythmia recurrence: Impact of atrial premature beat occurrence 1 day after pulmonary vein isolation for atrial fibrillation.

INTRODUCTION: Atrial premature beats (APBs) are the trigger for atrial fibrillation (AF). We sought to investigate the clinical significance of APB occurrence 1 day after pulmonary vein isolation (PVI) for AF using a short-time electrocardiogram. METHODS: A total of 206 patients undergoing PVI for paroxysmal AF were included. Electrocardiogram recording for 100 consecutive beats was performed 1 day after PVI. The patients were divided into two groups: those with reproducible APBs (≥1 beat) during reassessment (APB group, n = 49) or those without (non-APB group, n = 157). Late recurrence was defined as atrial tachyarrhythmia recurrence 3-12 months after PVI. The impact of APB occurrence on outcomes was investigated. RESULTS: Late recurrence occurred in 19 patients (9.2%). The presence of low-voltage areas, left atrial volume, and recurrence rate were higher in the APB group than in the non-APB group. In the APB group, the patients with recurrence had lower prematurity index (PI, coupling interval of APB/previous cycle length) compared to those without. Receiver-operating characteristic analysis revealed PI (<59.3) to be a predictive factor of recurrence (area under the curve: 0.733). The study subjects were then reclassified into three groups according to the absence of APB occurrence (n = 157), presence thereof with PI ≥ 59.3 (n = 33), and presence with PI < 59.3 (n = 16). The multivariate Cox models revealed that APB with PI < 59.3 was an independent predictor for recurrence (hazard ratio, 8.735; p < 0.001). CONCLUSION: A short-time electrocardiogram enables risk assessment for arrhythmia recurrence, and APB with low PI 1 day after PVI is a powerful predictor.

High-Burden Premature Atrial Contractions Predict New-Onset Atrial Fibrillation After Surgical Septal Myectomy.

Although increased premature atrial contractions (PACs) reportedly predict atrial fibrillation (AF) in both general and specific (e.g., patients with stroke) populations, early postoperative AF (POAF) risk in patients with increased PAC burden who require cardiac surgery remains unclear. We examined the correlation between different preoperative PAC burdens and POAF in patients with obstructive hypertrophic cardiomyopathy (OHCM) who underwent surgical treatment. We analyzed 304 consecutively admitted patients with OHCM without previous AF who underwent isolated septal myectomy between January 2015 and December 2018. All patients underwent preoperative 24-hour Holter electrocardiogram monitoring. PACs were present in 259 patients (85.20%) and absent in 45 patients (14.80%). According to the cut-off PAC number of 100 beats/24 hours, there were 211 patients (69.41%) with low-burden PACs and 48 patients (15.79%) with high-burden PACs. AF after septal myectomy occurred in 73 patients, which consisted of 3/45 in the non-PAC group (6.67%), 47/211 in the low-PAC-burden group (22.27%), and 23/48 in the high PAC burden group (47.92%). POAF incidence was higher in both low- and high-burden patients than in patients without PAC (p <0.01). Multivariate logistic regression analyses demonstrated that high-burden PACs (p = 0.02) and age (p <0.01) but not low-burden PACs (p = 0.22) independently predicted POAF in patients with OHCM. The area under the receiver operating characteristic curve for preoperative PACs was 0.72 (95% confidence interval 0.66 to 0.79, p <0.01, sensitivity: 68.49%, specificity: 69.26%). In conclusion, POAF incidence was significantly higher in patients with preoperative high-burden PACs and can predict POAF in patients with OHCM.

Premature atrial contractions promote local directional heterogeneities in conduction velocity vectors.

AIMS: Loss of cell-to-cell communication results in local conduction disorders and directional heterogeneity (LDH) in conduction velocity (CV) vectors, which may be unmasked by premature atrial contractions (PACs). We quantified LDH and examined differences between sinus rhythm (SR) and spontaneous PACs in patients with and without atrial fibrillation (AF). METHODS AND RESULTS: Intra-operative epicardial mapping of the right and left atrium (RA, LA), Bachmann's bundle (BB) and pulmonary vein area (PVA) was performed in 228 patients (54 with AF). Conduction velocity vectors were computed at each electrode using discrete velocity vectors. Directions and magnitudes of individual vectors were compared with surrounding vectors to identify LDH. Five hundred and three PACs [2 (1-3) per patient; prematurity index of 45 ± 12%] were included. During SR, most LDH were found at BB and LA [11.9 (8.3-14.9) % and 11.3 (8.0-15.2) %] and CV was lowest at BB [83.5 (72.4-94.3) cm/s, all P < 0.05]. Compared with SR, the largest increase in LDH during PAC was found at BB and PVA [+13.0 (7.7, 18.3) % and +12.5 (10.8, 14.2) %, P < 0.001]; CV decreased particularly at BB, PVA and LA [-10.0 (-13.2, -6.9) cm/s, -9.3 (-12.5, -6.2) cm/s and -9.1 (-11.7, -6.6) cm/s, P < 0.001]. Comparing patients with and without AF, more LDH were found during SR in AF patients at PVA and BB, although the increase in LDH during PACs was similar for all sites. CONCLUSION: Local directional heterogeneity is a novel methodology to quantify local heterogeneity in CV as a possible indicator of electropathology. Intra-operative high-resolution mapping indeed revealed that LDH increased during PACs particularly at BB and PVA. Also, patients with AF already have more LDH during SR, which becomes more pronounced during PACs.

Novel dual-reference approach facilitates the activation mapping and catheter ablation of premature atrial complexes with non-pulmonary vein and non-superior vena cava origins.

AIMS: Activation mapping of premature atrial complexes (PACs) proves challenging due to interference by mechanical bumping and non-targeted ectopies. This study aims to compare the mapping efficacy, instant success, and long-term recurrence of catheter ablation for PACs with non-pulmonary vein (PV) and non-superior vena cava (SVC) origins between the novel dual-reference approach (DRA) and the routine single-reference approach (SRA) of mapping. METHODS AND RESULTS: Patients with symptomatic, drug-refractory PACs, or frequent residual PACs after atrial tachyarrhythmia ablation were enrolled. During activation mapping, the coronary sinus (CS) catheter was used as the only timing reference in the SRA group. In the DRA group, another catheter, which was spatially separated from the CS catheter, was used as the second reference. The timing difference between the two references was used to discriminate the targeted PACs from the uninterested rhythms. Procedural parameters and long-term recurrence were compared. A total of 188 patients (109 in SRA and 79 in DRA) were enrolled. The baseline characteristics were similar. Compared with the SRA group, the DRA group had less repeated mapping (1.2 ± 0.4 vs. 1.4 ± 0.5, P = 0.004), shorter mapping (15 ± 6 vs. 23 ± 7 min, P < 0.001) and procedural time (119 ± 28 vs. 132 ± 22 min, P = 0.001), similar procedural complication rates (3.6 vs. 3.8%, P > 0.999), higher instant success (96.2 vs. 87.2%, P = 0.039), and lower recurrence rate (15.2 vs. 29.3%, hazard ratio 1.943, P = 0.033) during a 24-month follow-up. CONCLUSION: As a novel strategy, the DRA shortens the procedural time and improves both instant and long-term success of PAC ablation, serving as a promising approach in mapping PACs with non-PV and non-SVC origins.

Frequent premature atrial contractions as a signalling marker of atrial cardiomyopathy, incident atrial fibrillation, and stroke.

Premature atrial contractions are a common cardiac phenomenon. Although previously considered a benign electrocardiographic finding, they have now been associated with a higher risk of incident atrial fibrillation (AF) and other adverse outcomes such as stroke and all-cause mortality. Since premature atrial contractions can be associated with these adverse clinical outcomes independently of AF occurrence, different explanations have being proposed. The concept of atrial cardiomyopathy, where AF would be an epiphenomenon outside the causal pathway between premature atrial contractions and stroke has received traction recently. This concept suggests that structural, functional, and biochemical changes in the atria lead to arrhythmia occurrence and thromboembolic events. Some consensus about diagnosis and treatment of this condition have been published, but this is based on scarce evidence, highlighting the need for a clear definition of excessive premature atrial contractions and for prospective studies regarding antiarrhythmic therapies, anticoagulation or molecular targets in this group of patients.

Excessive supraventricular ectopic activity and future onset of atrial fibrillation in patients with cryptogenic stroke.

OBJECTIVES: Although evidence has shown the association of excessive supraventricular ectopic activity (ESVEA) with future development of atrial fibrillation (AF), this relationship is not yet fully understood. This study examines whether ESVEA can predict the future onset of AF, in patients presenting with cryptogenic stroke. MATERIALS AND METHODS: A retrospective cohort of 124 non-AF, consecutive patients, hospitalized for cryptogenic stroke between 2014 and 2015, was retrieved. 24-h inpatient monitoring with Holter was employed to reveal ESVEA, defined as the presence of more than 20 premature atrial complexes per hour (PACs/h) on average, or a more than 5 s duration of the longest supraventricular run (LSVR). After a median follow-up period of 5.2 years, the patients were examined for AF. RESULTS: From initial 124 patients, 12 died and one was lost during follow-up. For the total of 111 patients finally included, the median age was 56 years and 25.2% were females. The overall baseline median CHA2DS2-VASc score was 3. AF was found in 13 (11.71%) patients. Patients who were finally diagnosed with AF had a significantly higher number of PACs/h and a longer median LSVR duration at baseline (16.67 vs. 0.21, p < 0.001 and 3 vs. 0 s, p < 0.001, respectively). The presence of ESVEA was also significantly more frequent among AF patients (46.15%, 95%CI: 17.78%-74.22%) compared to non-AF ones (6.1%, 95%CI: 1.3%-10.7%, p < 0.001). CONCLUSIONS: Excessive atrial ectopy, detected with 24 h inpatient Holter monitoring, is a significant indicator of future development of AF in patients presenting originally with a cryptogenic stroke.

Acute Impact of Fine Particulate Air Pollution on Cardiac Arrhythmias in a Population-Based Sample of Adolescents: The Penn State Child Cohort.

Background Fine particulate (fine particles with aerodynamic diameters ≤2.5 µm [PM2.5]) exposure has been associated with a risk of cardiac arrhythmias in adults. However, the association between PM2.5 exposure and cardiac arrhythmias in adolescents remains unclear. Methods and Results To investigate the association and time course between PM2.5 exposure with cardiac arrhythmias in adolescents, we analyzed the data collected from 322 adolescents who participated in the PSCC (Penn State Child Cohort) follow-up examination. We obtained individual-level 24-hour PM2.5 concentrations with a nephelometer. Concurrent with the PM2.5 measure, we obtained 24-hour ECG data using a Holter monitor, from which cardiac arrhythmias, including premature atrial contractions and premature ventricular contractions (PVCs), were identified. PM2.5 concentration and numbers of premature atrial contractions/PVCs were summarized into 30-minute-based segments. Polynomial distributed lag models within a framework of a negative binomial model were used to assess the effect of PM2.5 concentration on numbers of premature atrial contractions and PVCs. PM2.5 exposure was associated with an acute increase in number of PVCs. Specifically, a 10 µg/m3 increase in PM2.5 concentration was associated with a 2% (95% CI, 0.4%-3.3%) increase in PVC counts 0.5 to 1.0, 1.0 to 1.5, and 1.5 to 2.0 hours after the exposure. Cumulatively, a 10 µg/m3 increment in PM2.5 was associated with a 5% (95% CI, 1%-10%) increase in PVC counts within 2 hours after exposure. PM2.5 concentration was not associated with premature atrial contraction. Conclusions PM2.5 exposure was associated with an acute increased number of ventricular arrhythmias in a population-based sample of adolescents. The time course of the effect of PM2.5 on ventricular arrhythmia is within 2 hours after exposure.

Role of the autonomic nervous system and premature atrial contractions in short-term paroxysmal atrial fibrillation forecasting: Insights from machine learning models.

BACKGROUND: Machine learning and deep learning techniques are now used extensively for atrial fibrillation (AF) screening, but their use for AF crisis forecasting has yet to be assessed in a clinical context. AIMS: To assess the value of two machine learning algorithms for the short-term prediction of paroxysmal AF episodes. METHODS: We conducted a retrospective study from an outpatient clinic. We developed a deep neural network model that was trained for a supervised binary classification, differentiating between RR interval variations that precede AF onset and RR interval variations far from any AF. We also developed a random forest model to obtain forecast results using heart rate variability variables, with and without premature atrial complexes. RESULTS: In total, 10,484 Holter electrocardiogram recordings were screened, and 250 analysable AF onsets were labelled. The deep neural network model was able to distinguish if a given RR interval window would lead to AF onset in the next 30 beats with a sensitivity of 80.1% (95% confidence interval 78.7-81.6) at the price of a low specificity of 52.8% (95% confidence interval 51.0-54.6). The random forest model indicated that the main factor that precedes the start of a paroxysmal AF episode is autonomic nervous system activity, and that premature complexes add limited additional information. In addition, the onset of AF episodes is preceded by cyclical fluctuations in the low frequency/high frequency ratio of heart rate variability. Each peak is itself followed by an increase in atrial extrasystoles. CONCLUSIONS: The use of two machine learning algorithms for the short-term prediction of AF episodes allowed us to confirm that the main cause of AF crises lies in an imbalance in the autonomic nervous system, and not premature atrial contractions, which are, however, required as a final firing trigger.

Transition of the heart rate and atrial premature complex after cryoballoon vs. radiofrequency ablation for paroxysmal atrial fibrillation.

The temporal changes in ambulatory monitoring findings after cryoballoon (CB) ablation of atrial fibrillation (AF) have not been well elucidated. This study aims to compare the details of ambulatory monitoring after CB and radiofrequency catheter (RFC) ablation for AF. Of 724 consecutive AF patients who underwent initial ablation using a CB or RFC, 508 (254 pairs) were selected using propensity score matching. Ambulatory monitoring was performed at 1, 3, 6, 12, 24 and 36 months after the procedure. After 1, 3 and 6 months, the number of total heart beats (THBs) was larger in the CB group than in the RFC group. It gradually decreased and became significantly similar by 12 months after ablation. THBs significantly increased 1, 3, 6 and 12 months after ablation in both the RFC and CB groups and became statistically similar by 24 months after ablation. The atrial premature contraction burden was higher in the RFC group than in the CB group at 3 months after ablation. THB and APC burden after AF ablation were significantly different between the RF and CB groups. THBs returned to statistically similarity by 2 years after ablation in both groups.

Association of atrial arrhythmias with thrombospondin-1 in patients with acute myocardial infarction.

OBJECTIVES: Atrial remodeling is the main developmental cause of atrial arrhythmias (AA), which may induce atrial fibrillation, atrial flutter, atrial tachycardia, and frequent premature atrial beats in acute myocardial infarction (AMI) patients. Thrombospondin-1 (TSP-1) has been shown to play an important role in inflammatory and fibrotic processes, but its role in atrial arrhythmias is not well described. The purpose of this study was to investigate the role of TSP-1 in AMI patients with atrial arrhythmias. METHODS: A total of 219 patients with AMI who underwent percutaneous coronary intervention and with no previous arrhythmias were included. TSP-1 were analyzed in plasma samples. Patients were classified into 2 groups, namely, with and without AA during the acute phase of MI. Continuous electrocardiographic monitoring was used for AA diagnosis in hospital. RESULTS: Twenty-four patients developed AA. Patients with AA had higher TSP-1 levels (29.01 ± 25.87 µg/mL vs 18.36 ± 10.89 µg/mL, p < 0.001) than those without AA. AA patients also tended to be elderly (65.25 ± 9.98 years vs 57.47 ± 10.78 years, p < 0.001), had higher Hs-CRP (39.74 ± 43.50 mg/L vs 12.22 ± 19.25 mg/L, p < 0.001) and worse heart function. TSP-1 (OR 1.033; 95% CI 1.003-1.065, p = 0.034), Hs-CRP (OR 1.023; 95% CI 1.006-1.041, p = 0.008), age (OR 1.067; 95% CI 1.004-1.135, p = 0.038) and LVDd (OR 1.142; 95% CI 1.018-1.282, p = 0.024) emerged as independent risk factors for AA in AMI patients. CONCLUSION: TSP-1 is a potential novel indicator of atrial arrhythmias during AMI.

Differences in Left Atrial Size and Function and Supraventricular Ectopy Between Black and White Participants in the ARIC Study.

Background Black Americans have more atrial fibrillation risk factors but lower atrial fibrillation risk than White Americans. Left atrial (LA) enlargement and/or dysfunction, frequent atrial tachycardia (AT), and premature atrial contractions (PAC) are associated with increased atrial fibrillation risk. Racial differences in these factors may exist that could explain the difference in atrial fibrillation risk. Methods and Results We included 2133 ARIC (Atherosclerosis Risk in Communities) study participants (aged 74±4.5 years[mean±SD], 59% women, 27% Black participants) who had echocardiograms in 2011 to 2013 and wore the Zio XT Patch (a 2-week continuous heart monitor) in 2016 to 2017. Linear regression was used to analyze (1) differences in AT/day or PAC/hour between Black and White participants, (2) differences in LA measures between Black and White participants, and (3) racial differences in the association of LA measures with AT or PAC frequency. Compared with White participants, Black participants had a higher prevalence of cardiovascular risk factors and disease, lower AT frequency, greater LA size, and lower LA function. After multivariable adjustments, Black participants had 37% (95% CI, 24%-47%) fewer AT runs/day than White participants. No difference in PAC between races was noted. Greater LA size and reduced LA function are associated with more AT and PAC runs; however, no race interaction was present. Conclusions Differences in LA measures are unlikely to explain the difference in atrial fibrillation risk between Black and White individuals. Despite more cardiovascular risk factors and greater atrial remodeling, Black participants have lower AT frequency than White participants. Future research is needed to elucidate the protective mechanisms that confer resilience to atrial arrhythmias in Black individuals.