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.

The diagnostic efficiency of artificial intelligence based 2 hours Holter monitoring in premature ventricular and supraventricular contractions detection.

BACKGROUND: Electrocardiography (ECG) and 24 hours Holter monitoring (24 h-Holter) provided valuable information for premature ventricular and supraventricular contractions (PVC and PSVC). Currently, artificial intelligence (AI) based 2 hours single-lead Holter (2 h-Holter) monitoring may provide an improved strategy for PSVC/PVC diagnosis. HYPOTHESIS: AI combined with single-lead Holter monitoring improves PSVC/PVC detection. METHODS: In total, 170 patients were enrolled between August 2022 and 2023. All patients wore both devices simultaneously; then, we compared diagnostic efficiency, including the sensitivity/specificity/positive predictive-value (PPV) and negative predictive-value (NPV) in detecting PSVC/PVC by 24 h-Holter and 2 h-Holter. RESULTS: The PPV and NPV in patients underwent 2 h-Holter were 76.00%/87.50% and 96.35%/98.55, respectively, and the sensitivity and specificity were 79.17%/91.30%, and 95.65%/97.84% in PSVC/PVC detection compared with 24 h-Holter. The areas under the ROC curves (AUCs) for PSVC and PVC were 0.885 and 0.741, respectively (p < .0001). CONCLUSIONS: The potential advantages of the 2 h-Holter were shortened wearing period, improved convenience, and excellent consistency of diagnosis.

Single catheter approach for treatment of premature ventricular contractions.

BACKGROUND: Catheter ablation has become one of the main treatment strategies in patients with premature ventricular complexes (PVC). The successful mapping and ablation can be performed with an ablation catheter without additional diagnostic catheters. HYPOTHESIS: We hypothesize that using a single catheter for PVC ablation may decrease complications, procedure time, and fluoroscopy exposure while maintaining comparable success rates. METHODS: Sixty-nine consecutive patients with PVC were treated with a single catheter approach compared to a historical cohort, in which a conventional setup was used. Propensity score matching was conducted with a 1:1 ratio. Outcome parameters included acute procedural success with elimination of all premature ventricular contractions after catheter ablation, procedural data as well as complication rates. RESULTS: Patients treated with a single catheter approach had shorter total procedure (60 minutes [IQR: 47,5-69,0 minutes] vs. 90 minutes [IQR 60-120 minutes]; p = 0.001) and fluoroscopy times (218 seconds [IQR: 110,5-446 seconds] vs. 310 seconds [IQR 190-640 seconds]; p = 0.012), which consecutively leads to a reduction of radiation exposure signified by a lower dose area product (155 cGycm² [IQR 74.4-334.5 cGycm²] vs. 368.4 cGycm² [IQR: 126-905.4 cGycm²]; p value 0.009). Acute procedural success rates were comparable in both groups (54 [84.3%] in the single catheter approach group and 58 [90.6%] in the conventional group; p: 0.287). CONCLUSION: A single catheter approach for the treatment of PVC is associated with a reduction of procedure- and fluoroscopy time, as well as a lesser radiation exposure, while maintaining equivalent acute success and complication rates compared with a conventionally used catheter setup.

Three-Day Monitoring of Adhesive Single-Lead Electrocardiogram Patch for Premature Ventricular Complex: Prospective Study for Diagnosis Validation and Evaluation of Burden Fluctuation.

BACKGROUND: Wearable electrocardiogram (ECG) monitoring devices are used worldwide. However, data on the diagnostic yield of an adhesive single-lead ECG patch (SEP) to detect premature ventricular complex (PVC) and the optimal duration of wearing an SEP for PVC burden assessment are limited. OBJECTIVE: We aimed to validate the diagnostic yield of an SEP (mobiCARE MC-100, Seers Technology) for PVC detection and evaluate the PVC burden variation recorded by the SEP over a 3-day monitoring period. METHODS: This is a prospective study of patients with documented PVC on a 12-lead ECG. Patients underwent simultaneous ECG monitoring with the 24-hour Holter monitor and SEP on the first day. On the subsequent second and third days, ECG monitoring was continued using only SEP, and a 3-day extended monitoring was completed. The diagnostic yield of SEP for PVC detection was evaluated by comparison with the results obtained on the first day of Holter monitoring. The PVC burden monitored by SEP for 3 days was used to assess the daily and 6-hour PVC burden variations. The number of patients additionally identified to reach PVC thresholds of 10%, 15%, and 20% during the 3-day extended monitoring by SEP and the clinical factors associated with the higher PVC burden variations were explored. RESULTS: The recruited data of 134 monitored patients (mean age, 54.6 years; males, 45/134, 33.6%) were analyzed. The median daily PVC burden of these patients was 2.4% (IQR 0.2%-10.9%), as measured by the Holter monitor, and 3.3% (IQR 0.3%-11.7%), as measured in the 3-day monitoring by SEP. The daily PVC burden detected on the first day of SEP was in agreement with that of the Holter monitor: the mean difference was -0.07%, with 95% limits of agreement of -1.44% to 1.30%. A higher PVC burden on the first day was correlated with a higher daily (R2=0.34) and 6-hour burden variation (R2=0.48). Three-day monitoring by SEP identified 29% (12/42), 18% (10/56), and 7% (4/60) more patients reaching 10%, 15%, and 20% of daily PVC burden, respectively. Younger age was additionally associated with the identification of clinically significant PVC burden during the extended monitoring period (P=.02). CONCLUSIONS: We found that the mobiCARE MC-100 SEP accurately detects PVC with comparable diagnostic yield to the 24-hour Holter monitor. Performing 3-day PVC monitoring with SEP, especially among younger patients, may offer a pragmatic alternative for identifying more individuals exceeding the clinically significant PVC burden threshold.

Impact on clinical outcome of ventricular arrhythmias in patients undergoing transcatheter aortic valve implantation.

BACKGROUND: Transcatheter aortic valve implantation (TAVI) has become a largely used treatment for severe aortic stenosis. There are limited data, however, about predictors of long-term prognosis in this population. In this study, we assessed whether ventricular arrhythmias may predict clinical outcomes in patients undergoing TAVI. METHODS AND RESULTS: We performed a 24 h ECG Holter monitoring in 267 patients who underwent TAVI for severe aortic stenosis within 30 days from a successful procedure. The occurrence of frequent premature ventricular complexes (PVCs; ≥30/h), polymorphic PVCs and nonsustained ventricular tachycardia (NSVT) was obtained for each patient. Clinical outcome was obtained for 228 patients (85%), for an average follow-up of 3.5 years (range 1.0-8.6). Cardiovascular events (CVEs; cardiovascular death or resuscitated cardiac arrest) occurred in 26 patients (11.4%) and 63 patients died (27.6%). Frequent PVCs but not polymorphic PVCs and NSVT were found to be associated with CVEs at univariate analysis. Frequent PVCs were indeed found in 12 patients with (46.2%) and 35 without (17.3%) CVEs [hazard ratio 2.30; 95% confidence interval (CI) 1.03-5.09; P  = 0.04], whereas polymorphic PVCs were found in 11 (42.3%) and 54 (26.7%) patients of the two groups, respectively (hazard ratio 1.44; 95% CI 0.64-3.25; P  = 0.38), and NSVT in 9 (34.6%) and 43 patients of the two groups, respectively (hazard ratio 1.18; 95% CI 0.48-2.87; P  = 0.72). Frequent PVCs, however, were not significantly associated with CVEs at multivariate Cox regression analysis (hazard ratio 1.53; 95% CI 0.37-6.30; P  = 0.56). Both frequent PVCs, polymorphic PVCs and NSVT showed no significant association with mortality. CONCLUSION: In our study, the detection of frequent PVCs at Holter monitoring after TAVI was a predictor of CVEs (cardiovascular death/cardiac arrest), but this association was lost in multivariable analysis.

Electrocardiographic predictors of left ventricular scar in athletes with right bundle branch block premature ventricular beats.

AIMS: Right bundle branch block (RBBB) morphology non-sustained ventricular arrhythmias (VAs) have been associated with the presence of non-ischaemic left ventricular scar (NLVS) in athletes. The aim of this cross-sectional study was to identify clinical and electrocardiogram (ECG) predictors of the presence of NLVS in athletes with RBBB VAs. METHODS AND RESULTS: Sixty-four athletes [median age 39 (24-53) years, 79% males] with non-sustained RBBB VAs underwent cardiac magnetic resonance (CMR) with late gadolinium enhancement in order to exclude the presence of a concealed structural heart disease. Thirty-six athletes (56%) showed NLVS at CMR and were assigned to the NLVS positive group, whereas 28 athletes (44%) to the NLVS negative group. Family history of cardiomyopathy and seven different ECG variables were statistically more prevalent in the NLVS positive group. At univariate analysis, seven ECG variables (low QRS voltages in limb leads, negative T waves in inferior leads, negative T waves in limb leads I-aVL, negative T waves in precordial leads V4-V6, presence of left posterior fascicular block, presence of pathologic Q waves, and poor R-wave progression in right precordial leads) proved to be statistically associated with the finding of NLVS; these were grouped together in a score. A score ≥2 was proved to be the optimal cut-off point, identifying NLVS athletes in 92% of cases and showing the best accuracy (86% sensitivity and 100% specificity, respectively). However, a cut-off ≥1 correctly identified all patients with NLVS (absence of false negatives). CONCLUSION: In athletes with RBBB morphology non-sustained VAs, specific ECG abnormalities at 12-lead ECG can help in detecting subjects with NLVS at CMR.

In athletes with right bundle branch block (RBBB) morphology non-sustained ventricular arrhythmias (VAs), the presence of a non-ischaemic left ventricular scar (NLVS) may be highly suspected if one or more of the following electrocardiogram (ECG) characteristics are present at the 12-lead resting ECG: low QRS voltages in limb leads, negative T waves in inferior leads, negative T waves in limb leads I­aVL, negative T waves in precordial leads V4­V6, presence of left posterior fascicular block, presence of pathologic Q waves, and poor R-wave progression in right precordial leads. This score should be externally validated in a larger population of athletes with VAs. In athletes with RBBB morphology non-sustained Vas, attention should be placed on the 12-lead resting ECG to suspect the presence of an NLVS. In athletes with RBBB VAs and the presence of one or more of the identified ECG characteristics, a cardiac magnetic resonance with late gadolinium enhancement is useful to rule out an NLVS.

Ablation of epicardial ventricular focus through coronary sinus using pulsed-field ablation. A case report.

INTRODUCTION: With the entry of pulsed-field ablation (PFA) into electrophysiology, new possibilities for ablation of different substrates such as epicardial foci of premature ventricular contractions (PVCs) from coronary venous system (CVS) have been opened. METHODS: This article focuses on a case of a 27-year-old patient with frequent monomorphic PVCs of epicardial origin, treated by radiofrequency ablation, followed by PFA. RESULTS: After unsuccessful focus ablation through CVS with RFA, successful ablations from the same region with PFA were achieved. CONCLUSION: This is the first described case of successful ablation of epicardial PVCs using PFA, which we hope will help in defining indications for this novel technology and enhance quality of treatment for patients with different arrhythmias.

A "two-step classification" machine learning method for non-invasive localization of premature ventricular contraction origins based on 12-lead ECG.

BACKGROUND: Premature ventricular contraction (PVC) is a type of cardiac arrhythmia that originates from ectopic pacemaker in the ventricles. The localization of the origin of PVC is essential for successful catheter ablation. However, most studies on non-invasive PVC localization focus on elaborate localization in specific regions of the ventricle. This study aims to propose a machine learning algorithm based on 12-lead electrocardiogram (ECG) data that can improve the accuracy of PVC localization in the whole ventricle. METHODS: We collected 12-lead ECG data from 249 patients with spontaneous or pacing-induced PVCs. The ventricle was divided into 11 segments. In this paper, we propose a machine learning method consisting of two consecutive classification steps. In the first classification step, each PVC beat was labeled to one of the 11 ventricular segments using six features, including a newly proposed morphological feature called "Peak_index." Four machine learning methods were tested for comparative multi-classification performance and the best classifier result was kept to the next step. In the second classification step, a binary classifier was trained using a smaller combination of features to further differentiate segments that are easily confused. RESULTS: The Peak_index as a proposed new classification feature combined with other features is suitable for whole ventricle classification by machine learning methods. The test accuracy of the first classification reached 75.87%. It is shown that a second classification for confusable categories can improve the classification results. After the second classification, the test accuracy reached 76.84%, and when a sample classified into adjacent segments was considered correct, the test "rank accuracy" was improved to 93.49%. The binary classification corrected 10% of the confused samples. CONCLUSION: This paper proposes a "two-step classification" method to localize the origin of PVC beats into the 11 regions of the ventricle using non-invasive 12-lead ECG. It is expected to be a promising technique to be used in clinical settings to help guide ablation procedures.

Predictors and possible mechanisms of premature ventricular contraction induced cardiomyopathy.

Premature ventricular complexes (PVCs) are encountered frequently in clinical practice. While PVCs may have various causes, a small number of individuals with PVCs develop cardiomyopathy in the absence of other potential etiologies. When correctly identified, patients with PVC-incuded cardiomyopathy can have dramatic improvement of their cardiomyopathy with treatment of their PVCs. In this focused review, we discuss potential predictors of PVC-induced cardiomyopathy, including PVC frequency, PVC characteristics, and modifiable patient risk factors. We also review some proposed mechanisms of PVC-induced cardiomyopathy and conclude with future directions for research and clinical practice.

Are antiarrhythmic agents indicated in premature ventricular complex-induced cardiomyopathy and when?

INTRODUCTION: Premature ventricular complexes (PVCs) are the most common ventricular arrhythmia that are encountered in the clinical practice. Recent data suggests that high PVC burden may lead to the development of PVC-induced cardiomyopathy (PVC-CM) even in patients without structural heart disease. Treatment for effective suppression of PVCs, can reverse PVC-CM. Both antiarrhythmic drugs (AADs) and catheter ablation (CA) are recognized treatment modalities for any cardiac arrhythmias. However, with increasing preference of CA, the role of AADs needs further defining regarding their efficacy, safety, indications and patient selection to treat PVC-CM. METHODS: To ascertain the role of AADs to treat PVC-CM; whether they are indicated to treat PVC-CM, and if so, when, we interrogated PubMed and other search engines for English language publications with key words premature ventricular complexes (PVCs), cardiomyopathy, anti-arrhythmic drugs, catheter ablation, and pharmacological agents. All publications were carefully reviewed and scrutinized by the authors for their inclusion in the review paper. For illustration of cases, ethical standard was observed as per the 1975 Declaration of Helsinki, and the patient was treated as per the prevailing standard of care. Informed consent was obtained from the patient for conducting the ablation procedure. RESULTS: Our literature search specifically the pharmacological treatment of PVC-CM with AADs revealed significant paradigm shift in treatment approach for PVCs and PVC-induced cardiomyopathy. No major large, randomized control trials of AADs versus CA for PVC-CM were found. We found that beta-blockers and calcium channel blockers are particularly effective in the treatment of PVCs originating from right ventricular outflow tract. For Class Ic AADs - flecainide and propafenone, small clinical studies showed Class Ic AADs to be effective in PVC suppression, but their usage was not recommended in patients with significant coronary artery disease. Mexiletine was found to have modest effect on PVC suppression. Studies showed sotalol to significantly reduce PVCs frequency in patients receiving both low and high doses. Studies also showed amiodarone to have higher successful PVC suppression, but not recommended as a first-line treatment for patients with idiopathic PVCs in the absence of symptoms and left ventricular dysfunction. For dronedarone, no major clinical data were available. CONCLUSIONS: Based on the available data in the literature, we conclude that AADs play important role in the treatment of PVC-induced cardiomyopathy. However, appropriate patient selection criteria are vitally important, and in general terms AADs are indicated or polymorphic PVCs, epicardial PVCs; and when CA procedure is contraindicated, or not feasible or failed.

The comparison between the novel technique and conventional method in the catheter ablation of premature ventricular contractions originating from the free wall of tricuspid annulus.

BACKGROUND: This study aimed to assess the safety and effectiveness of a novel technique for catheter ablation in patients with premature ventricular contraction (PVC) from the free wall of tricuspid annulus (TV). HYPOTHESIS: We hypothesized that the novel technique is more efficacious than the traditional approach. METHODS: We retrospectively investigated 59 consecutive patients with PVC originating from the free wall of TV between January 2013 and November 2021. The patients were divided into two groups: the reversed S-curve technique group (RST, n = 26) and the reversed C-curve technique group (RCT, n = 33). The RST under the support of a steerable sheath was used in RST group, while the RCT under the support of a nonsteerable sheath was used in the RCT group. Systematic mapping and radiofrequency ablation were preferentially performed under the valve in all patients. RESULTS: Compared to the RCT group, total procedural time and fluoroscopic exposure time were significantly shorter in RST group. Two patients experienced cardiac tamponade in the RCT group, while no complications were observed in RST group (p = .498). The success rate was significantly higher in RST group compared to RCT group (81.9% vs. 100%, p = .029). Three patients in RCT group failed to ablate during the operation but were successfully ablated using the novel method. During regular follow-up, no patients in the RST group had a recurrence, while three patients in the RCT group did (p = .274). CONCLUSIONS: It suggests that the reserved S-curve technique, supported by a steerable sheath, is a feasible and effective method for ablating PVC originating from the free wall of TV.

Pleomorphism of premature ventricular complexes originating from papillary muscles and their myocardial connections.

BACKGROUND: Patients with arrhythmias originating from papillary muscles (PAPs) often have pleomorphic ventricular arrhythmias (PVAs) that can result in failed ablations. The mechanism of PVAs is unknown. OBJECTIVE: The purpose of this study was to assess the prevalence and mechanisms of PVAs and the impact on outcomes in patients with focal left ventricular PAP ventricular arrhythmias (VAs). METHODS: The sites of origin (SOOs) of VAs in 43 consecutive patients referred for ablation of focal left ventricular PAP VAs were determined by activation and pacemapping. SOOs were classified as (1) unifocal generating a single VA morphology; (2) unifocal from a deeper-seated origin generating multiple VA morphologies; (3) unifocal located on a PAP branching site; (4) multifocal from a single or multiple PAPs generating multiple VA morphologies; and (5) multifocal from a PAP and a different anatomic source. RESULTS: Most patients had multiple morphologies (n = 34 [79%]) and multiple mechanisms (79%) generating the different VA morphologies. Most of the patients with PVAs had multiple SOOs from a single or different PAPs (n = 23 [68%]), followed by patients with SOOs from PAP and non-PAP sites (n = 19 [56%]). In 13 patients (38%), single SOOs accounted for the observed PVAs. The frequent observation (n = 20) of changing QRS morphologies after radiofrequency energy delivery targeting a single VA suggests the presence of a deeper focus with changing sites of preferential conduction. CONCLUSION: VA pleomorphism in patients with PAP arrhythmias is most often due to premature ventricular complexes originating from different SOOs. The second most common cause is preferential conduction from a single SOO via PAP branching sites.

Association between excess catecholamine synthesis and polymorphic premature ventricular contraction.

BACKGROUND: The reasons for the etiology of premature ventricular contractions (PVCs) are not specifically known. Many patients are resistant to medical treatment, and a factor that would predict response to medical treatment cannot be identified. This study aims to investigate if a high catecholamine level results in polymorphic PVC. METHODS: This study was obtained by prospective data registry analysis. A total of 100 patients, 50 from the PVC group, and 50 from the control group have been evaluated. The participants who were included in the patient group had a polymorphic PVC of 5% or more in their 24-h Holter evaluations. Metanephrine showing the level of adrenaline and normetanephrine, showing the level of noradrenaline levels have been measured from these urine samples. RESULT: There was no difference between the two groups in terms of biochemical and essential characteristics. Normetanephrine level has been significantly higher in the PVC group compared to the control group (323.9 ± 208.9 µg to 129.25 ± 67.88 µg; p < 0.001). Similarly, metanephrine level has also been higher in the PVC group (124.75 ± 82.43 µg to 52.615 ± 36,54 µg; p < 0.001). A positive and moderate correlation has been identified between the number and ratio of PVC and the metanephrine and normetanephrine levels. CONCLUSION: In this study, we found that the catecholamine levels were higher in the polymorphic PVC group than in the healthy volunteers. Also, an increase in the number and rate of PVC has been observed as the catecholamine levels increased. CLINICAL TRIAL REGISTRATION: Urine Levels of Metanephrine and Normetanephrine in Patients With Frequent PVC; ClinicalTrials.gov number NCT03447002.

The significance of heart rate variability in patients with frequent premature ventricular complex originating from the ventricular outflow tract.

BACKGROUND: As an indicator of cardiac autonomic nervous activity, heart rate variability (HRV) is closely linked to premature ventricular complexes (PVCs). However, its role in patients with frequent PVCs originating from the ventricular outflow tract remains unclear. HYPOTHESIS: Here, we hypothesize that there may be alterations in HRV among patients with frequent PVCs originating from the ventricular outflow tract, which could play significant roles in the management of such patients. METHODS: A retrospective study was conducted, including 106 patients with frequent outflow tract PVCs and 106 healthy participants as controls. HRV was assessed based on the 24-hour Holter recording. The originating foci of PVCs were identified during radiofrequency catheter ablation. RESULTS: Patients with frequent outflow tract PVCs exhibited decreased levels of high frequency (HF), standard deviation of all NN intervals, and standard deviation of the average NN intervals, but increased ratios of low frequency to HF (LF/HF ratio), even after propensity score-matched analysis. Further investigation revealed that patients with PVCs originating from right ventricular outflow tract (RVOT) had much higher LF/HF ratios. Multivariate logistic regression analysis demonstrated that the LF/HF ratio was independently associated with PVCs originating from RVOT. Receiver operating characteristics curve indicated that the LF/HF ratio effectively determined the origin of PVCs (the area under the curve = 0.75, p < .001). CONCLUSIONS: Patients with frequent outflow tract PVCs exhibited impaired HRV. Additionally, the LF/HF ratio played a significant role in determining the origin of outflow tract PVCs.

Differentiating Origins of Outflow Tract Ventricular Arrhythmias: The Correction of Transitional Zone Index Is Not Superior to the Original One.

INTRODUCTION: Our team once proposed a correction of transitional zone index (CTZI) based on the transitional zone index (TZI) in view of achieving a more precise prediction of outflow tract ventricular arrhythmia (OTVA). The predictive accuracy of these two electrocardiogram (ECG) algorithms has not been validated and compared. The purpose of this study was to compare the predictive accuracy of TZI and CTZI in a much larger population with idiopathic OTVA. METHODS: The predictive accuracy of TZI and CTZI was compared in 695 individuals with idiopathic premature ventricular complex or ventricular tachycardia which exhibited a left bundle branch block pattern and inferior axis QRS morphology. Receiver operating characteristic curve analysis, decision curve analysis, and calibration curve were used to compare the predictive accuracy of TZI and CTZI. RESULTS: TZI and CTZI manifested the similar area under the curve. While a TZI of <0 predicted a left ventricular outflow tract (LVOT) origin with a high specificity of 88.2% but a low sensitivity of 67.1%, a CTZI of <0 yielded a high sensitivity of 84.3% but a low specificity of 59.5% in the overall analysis. Similar results were yielded in the sub-analysis of participants with a precordial transition occurring at lead V3. In the sub-analysis of participants with a TZI = 0, CTZI demonstrated a bit higher but not satisfactory predictive accuracy than TZI. CONCLUSION: Based on the scientific spirit of self-criticism and seeking truth from facts, our team disproves the correction of TZI proposed previously.