QRS Complex Research Articles

Severe Hyperkalemia in a Child with Vomiting and Diarrhea

Case Presentation: A 13-month-old child with past medical history of congenital adrenal insufficiency presented to the emergency department with vomiting and diarrhea. Initially the child was noticed to have bradycardia with normal blood pressure. An electrocardiogram (ECG) showed tall T waves, broad QRS complex, and widened PR interval suggestive of severe hyperkalemia. The initial blood gas showed potassium of 10.7 millimoles per liter. The patient was started on calcium gluconate with immediate resolution of ECG changes. Further management with insulin, dextrose, and sodium olystyrene sulfonate led to normal potassium levels. Discussion: Hyperkalemia is a life-threatening condition in children, especially in those with congenital adrenal insufficiency. The ECG showed different changes as the levels of serum potassium levels increased ranging from tall T waves, wide QRS complex, increased PR interval to arrythmias. Immediate treatment with calcium gluconate in such cases has significant cardioprotective effect. It is important to recognize the ECG changes manifested by changes in serum potassium levels. Our patient had classic ECG changes manifested in severe hyperkalemia.

An explainable deep learning model to predict partial anomalous pulmonary venous connection for patients with atrial septal defect

BackgroundPatients with partial anomalous pulmonary venous connection (PAPVC) usually present asymptomatic and accompanied by intricate anatomical types, which results in missed diagnosis from atrial septal defect (ASD). The present study aimed to explore the predictive variables of PAPVC from patients with ASD and constructed an explainable prediction model based on deep learning.MethodsThe retrospective study included 834 inpatients with ASD in Women and Children's Hospital, Qingdao University from January 2018 to January 2023. They were separated into two groups based on the presence of PAPVC. Propensity score matching and SMOTE were used to balance the baseline data between groups. The differential variables between the two groups were determined by univariate logistic regression. The patients were randomly divided into the training set and the validation set in a ratio of 8:2. Support vector machines (SVM), Random forest, Decision tree, XGBoost, and LightGBM were used to build models by differential variables. The classification performance of models was compared. Split, gain and SHAP were used to measure the importance of differential variables and improve the interpretability of the model. Moreover, a portion of the patients was included in the validation set to test the performance of the selected models.ResultsThree hundred twenty-eight patients with ASD and patients with 82 PAPVC were included in the training set and the validation set, respectively. The selection of 10 differential variables was based on univariate logistic regression, including right atrial diameter (longitudinal axis and transverse axis), right ventricular diameter, left atrial diameter, left ventricular end-diastolic diameter, left ventricular end-systolic diameter, P-wave voltage, P-wave interval PR interval, and QRS-wave voltage. In the classification model established based on differential variables, the LightGBM model achieved the highest performance on the validation set (AUC = 0.93). Based on variables importance analysis, the LightGBM-Clinic model was retrained by P-wave voltage, P-wave interval, PR interval, QRS wave interval, and right ventricular diameter, and performed excellently (AUC = 0.90). The AUC of the LightGBM-Clinic model was 0.87 in the test set.ConclusionIn this study, the LightGBM model performs excellently in determining whether patients with ASD are accompanied by PAPVC. ECG parameters such as P-wave voltage were important to predictive value and enhance the explainability of the model.

Atrial fibrillation – a comparative review of one of the most common arrhythmias in dogs and humans

Atrial fibrillation is the most prevalent arrythmia in dogs and humans and is characterised by chaotic depolarisation of the atria, resulting in damage to the atrial myocardium. It can lead to heart failure or worsen an existing condition and cause sudden death. Electrocardiographically, atrial fibrillation is characterised by the absence of P waves and an irregularly irregular rhythm, with narrow QRS complexes. Treatment of atrial fibrillation requires knowledge of pathophysiology and the pharmacology of antiarrhythmic drugs. In contrast to human medicine, the treatment of dogs revolves mainly around rate control strategies, although new studies propose the consideration of several rhythm strategies. Considering the complexity of atrial fibrillation, there is strong need for a consensus on classification, diagnosis and treatment in dogs.

Right bundle branch block in suspected acute coronary syndromes: Diagnostic challenges, treatment and prognosis

BackgroundThere is still conflicting evidence regarding the prognostic implications of right bundle branch block (RBBB) in the general population but also in patients with heart diseases like acute coronary syndromes (ACS). In accordance with current guidelines, RBBB in ACS patients is considered as STEMI equivalent. However, recent studies indicate that further differentiation is necessary in this group, as we will outline below. Methods and resultsA literature search was conducted in PubMed and Google Scholar.In previous studies, RBBB in the general population were mostly considered benign changes of the electrical conduction system. However, recent studies indicate that both complete and incomplete RBBB are associated with increased cardiovascular morbidity and mortality. In addition, among unselected patients with suspected ACS presenting to the emergency department, the prevalence of RBBB was 3 % and it was associated with elevated mortality. The subsequent angiographic identification of a culprit coronary artery stenosis leading to stent implantation was similar at approximately 2 % regardless of the initial ECG presentation with narrow QRS complexes, left bundle branch block (LBBB), or RBBB.Finally, in a group of high-risk patients for ST-elevation myocardial infarction (STEMI), the prevalence of RBBB was 12 %. While RBBB was associated with poor outcome compared to non-BBB and LBBB patients, diagnostic accuracy of STEMI criteria was not affected by the presence of RBBB. However, RBBB patients without distinct STEMI signs in ECG often showed acute STEMI on angiography indicating a potential benefit from immediate transfer to the cardiac catheterization laboratory. ConclusionIn the general population, patients with RBBB and risk factors may need further evaluation. Regarding ACS patients, recent studies support current guidelines that recommend acute invasive evaluation for high-risk ACS patients with RBBB, regardless of ST-T deviations. However, in an unselected group of ACS patients, differential diagnoses should also be investigated through additional diagnostic procedures.

Rotary excitation of non-sinusoidal pulsed magnetic fields: Towards non-invasive direct detection of cardiac conduction.

There is a need for high resolution non-invasive imaging methods of physiologic magnetic fields. The purpose of this work is to develop a MRI detection approach for non-sinusoidal magnetic fields based on the rotary excitation (REX) mechanism which was previously successfully applied for the detection of oscillating magnetic fields in the sub-nT range. The new detection concept was examined by means of Bloch simulations, evaluating the interaction effect of spin-locked magnetization and low-frequency pulsed magnetic fields. The REX detection approach was validated under controlled conditions in phantom experiments at 3 T. Gaussian and sinc-shaped stimuli were investigated. In addition, the detection of artificial fields resembling a cardiac QRS complex, which is the most prominent peak visible on a magnetocardiogram, was tested. Bloch simulations demonstrated that the REX method has a high sensitivity to pulsed fields in the resonance case, which is met when the spin-lock frequency coincides with a non-zero Fourier component of the stimulus field. In the experiments, we found that magnetic stimuli of different durations and waveforms can be distinguished by their characteristic REX response spectrum. The detected REX amplitude was proportional to the stimulus peak amplitude (R2 > 0.98) and the lowest field detection was 1 nT. Furthermore, the detection of QRS-like fields with varying QRS durations yielded significant results in a phantom setup (p < 0.001). REX detection can be transferred to non-sinusoidal pulsed magnetic fields and could provide a non-invasive, quantitative tool for spatially resolved assessment of cardiac biomagnetism. Potential applications include the direct detection and characterization of cardiac conduction.

Electrocardiographic Changes in Second and Third Trimester in Bangladesh: A Comparative Study

Background: During pregnancy, there are notable changes in cardiovascular function to meet the increasing needs of the developing baby. The objective of this study was to compare ECG in pregnant women during their second and third trimesters with a control group of non-pregnant women in Bangladesh. This study aims to offer valuable insights into the cardiovascular changes that happen during pregnancy. This study's findings are important for maternal health research and clinical practice in Bangladesh and beyond. Objective: The purpose of this study is to analyze and compare the ECG variations in women during the second and third trimesters of pregnancy. Methods: The study took place in the gynecology Department at CMH Saidpur, Bangladesh. This study was conducted from March 2023 to August 2023. During this period, 75 pregnant patients in their 2nd trimester and 75 patients in their 3rd trimester were chosen as cases from antenatal outdoor, while 75 non-pregnant women of the same age were selected as the control group. We use the purposive sampling method. Results: During pregnancy, there were notable changes in BMI, heart rate, and PR interval. BMI decreased in the second trimester and increased in the third trimester.22.67% were nulliparous and 77.33% were multiparous in 2nd trimester. In the third trimester, 26.67% were nulliparous and 73.33% multiparous. So, no significant difference in parity. Heart rate increased in both trimesters, while the PR interval shortened in both trimesters. No significant changes were observed in the durations of the QRS complex or QT interval. In our study, the QTc interval displayed a significant rise. ST depression, which may suggest decreased blood flow, was exclusively seen in pregnant women, particularly in the third trimester. Conclusion: We found no significant changes in age, but BMI, heart rate, and PR interval were significantly different from the control group throughout pregnancy. No significant QRS complex or QT interval duration changes were identified. The QTc interval rose. ST depression, more prominent in the third trimester, only affected pregnant women. As shown by ST depression, pregnancy may change cardiac function, electrical activity, and ischemia.

Analysis of the mean electrical axis of the heart from standard electrographic leads in normal adult males

Background: Electrocardiogram has been widely applied as a diagnostic tool for cardiovascular disease. The concept of the cardiac vector is crucial for the clinical application in ECG interpretation. Methods: A prospective cross-sectional study was conducted among 116 male subjects, aged 18-25 years, comprising students and staff of Gandaki Medical College Teaching Hospital and Research Center, Pokhara, Nepal, over the period from June to September 2023. Electrocardiograms (ECGs) were recorded using a standard ECG machine with conventional limb leads. The mean electrical axis of the heart for each individual was determined by plotting the net voltage of the QRS complex in Lead-I and Lead-III. The study aimed to analyze the correlation between the cardiac vector and physical measurements, such as height, weight, Body Surface Area (BSA), and Body Mass Index (BMI). Data analysis was performed using SPSS version 27.0. Results: The normal mean electrical axis of the healthy male subjects was observed as 57.88±24.55°. There was significant positive correlation of cardiac vector with height (p&lt; 0.05), whereas negative correlation was observed with weight and BMI (p&lt; 0.01). However, there was no significant correlation with BSA. In our study we observed the maximum left axis cardiac vector as -10° and right axis as 90° among 116 male subjects. Conclusion: We established a cardiac vector with values differing from those reported in other studies, using standard bipolar limb leads in normal, healthy male subjects. It is also examined that greater BMI has shifted the electrical activity of the ventricles to the left.

Novel real-time automation of combined frequency and low voltage substrate mapping to guide ablation for Brugada syndrome: a case report

Abstract Background Brugada syndrome (BrS) is an inherited cardiac condition that increases the risk of sudden cardiac death (SCD) due to ventricular arrhythmias. Catheter ablation has been shown to effectively reduce recurrent ventricular fibrillation (VF) episodes through targeting of abnormal electrograms predominantly located within the anterior surface of the right ventricular outflow tract. Signal frequency mapping is an emerging concept that provides further definition of pathological ventricular substrate. Case summary A 66-year-old male with BrS was admitted to our institution with ICD shocks for VF. Electro-anatomical mapping (EAM) and ablation was performed utilising a novel automated frequency-based strategy. Combined automated frequency and low voltage maps were generated to define high frequency, low voltage (HF-LVo) depolarisation abnormalities within the QRS complex. Low frequency, low voltage (LF-LVo) regions from the QRS terminal notch to the T-wave offset were also identified. The combined HF-LVo and LF-LVo map areas totalled 12.4cm2, compared to the conventional low voltage and late potential map areas, which were 44cm2 and 27.8cm2 respectively. The ablation strategy targeted HF-LVo and LF-LVo regions only. Following ablation, re-mapping demonstrated near complete abolition of HF-LVo and LF-LVo regions, with no inducible ventricular arrhythmias during extra-stimulation testing. During follow-up, ECG normalisation was observed, with no further ventricular arrhythmias and a negative ajmaline challenge at 6 months. Discussion Catheter ablation for BrS utilising a novel automated combined frequency and low voltage EAM approach can objectively identify relevant substrate. The results demonstrate adequate substrate modification with comparable ablation target areas to previous studies and encouraging clinical outcomes.

Prolonged ventricular activation time as a novel biomarker identifying burn-out phase of hypertrophic cardiomyopathy

Abstract Background Patients with hypertrophic cardiomyopathy (HCM) classically have preserved systolic function and decreased left ventricular end-diastolic volume. However, in a small sub-population, patients paradoxically develop systolic dysfunction, left ventricular dilatation, and ventricular wall thinning, which is known as end-stage hypertrophic cardiomyopathy or "burned-out cardiomyopathy’. Although an electrocardiogram (ECG) is a pivotal tool in HCM, its role in the detection of burned-out HCM has not been investigated. Purpose We assessed the ventricular activation time (VAT), an ECG marker of the duration of ventricular depolarization, as a predictive tool in the detection of the HCM burn-out phase. Methods We prospectively studied consecutive patients diagnosed with HCM via echocardiography at our medical center between 2017 and 2022. The ECG, along with echocardiography, was performed on the same day as the diagnosis. VAT was measured in milliseconds between the onset of the QRS complex to the peak or R wave on the V5 and V6 precordial ECG lead. HCM burn-out phase was supported when the left ventricular ejection fraction (LVEF) was below 50%, measured with echocardiography. Statistical analysis was performed using the SPSS software. Results Forty-five patients with HCM were studied, and their mean age was 51, while 78% (35/45) were male. Echocardiography data upon diagnosis revealed a mean maximum wall thickness of 19 (±3mm) and a mean left ventricular ejection fraction of 65% (±5%). Left ventricular outflow obstruction was present in 31% (14/45). During the study, 24% (11/45) presented atrial fibrillation, 44% (20/45) had an ICD implantation, and 22% (10/45) progressed to the burn-out phase of HCM. HCM patients who presented atrial fibrillation (63±31 vs. 46±14msec, p=0.018) or burn-out phase (65±32 vs. 46±13msec, p=0,009) had a significantly higher VAT than those subsets without. Notably, there was a significant positive relationship between VAT a burn-out phenotype (r=0,385, p=0.009). HCM patients with greater VAT also had a significantly higher risk of presenting a larger left atrial diameter (r=0,295, p=0.048), an increased left ventricular end-diastolic diameter (r=0.306, p=0.041), and a trend of presenting a lower LVEF (r=-0,262, p=0.082). Finally, we revealed a positive relationship between VAT and atrial fibrillation incidence (r=0,352, p=0.018). Conclusion Prolongation of VAT predicts the incidence of burn-out stage in patients with HCM and atrial fibrillation. Therefore, it seems to be a promising, inexpensive ECG marker for HCM progression and severity. Our findings emphasize the pivotal role of the ECG as a useful and inexpensive tool in the diagnostic follow-up of HCM.

Dual-chamber CRT-D using ICD lead implantation in the LBBAP position

Abstract Background Interest in conduction system pacing (CSP) has increased in recent years. For left bundle branch area pacing (LBBAP), 4F and 6F pacing leads have been shown to be effective and safe. No information is available on the potential use of ICD leads for LBBAP. Aim The objective of the study was to demonstrate the feasibility of implanting an ICD lead in the LBBAP position to reduce the number of leads for CRT-D therapy. Patients and Methods We implanted the 7F ICD lead in the LBBAP position through a new 10F CSP delivery sheath in ten consecutive patients. Periprocedural data, QRS morphology and degree of QRS reduction were analyzed. Results Ten consecutive patients (one female) aged 69.5±9.2 years were treated with the above-mentioned method. Eight patients had ischemic cardiomyopathy and two patients had nonischemic cardiomyopathy. All patients had a CRT-D indication. Eight patients had a wide QRS complex with complete LBB and a QRS complex of 184.8±25.8 ms. Two patients had a narrow QRS complex but first-degree AV block with a PR interval greater than 240 ms. Left ventricular ejection fraction was 31.8±8.6%. Operative and fluoroscopy times were 103.6±30.3 minutes and 10.5±6.1 minutes, respectively. On average, 1.7 ± 0.6 screwing attempts were required per patient. The intraprocedural LBBAP threshold was 0.78±0.6V/1.0ms, the impedance was 530.8±86.5 ohm, and the R-wave amplitude was 9±3.3mV. The unipolar paced QRS complex was 123.6±15.9ms, the bipolar paced QRS complex was 129.5±12.8ms, and the bipolar paced QRS complex on the next day was 133.3±11.7. The mean duration from stimulus to R-wave peak in lead V6 was 82.9 ± 19.7 ms. The R-wave interpeak interval between leads V6 and V1 was 43.4 ± 9.7 ms. All but one patient received an effective defibrillation threshold test at 30J (n=8) and 36J (n=1). One patient was not tested during the procedure due to high risk. Conclusion This first-in-human study of ICD lead implantation in the LBBAP position demonstrated its feasibility and efficacy in achieving conduction system stimulation. This approach may lead to a reduction in the number of leads implanted for cardiac resynchronization therapy. Figure 1. A- RAO view, angiography of the RV for verification of the TVA-summit. B- LAO view, angiography from the CSP- sheath after reaching final position of the LBBAP lead (right sided interventricular septum - yellow dotted line). C – 12 lead ECG (speed 50mm/sec) demonstrating paced and native QRS complexes. D – Fluoroscopy in RAO view, final result. E – Fluoroscopy in LAO view, final result. F – Transthoracic echocardiography the next day (4Ch view) demonstrates optimal LBBAP lead position.. RAO – right anterior oblique; LAO – left anterior oblique; TVA – tricuspid valve anulus; CSP – conduction system pacing; LBBAP – left bundle branch area pacing.Figure 1.

Validation of an artificial intelligence system for holter ECG analysis

Abstract Introduction Holter ECG is a commonly used tool to identify heart rhythm disorders. As physician-based analysis of such Holter ECG is time consuming, various approaches using computerized interpretation have been developed. However, accuracy of these tools remains inferior to physician-based analysis. Thus, this study assesses the diagnostic performance of an artificial intelligence (AI)-powered Holter ECG service in comparison to results from reference databases as well as with physician-based evaluation. Methods 231 ECG recordings, covering 2,261 hours of ECG with annotations for 10,024,315 heartbeats from the following reference databases were used: MIT-BIH Arrhythmia (MITDB), American Heart Association ECG (AHDB), MIT-BIH Atrial Fibrillation (AFDB), Long Term Atrial Fibrillation (LTAFDB). Those recordings were originally collected from a mixed population of inpatients and outpatients between 1975 and 2008. Analysis of these recordings regarding the detection of QRS complexes, QRS classification and detection of Atrial Fibrillation (AF) was performed using a novel service for AI-based ECG analysis. Results were compared to the diagnosis stated within the database. QRS complex detection accuracy was performed on recordings from MITDB and AHADB by checking if time positions are within 150 ms to reference annotations. The QRS classification in three classes (normal, supraventricular, ventricular) was then compared for each detected heartbeat. Mismatches were adjudicated manually by three experts. Episodes of Atrial Fibrillation were detected in recordings from MITDB, AFDB and LTAFDB and compared to the reference episodes from the databases. The accuracy was evaluated based on the overlap with the reference annotations in the time-domain. Results Sensitivity and Precision of heartbeat detection compared to the reference databases exceeded 99% Figure 1 displays the results of heartbeat classification. Normal heartbeats were classified with a sensitivity of 99.6%, precision of 99.9% and specificity of 99.6%. For ventricular heartbeats, a sensitivity of 99.58 %, precision of 99.88 and specificity of 99.99% were achieved. Premature supraventricular contractions were recognized with a sensitivity of 99.58 %, precision of 100% and specificity of 100%. When comparing the 248,187 QRS complex classifications of MITDB and AHADB to the AI-powered analysis, 128 discrepancies were revealed. 43 were due to a discrepancy of convention as these beats were in sections that were also marked as AF episodes by the databases and the AI-powered analysis marks all beats in AF episodes as normal. Of the 85 remaining discrepancies, more than 87% were adjudicated in favor of the AI-powered analysis by the experts. Figure 2 shows the comparison of AF detection results showing Sensitivity and Precision above 99%. Conclusion AI-powered Holter ECG analysis compared to reference ECG stripes exceed 99% of sensitivity, specificity and precision.QRS complex detectionAF/ AFib detection

Prognostic parameters predict cardiac events in Brugada syndrome: a meta-analysis

Abstract Background Brugada syndrome (BrS) is recognized as a cause of sudden cardiac death (SCD), ventricular tachycardia or ventricular fibrillation (VT/VF). However, the prognosis varies among the patients with Brugada electrocardiograph (ECG) pattern. Furthermore, there is no prognostic tool to predict the worsening cardiac outcomes in BrS. Objectives Primary outcome was to assess the association between risks including patient history, ECG pattern, electrophysiology study (EPS) findings and cardiac events which is identified as VT/VF or SCD. Method We performed a meta-analysis of prospective and retrospective cohort studies which assessed the risks and cardiac events in patients with BrS. Pooled hazard ratios (HRs) was analyzed by using Random-effect model. Result A total of 27 studies involving 15,990 BrS patients. Of these, 17 were retrospective studies and 10 were prospective studies. In univariate analysis, the risks including male, aborted SCD, QRS duration≥120 msec, fragmented QRS (multiple spikes within the QRS complex in lead V1-V3), late potential (positive terminal filtered QRS complex of signal-averaged ECG), sinus node dysfunction or inducibility of ventricular tachyarrhythmias during EPS associated with a higher risk of cardiac events in BrS. In multivariate analysis, higher risks of cardiac events were associated in BrS patients with history of syncope (HR 2.65, 95% confidence interval (CI): 1.68-4.19, I2 = 54 %, p-value &amp;lt;0.001), family history of SCD (HR 2.64, 95%CI:1.39-5.01, I2 = 0%, p-value = 0.003), prior VF (HR 14.52, 95%CI: 3.36-62.84, I2 = 62%, p-value &amp;lt;0.001), type 1 Brugada ECG pattern (HR 2.07, 95%CI: 1.13-3.79, I2 = 0%, p-value = 0.018), spontaneous type 1 ECG pattern (HR 1.91, 95%CI: 1.01-3.61, I2 = 58%, p-value = 0.046), early repolarization pattern (HR 2.78, 95%CI: 1.9-4.07, I2 = 0%, p-value &amp;lt; 0.001) and history of atrial fibrillation before BrS diagnosis (HR 1.82, 95%CI: 1.03-3.23, I2 = 49%, p-value = 0.039) (Table 1). Conclusion Our findings suggest that patient history, ECG pattern, EPS findings can predict the cardiac events. Introducing a risk prediction model could aid in early management of BrS.

QRS complex fragmentation status before and after cardiac resynchronization therapy predicts hospitalizations for heart failure

Abstract Introduction Cardiac resynchronization therapy (CRT) reduces mortality and hospitalization for heart failure (HF) in selected patients with HF with reduced ejection fraction (HFrEF). However, there is a significant percentage of non-responders who are readmitted for HF after implantation. Several biomarkers and electrocardiographic findings have been suggested as prognostic markers in this group of patients. Fragmentation of the QRS complex (QRSf) has been associated with worse prognosis in several cardiac diseases, but evidence in patients undergoing CRT remains to be limited. Purpose To evaluate if the changes in QRSf status before and after CRT implantation have a prognostic role in patients undergoing CRT in terms of hospitalization for HF. Methods Consecutive patients undergoing CRT were prospectively included from October 2009 to December 2022. Demographic clinical, electrocardiographic and echocardiographic variables were recorded. Prospective follow-up variables were collected from electronic clinical records and telephone interview. QRSf complex was defined by the presence of different RSR′ patterns including an additional R-waves (R′) and notches of the R-wave and S-wave in two contiguous leads corresponding to a main coronary artery territory in a 12-lead surface electrocardiogram performed before and after CRT. Results A total of 244 patients (mean age 72 ± 10 years, 80% male) were included. The etiology of the LV systolic dysfunction was ischemic in 50.0%. Mean LVEF before implantation was 25 ± 9% and mean paced QRS width was 141 ± 23 ms. CRT-D was implanted in 176 patients (72.2%). At baseline, 150 patients had a QRSf. After CRT implantation, 69 (28.4%) patients experimented a change in QRSf status: 29 patients (11.9%) without prior QRSf developed QRSf, whereas 40 patients (16.5%) resolved QRSf after CRT. Median follow-up time was 36.0 months (interquartile range 18.2-75.7). At follow-up, 90 patients died and 91 presented at least one hospitalization for HF. Multivariate Cox regression survival analysis showed that development of QRSf after CRT implantation (HR 8.87; 95% CI 1.85-42.50) and the presence of QRSf before implantation with or without paced QRSf after CRT (HR 8.21; 95% CI 1.75-38.50 and HR 16.70; 95% CI 3.88-71.80 respectively) were independently associated with hospitalizations for HF. Univariate and multivariate Cox regression analyses for HF hospitalization are presented in Table 1. Figure 1 presents Kaplan-Meier curves for QRSf status and hospitalizations for HF. Conclusions According to our results, QRSf status before and after CRT have a significant prognostic role in terms of hospitalization for HF after CRT, especially in those who develop QRSf after CRT and those with baseline QRSf regardless QRSf status after CRT. The worse prognosis was observed in those with QRSf before and after CRT. Therefore, these patients should be followed more strictly because they are at higher risk of decompensation.Table 1.Cox Regression Analyses

An explainable AI for trustworthy detection of atrial fibrillation on reduced lead ECGs in mobile applications

Abstract Introduction Artificial intelligence (AI), particularly deep learning (DL), has demonstrated high performance in various diagnostic problems, including the detection of paroxysmal atrial fibrillation (AF) from electrocardiograms (ECGs). In mobile applications, these approaches can help to detect AF at an early stage and thus prevent possible secondary diseases. However, due to their black-box nature, DL approaches lack explainability and interpretability. Furthermore, 12-lead ECGs are the clinical standard, but mobile devices usually only provide 1–3 leads, which are similar but not identical to Einthoven leads and differ in morphology. Purpose We apply a recently introduced explainable ECG analysis architecture (xECGArch) to single-lead ECGs to verify its performance in mobile applications. xECGArch can learn rhythmic and morphological characteristics using two parallel convolutional neural networks of different dimensions (Fig. 1). When combined with methods from explainable AI, the classification can be traced back to rhythmic and morphological characteristics. Methods We used a subset of 9 854 ECGs (n(AF) = n(non-AF) = 4 927) from 4 public databases (Chapman-Shaoxing, CPSC2018, Georgia, and PTB-XL). Noise was removed using a cascade of high-pass filtering at 0.3 Hz and discrete wavelet transform. For each lead, we trained xECGArch on single-lead ECGs of 10 s length to classify AF vs. non-AF using 90% of the ECGs with 5-fold cross-validation and tested it on the remaining randomly selected ECGs (n(AF) = 507, n(non-AF) = 479). Consistent data splitting was ensured for all leads. Model explanations were generated using deep Taylor decomposition. Results Both models achieved minimum 91.1% accuracy for each ECG lead (Fig. 1). On lead I, the morphology model outperformed the rhythm model with 92.8% vs. 91.5% accuracy, while the rhythm model slightly outperformed the morphology model on leads II and III with 94.2%–95.0% accuracy vs. 91.1%–94.0%. Both models achieved maximum accuracy of 95.0% (rhythm) and 94.0% (morphology) on lead II. By combining both models, xECGArch reached 93.7%–95.1% accuracy. The model explanations confirm that the rhythm model primarily considers QRS complexes as relevant, while the morphology model focuses on fibrillatory waves (Fig. 1). Conclusions Both rhythm and morphology models achieved reliable results across all leads, competing with the state-of-the-art for automatic AF detection from single-lead ECGs. The combination of both models in xECGArch further increased the accuracy. xECGArch is based on the medical reading of ECGs by considering rhythm and morphology characteristics and is therefore interpretable by design. The model explanations are consistent with the diagnostic criteria for AF (Fibrillatory waves and absolute arrhythmia) across leads. With high accuracy on different single-lead ECGs and improved interpretability, xECGArch provides a trustworthy method for ECG analysis in mobile applications.

Identifying heart failure dynamics using multi-point electrocardiograms and deep learning

Abstract Background Heart failure (HF) hospitalizations are related to poor survival outcomes, emphasizing the need for early detection and intervention. Recent studies have reported the potential of deep learning algorithms in identifying heart failure through electrocardiogram (ECG) with notable accuracy. However, evidence supporting their utility in the ongoing monitoring and follow-up of HF patients remains uncertain. Advanced diagnostic tools that can effectively track heart failure progression or improvement over time are needed. Purpose To address this challenge, we developed a deep learning model analyzing 12-lead ECG waveforms at two time points, aiming to detect HF deterioration or improvement, potentially revolutionizing HF management. Methods This study analyzed 32,045 ECGs from 6,892 unique adult patients (aged 18 years and older) visiting the Department of Cardiology at Kobe University Hospital. The participants were randomly assigned to training (4,284 patients), validation (1,034 patients), and test (1,034 patients) datasets. ElecTransformer was developed to classify HF status into deteriorated, improved, and no change classes based on ECG waveform signals at two different time points and to estimate brain natriuretic peptide (BNP) levels. Performance metrics, such as the area under the receiver operating characteristic curve (AUROC) and accuracy, were calculated, and attention mapping via gradient-weighted class activation mapping was utilized to interpret the model's decision-making ability. Results The patients had an average age of 65 years (±15.4 years) and BNP levels averaged 71.5 pg/mL (25.8 to 185.2 pg/mL). For HF status classification, ElecTransformer achieved an AUROC of 0.845 and an accuracy of 0.821, improving to an AUROC of 0.885 and an accuracy of 0.833 with baseline BNP integration. The ElecTransformer accurately estimated BNP levels from ECG data, evidenced by a correlation coefficient of 0.798. Averaged attention mapping showed that the QRS complex was the most important feature for determining model outputs with lesser effects seen for P waves and T waves variance Conclusions Harnessing a Transformer-based deep learning model to analyze multiple ECGs markedly improves the accuracy in detecting changes in heart failure status. This method offers a valuable non-invasive option for monitoring heart failure progression, potentially leading to better patient management and earlier intervention in heart failure treatment.Architecture and Performance of ModelsAveraged attention mapping

Validation of chest-belt ECG evaluation using artificial intelligence

Abstract Background Simple, cheap wearables for long-term ECG monitoring with automatic analysis of all measurements using a bespoke artificial intelligence (AI) are scarce. Annotated single-lead ECG data from a chest-belt are missing. Methods We have developed a complex software environment to acquire raw ECG data from the Polar H10 chest-belt, and a bespoke, original AI to detect artifacts, QRS complexes and the presence of atrial fibrillation (AF) from chest-belt recordings. Original manually annotated ECG recordings from real patients from cardiology departments using the chest-belt and a public MIT-BIH database as reference were used for validation. Results QRS determination by AI (version Q4/23) in evaluating MIT-BIH database of ECG samples had a 97.67 % sensitivity and a 97.73 % positive predictive value. AF in MIT-BIH database was detected by AI with 90.31 % sensitivity and 92.09 % positive predictive value. To assess AI accuracy in ECG from a chest-belt, 150 consecutive measurements using Polar H10 chest-belt (215 hours of ECG recordings in total) from individual patients were included in the analysis. Patients were not limited in any physical activity during measurements. 7.15 % of the length of all recordings (15.4 hours) was assessed as noise by AI and excluded from the analysis. AF lasting longer than 30 seconds was present in 14 of 150 (9.3 %) manually evaluated recordings. QRS determination by AI in evaluating manually annotated chest-belt data had 99.76 % sensitivity and 99.74 % positive predictive value. AF in manually annotated chest-belt data was detected by AI with 92.86 % sensitivity and 100 % positive predictive value. Conclusion A chest-belt can be used to reliably detect QRS complexes and the presence of atrial fibrillation with high accuracy when using a bespoke artificial intelligence for the evaluation. Commonly available devices capable of long ECG measurements could be used for patient-empowered screening for important arrhythmias.Atrial fibrillation on chest-belt ECG

Local ventricular activation at the distal great cardiac vein determines right- and left-sided approach for catheter ablation of outflow tract arrhythmias: a simple and rapid discriminator

Abstract Background When the precordial transition zone (TZ) of idiopathic outflow tract arrhythmias (OTAs) is present around lead V3, it may be difficult to precisely determine which outflow tract is responsible for the origin of the OTAs from the ECG characteristics. Purpose We hypothesized that mapping around the distal portion of the great cardiac vein (dGCV) would be useful for identifying which outflow tract is the origin of OTAs during radiofrequency catheter ablation (RFA). Methods Among 28 OTA patients who underwent dGCV mapping and successful RFA at our institution from June 2021 to February 2024, 16 whose TZ during the OTAs was ＞lead V2 and ＜lead V4 were included in this study. In all patients, activation mapping around the dGCV with the novel 2.7 Fr over-the-wire (OTW)-type decapolar catheter was performed during the OTAs. Results In all patients, the mapping catheter could be easily placed in the dGCV. In patients whose OTAs were successfully ablated from the left-sided OT (n=7), the local ventricular activation time in the dGCV during OTAs preceded the QRS onset (LAT-dGCV) by -26.1±7.0 msec, which was significantly earlier than that of OTAs successfully ablated from the right-sided OT (n=9; -4.0±5.7 msec; p&amp;lt;0.001). An LAT-dGCV &amp;gt;-18 msec indicated a left-sided OTA, and right-sided and left-sided OTAs were completely distinct. Patients with an LAT-dGCV &amp;gt;-18 msec and mapping initiated first in the left-sided OT had shorter procedure times than those with mapping initiated first in the right-sided OT (p&amp;lt;0.001). Conclusions Mapping the dGCV with this OTW-type catheter is easy and safe. The earliness of the local ventricular activation in the dGCV during OTAs could easily and precisely differentiate between right-sided and left-sided OTAs, resulting in a successful ablation with a shorter procedure time.

A mcgyvering way to left bundle branch area pacing : using the treadmill test machine ECG system and modified V1 / V6 leads connected to the pacing system analyser for left bundle branch area pacing

Abstract Background Left bundle branch area pacing (LBBaP) is a novel pacing modality which provides physiological synchronisation of both the ventricles. However, its use and adoption requires the presence of a standardised electrophysiological (EP) system with 12 lead ECG to show left bundle branch area capture. Purpose The aim of the study was to assess the feasibility and outcomes of using the conventional treadmill test (TMT) machine 12 lead ECG system and modified V1 and V6 leads connected to the pacing system analyser (PSA) to demonstrate conduction system capture during left bundle branch area pacing (LBBaP). Methods LBBaP was attempted by a single operator in a mixed cohort of patients at peripheral hospitals lacking the standardised EP system. The presence of LBB area capture was tested with the aid of the 12 lead ECG system connected to the standard TMT machine (1). Conduction system capture was also assessed using modified V1 and V6 leads connected to the PSA for measurement of V6 left ventricular activation time (LVAT)(2) . The baseline clinical, procedural, pacing, electrocardiographic parameters, echocardiographic response (&amp;gt; 10% improvement in ejection fraction {EF}) and clinical response to LBBaP were assessed. Results LBBaP was attempted in 19 patients and was successful in 18 patients (94.7%). Patient characteristics include age 66.7 +/- 11.47 years, female 47.37%, male 52.63%, ischaemic cardiomyopathy 10.52% and non-ischaemic cardiomyopathy 5.26% .The mean baseline EF and QRS duration was 45%+/-14% and 130.18 +/-10.45 milliseconds(ms) respectively. LBBaP threshold was 0.59 +/-0.168 volts and R wave amplitude was 12+/-3.5 millimetres , which remained stable during the mean follow up of 15.9 +/-13.67 months. The mean fluoroscopic duration was 11.57 +/-2.58 minutes and procedural time was 108.78+/-29.20 minutes. LBBaP resulted in impressive narrowing of the QRS duration to 102.39 +/-10.55 ms (p&amp;lt;0.001) with LVAT of 68.94 +/-9.94 ms. LVEF improved in the patients with cardiomyopathy from 33.4 +/- 5.77 % to 48.2+/-12.37 % (p=0.028) .Clinical and echocardiographic response was noted in 87.5% of patients with cardiomyopathy. Conclusion The 12 lead ECG system with the standardised TMT machine in conjunction with the modified V1 and V6 leads connected to the PSA is a feasible alternative to the EP system to perform successful left bundle branch area pacing.ECG leads connected during LBBapClinical profile of patients

The impact of QRS complex fragmentation status before and after cardiac resynchronization therapy with defibrillator implantation: Is it a predictor of arrhythmic events?

Abstract Introduction Cardiac resynchronization therapy with an implantable cardioverter defibrillator (CRT-D) has demonstrated efficacy in reducing mortality, hospitalization for heart failure (HF), and sudden cardiac death among subgroups of patients with HF with reduced ejection fraction (HFrEF). However, this population is highly heterogeneous, necessitating risk stratification. Several clinical findings, including QRS complex fragmentation (QRSf), have been identified as potential prognostic factors for arrhythmic risk. Nonetheless, evidence supporting the prognostic significance of QRSf in patients undergoing CRT-D remains limited. Purpose The aim of this study is to assess whether alterations in QRSf status, before and after CRT-D implantation, can predict arrhythmic events (AE) in patients with HFrEF. Methods This study included consecutive patients underwent CRT-D implantation at our center from October 2009 to December 2022. Demographic, clinical, electrocardiographic and echocardiographic data were obtained from electronic medical records and telephone interviews. QRSf was defined by the presence of various RSR′ patterns, including additional R waves (R′) or notching of the R and S wave in two contiguous leads corresponding to a primary coronary artery territory on a 12-lead electrocardiogram conducted before and after CRT-D implantation. An AE was characterized by appropriate ICD therapy (antitachycardia pacing or shock) for a ventricular arrhythmia or sustained ventricular arrhythmia without the need for ICD therapy. Results A total of 176 patients were included (mean age 69.9 ± 9.6 years with 80.6% male). Ischemic etiology accounted for 54.6% of cases of LV systolic dysfunction, with a mean baseline LVEF of 23.6%. CRT-D was indicated as secondary prevention in 18 patients. At baseline, 114 patients (64.8%) presented QRSf. Following CRT implantation, 17 patients (9.8%) without previous QRSf developed QRSf, while 26 patients (14.9%) resolved QRSf. The median follow-up was 43.6 months (interquartile range 19.5-81.1). During follow-up, 90 patients died and 29 AE occurred (16.5%). Among these, 23 patients had QRSf before and after CRT, whereas 6 AE occurred in patients without QRSf. Multivariate survival analysis using Cox regression demonstrated that the presence of QRSf before and after CRT-D was an independent predictor of AE (HR 3.56; 95% CI 1.00-12.70). Univariate and multivariate Cox regression analyses are presented in Table 1. Kaplan-Meier curves for AE in relation to QRSf status before and after CRT-D are illustrated in Figure 1. Conclusions Our findings suggest that the presence of QRSf and its persistence following CRT-D implantation appears to be an independent predictor of AE after CRT-D implantation in patients with HFrEF. Therefore, these patients would benefit from closer monitoring as they exhibit a heightened risk of arrhythmic events. Nevertheless, further research is warranted to validate these results.Table 1.Cox Regression Analysis.

Utilizing unsupervised machine learning to uncover novel phenogroups within the broad QRS complex

Abstract Background Conduction disease can manifest as a broad QRS complex on the ECG. Broad QRS is conventionally categorised as left bundle branch block (LBBB) and right bundle branch block (RBBB) or non-specific intraventricular conduction delay (IVCD), based on QRS morphology. These subgroups were coined over a century ago and have been relevant for heart failure with reduced ejection fraction and cardiac resynchronization therapy (CRT). However, there may be more precise phenogroups underlying broad QRS complexes. Purpose Using unsupervised machine learning to define novel broad QRS phenogroups and characterise them using clinical variables and disease outcomes. Methods We extracted 51 relevant features using a Variational Autoencoder from 47,456 median-beat ECGs with broad QRS intervals (QRS ≥ 130ms) from a secondary care cohort. These were input into Discriminative Dimensionality Reduction via Learning a Tree (DDRTree), a clustering method that models the continuum of heterogeneity by projecting the underlying distribution as a tree structure in a low-dimensional space, while assigning distinct branch/cluster labels. Results Six distinct phenogroups were identified within broad QRS morphologies (Figure-1). Two branches were RBBB dominant (Branch 1: more males, high-comorbidity; Branch 6: low-comorbidity/healthy-RBBB). Two branches were LBBB dominant (Branch 4: mixed IVCD with CHB burden; Branch 5: more females, CRT responders). Two branches were IVCD/mixed-phenotype (Branch 2: IVCD-dominant, high risk of future cardiovascular events; Branch 3: average/core branch). Within LBBB, Branch 4 and 5 showed similar trends with improving echocardiography profiles and CRT response when adjusted for covariates, each compared against the core branch. Branch 5 was distinct due its high risk of future HF (HR 1.19 [1.07-1.33] p &amp;lt; 0.01), cardiovascular death (HR 1.35 [1.20-1.50] p &amp;lt; 0.0001), all-cause mortality (HR 1.08 [1.01-1.16] p &amp;lt; 0.05) and CHB (HR 1.35 [1.16-1.56] p &amp;lt; 0.0001) (Figure-2). Conversely within RBBB, Branch 1 and 6 showed stark differences across various traits. Branch 1 captured a high-risk profile associated to higher risk of cardiovascular death (HR 1.37 [1.24-1.52] p &amp;lt; 0.0001), all-cause mortality (HR 1.20 [1.12-1.29] p &amp;lt; 0.0001) and CHB (HR 1.15 [1.01-1.32] p &amp;lt; 0.05) (Figure-2), while Branch 6 retained a low-risk phenotype. The tree dimensions also revealed relevant trends in cardiac anatomy and valvular dysfunction; the top-left region in Figure-1 associated with higher left ventricular ejection fraction and lower left ventricular end-diastolic dimension, lower left ventricular end-systolic dimension and a greater CRT response. Conclusion Through unsupervised methods we have identified conduction disease phenogroups with additive value for disease prognosis and CRT response prediction beyond traditional LBBB and RBBB labels. These novel phenogroups may help guide precision care for patients with a broad QRS complex.Figure-1Figure-2