Cardiac resynchronization therapy (CRT) reduces morbidity and mortality in systolic heart failure patients with ventricular conduction delay. Variability of individual response to CRT warrants improved patient selection. The Markers and Response to CRT (MARC) study was designed to investigate markers related to response to CRT. We prospectively studied the ability of 11 clinical, 11 electrocardiographic, 4 echocardiographic, and 16 blood biomarkers to predict CRT response in 240 patients. Response was measured by the reduction of indexed left ventricular end-systolic volume (LVESV_i) at 6 months follow-up. Biomarkers were related to LVESV_i change using log-linear regression on continuous scale. Covariates that were significant univariately were included in a multivariable model. The final model was utilized to compose a response score. Age was 67 ± 10 years, 63% were male, 46% had ischaemic aetiology, LV ejection fraction was 26 ± 8%, LVESV_i was 75 ± 31 mL/m², and QRS was 178 ± 23 ms. At 6 months LVESV_i was reduced to 58 ± 31 mL/m² (relative reduction of 22 ± 24%), 130 patients (61%) showed ≥ 15% LVESV_i reduction. In univariate analysis 17 parameters were significantly associated with LVESV_i change. In the final model age, QRS_AREA (using vectorcardiography) and two echocardiographic markers (interventricular mechanical delay and apical rocking) remained significantly associated with the amount of reverse ventricular remodelling. This CAVIAR (CRT-Age-Vectorcardiographic QRS_AREA -Interventricular Mechanical delay-Apical Rocking) response score also predicted clinical outcome assessed by heart failure hospitalizations and all-cause mortality. The CAVIAR response score predicts the amount of reverse remodelling after CRT and may be used to improve patient selection. Clinical Trials: NCT01519908

Atrial fibrillation (AF) is often preceded by underlying cardiac diseases causing ventricular pressure overload. It was our aim to investigate the progression of atrial remodeling in a small animal model of ventricular pressure overload and its association with induction of AF. Male mice were subjected to transverse aortic constriction (TAC) or sham operation. After four or eight weeks, echocardiographic measurements and hemodynamic measurements were made and AF induction was tested. The hearts were either fixed in formalin or ventricles and atria were separated, weighed and snap-frozen for RNA analysis. Four weeks of pressure overload induced ventricular hypertrophy and minor changes in the atria. After eight weeks a significant reduction in left ventricular function occurred, associated with significant atrial remodeling including increased atrial weight, a trend towards an increased left atrial cell diameter, atrial dilatation and increased expression of markers of hypertrophy and inflammation. Histologically, no fibrosis was found in the left atrium. But atrial gene expression related to fibrosis was increased. Minor changes related to electrical remodeling were observed. AF inducibility was not different between the groups. Left ventricular end diastolic pressures were increased and correlated with the severity of atrial remodeling but not with AF induction. Permanent ventricular pressure overload by TAC induced atrial remodeling, including hypertrophy, dilatation and inflammation. The extent of atrial remodeling was directly related to LVEDP and not duration of TAC per se.

This study aims to identify and visualize electrocardiogram (ECG) features using an explainable deep learning–based algorithm to predict cardiac resynchronization therapy (CRT) outcome. Its performance is compared with current guideline ECG criteria and QRS_AREA. A deep learning algorithm, trained on 1.1 million ECGs from 251 473 patients, was used to compress the median beat ECG, thereby summarizing most ECG features into only 21 explainable factors (FactorECG). Pre-implantation ECGs of 1306 CRT patients from three academic centres were converted into their respective FactorECG. FactorECG predicted the combined clinical endpoint of death, left ventricular assist device, or heart transplantation [c-statistic 0.69, 95% confidence interval (CI) 0.66–0.72], significantly outperforming QRS_AREA and guideline ECG criteria [c-statistic 0.61 (95% CI 0.58–0.64) and 0.57 (95% CI 0.54–0.60), P < 0.001 for both]. The addition of 13 clinical variables was of limited added value for the FactorECG model when compared with QRS_AREA (Δ c-statistic 0.03 vs. 0.10). FactorECG identified inferolateral T-wave inversion, smaller right precordial S- and T-wave amplitude, ventricular rate, and increased PR interval and P-wave duration to be important predictors for poor outcome. An online visualization tool was created to provide interactive visualizations (https://crt.ecgx.ai). Requiring only a standard 12-lead ECG, FactorECG held superior discriminative ability for the prediction of clinical outcome when compared with guideline criteria and QRS_AREA, without requiring additional clinical variables. End-to-end automated visualization of ECG features allows for an explainable algorithm, which may facilitate rapid uptake of this personalized decision-making tool in CRT. First, an artificial intelligence algorithm (variational auto-encoder) was pretrained on 1.1 million electrocardiograms (ECGs) to learn the underlying continuous factors that generate the ECG (i.e. the FactorECG). In this process, the variational auto-encoder (VAE) learns to reconstruct ECGs as accurately as possible using only 21 continuous factors without any human input. In the training phase, the pre-procedural median beat ECGs of 1306 cardiac resynchronization therapy (CRT) patients were each converted into their FactorECG. These 21 factors were subsequently used as input in a Cox model to predict the primary composite endpoint of left ventricular assist device implantation, heart transplantation and all-cause death, and the secondary endpoint of echocardiographic response. FactorECG significantly improved outcome prediction following CRT when compared with the current guidelines and QRS_AREA. The algorithm is explainable by using the decoder to visualize the effect of the ECG factors that significantly predicted outcome on the median beat ECG morphology. Here, for example, the influence of Factor 9 (F₉) is visualized, where higher values represent a more left bundle branch block-like ECG morphology and lower values, a more right bundle branch block-like morphology. CRT, cardiac resynchronization therapy; DNN, deep neural network; ECG, electrocardiogram; HTx, heart transplantation; LVAD, left ventricular assist device.

Parameters using myocardial strain analysis may predict response to cardiac resynchronization therapy (CRT). As the agreement between currently available strain imaging modalities is unknown, three different modalities were compared. Twenty-seven CRT-candidates, prospectively included in the MARC study, underwent cardiac magnetic resonance (CMR) imaging and echocardiographic examination. Left ventricular (LV) circumferential strain was analysed with CMR tagging (CMR-TAG), CMR feature tracking (CMR-FT), and speckle tracking echocardiography (STE). Basic strain values and parameters of dyssynchrony and discoordination obtained with CMR-FT and STE were compared to CMR-TAG. Agreement of CMR-FT and CMR-TAG was overall fair, while agreement between STE and CMR-TAG was often poor. For both comparisons, agreement on discoordination parameters was highest, followed by dyssynchrony and basic strain parameters. For discoordination parameters, agreement on systolic stretch index was highest, with fair intra-class correlation coefficients (ICC) (CMR-FT: 0.58, STE: 0.55). ICC of septal systolic rebound stretch (SRS_sept) was poor (CMR-FT: 0.41, STE: 0.30). Internal stretch factor of septal and lateral wall (ISF_sep–lat) showed fair ICC values (CMR-FT: 0.53, STE: 0.46), while the ICC of the total LV (ISF_LV) was fair for CMR-FT (0.55) and poor for STE (ICC: 0.32). The CURE index had a fair ICC for both comparisons (CMR-FT: 0.49, STE 0.41). Although comparison of STE to CMR-TAG was limited by methodological differences, agreement between CMR-FT and CMR-TAG was overall higher compared to STE and CMR-TAG. CMR-FT is a potential clinical alternative for CMR-TAG and STE, especially in the detection of discoordination in CRT-candidates.

Objective Atrial fibrillation (AF) often progresses from paroxysmal AF (PAF) to more permanent forms. To improve personalised medicine, we aim to develop a new AF progression risk prediction model in patients with PAF. Methods In this interim-analysis of the Reappraisal of AF: Interaction Between HyperCoagulability, Electrical Remodelling, and Vascular Destabilisation in the Progression of AF study, patients with PAF undergoing extensive phenotyping at baseline and continuous rhythm monitoring during follow-up of ≥1 year were analysed. AF progression was defined as (1) progression to persistent or permanent AF or (2) progression of PAF with >3% burden increase. Multivariable analysis was done to identify predictors of AF progression. Results Mean age was 65 (58–71) years, 179 (43%) were female. Follow-up was 2.2 (1.6–2.8) years, 51 of 417 patients (5.5%/year) showed AF progression. Multivariable analysis identified, PR interval, impaired left atrial function, mitral valve regurgitation and waist circumference to be associated with AF progression. Adding blood biomarkers improved the model (C-statistic from 0.709 to 0.830) and showed male sex, lower levels of factor XIIa:C1-esterase inhibitor and tissue factor pathway inhibitor, and higher levels of N-terminal pro-brain natriuretic peptide, proprotein convertase subtilisin/kexin type 9 and peptidoglycan recognition protein 1 were associated with AF progression. Conclusion In patients with PAF, AF progression occurred in 5.5%/year. Predictors for progression included markers for atrial remodelling, sex, mitral valve regurgitation, waist circumference and biomarkers associated with coagulation, inflammation, cardiomyocyte stretch and atherosclerosis. These prediction models may help to determine risk of AF progression and treatment targets, but validation is needed. Trial registration number NCT02726698.

Introduction: Recent studies have shown that the baseline QRS area is associated with the clinical response after cardiac resynchronization therapy (CRT). In this study, we investigated the association of QRS area reduction (∆QRS area) after CRT with the outcome. We hypothesize that a larger ∆QRS area is associated with a better survival and echocardiographic response.Methods and Results: Electrocardiograms (ECG) obtained before and 2–12 months after CRT from 1299 patients in a multi‐center CRT‐registry were analyzed. The QRS area was calculated from vectorcardiograms that were synthesized from 12‐lead ECGs. The primary endpoint was a combination of all‐cause mortality, heart transplantation, and left ventricular (LV) assist device implantation. The secondary endpoint was the echocardiographic response, defined as LV end‐systolic volume reduction ≥ of 15%. Patients with ∆QRS area above the optimal cut‐off value (62 µVs) had a lower risk of reaching the primary endpoint (hazard ratio: 0.43; confidence interval [CI] 0.33–0.56, p < .001), and a higher chance of echocardiographic response (odds ratio [OR] 3.3;CI 2.4–4.6, p < .0001). In multivariable analysis, ∆QRS area was independently associated with both endpoints. In patients with baseline QRS area ≥109 µVs, survival, and echocardiographic response were better when the ∆QRS area was ≥62 µVs (p < .0001). Logistic regression showed that in patients with baseline QRS area ≥109 µVs, ∆QRS area was the only significant predictor of survival (OR: 0.981; CI: 0.967–0.994, p = .006).Conclusion: ∆QRS area is an independent determinant of CRT response, especially in patients with a large baseline QRS area. Failure to achieve a large QRS area reduction with CRT is associated with a poor clinical outcome.