Electrocardiogram-based deep learning improves outcome prediction following cardiac resynchronization therapy.

AIMS: 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 QRSAREA. METHODS AND RESULTS: 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 QRSAREA 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 QRSAREA (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). CONCLUSION: Requiring only a standard 12-lead ECG, FactorECG held superior discriminative ability for the prediction of clinical outcome when compared with guideline criteria and QRSAREA, 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.

Comparison of the relation of the ESC 2021 and ESC 2013 definitions of left bundle branch block with clinical and echocardiographic outcome in cardiac resynchronization therapy.

INTRODUCTION: We aimed to investigate the impact of the 2021 European Society of Cardiology (ESC) guideline changes in left bundle branch block (LBBB) definition on cardiac resynchronization therapy (CRT) patient selection and outcomes. METHODS: The MUG (Maastricht, Utrecht, Groningen) registry, consisting of consecutive patients implanted with a CRT device between 2001 and 2015 was studied. For this study, patients with baseline sinus rhythm and QRS duration ≥ 130ms were eligible. Patients were classified according to ESC 2013 and 2021 guideline LBBB definitions and QRS duration. Endpoints were heart transplantation, LVAD implantation or mortality (HTx/LVAD/mortality) and echocardiographic response (LVESV reduction ≥15%). RESULTS: The analyses included 1.202, typical CRT patients. The ESC 2021 definition resulted in considerably less LBBB diagnoses compared to the 2013 definition (31.6% vs. 80.9%, respectively). Applying the 2013 definition resulted in significant separation of the Kaplan-Meier curves of HTx/LVAD/mortality (p < .0001). A significantly higher echocardiographic response rate was found in the LBBB compared to the non-LBBB group using the 2013 definition. These differences in HTx/LVAD/mortality and echocardiographic response were not found when applying the 2021 definition. CONCLUSION: The ESC 2021 LBBB definition leads to a considerably lower percentage of patients with baseline LBBB then the ESC 2013 definition. This does not lead to better differentiation of CRT responders, nor does this lead to a stronger association with clinical outcomes after CRT. In fact, stratification according to the 2021 definition is not associated with a difference in clinical or echocardiographic outcome, implying that the guideline changes may negatively influence CRT implantation practice with a weakened recommendation in patients that will benefit from CRT.

Association of vectorcardiographic T-wave area with clinical and echocardiographic outcomes in cardiac resynchronization therapy.

AIMS: Data on repolarization parameters in cardiac resynchronization therapy (CRT) are scarce. We investigated the association of baseline T-wave area, with both clinical and echocardiographic outcomes of CRT in a large, multi-centre cohort of CRT recipients. Also, we evaluated the association between the baseline T-wave area and QRS area. METHODS AND RESULTS: In this retrospective study, 1355 consecutive CRT recipients were evaluated. Pre-implantation T-wave and QRS area were calculated from vectorcardiograms. Echocardiographic response was defined as a reduction of ≥15% in left ventricular end-systolic volume between 3 and 12 months after implantation. The clinical outcome was a combination of all-cause mortality, heart transplantation, and left ventricular assist device implantation. Left ventricular end-systolic volume reduction was largest in patients with QRS area ≥ 109 µVs and T-wave area ≥ 66 µVs compared with QRS area ≥ 109 µVs and T-wave area < 66 µVs (P = 0.004), QRS area < 109 µVs and T-wave area ≥ 66 µVs (P < 0.001) and QRS area < 109 µVs and T-wave area < 66 µVs (P < 0.001). Event-free survival rate was higher in the subgroup of patients with QRS area ≥ 109 µVs and T-wave area ≥ 66 µVs (n = 616, P < 0.001) and QRS area ≥ 109 µVs and T-wave area < 66 µVs (n = 100, P < 0.001) than the other subgroups. In the multivariate analysis, T-wave area remained associated with echocardiographic response (P = 0.008), but not with the clinical outcome (P = 0.143), when QRS area was included in the model. CONCLUSION: Baseline T-wave area has a significant association with both clinical and echocardiographic outcomes after CRT. The association of T-wave area with echocardiographic response is independent from QRS area; the association with clinical outcome, however, is not.

Non-invasive three-dimensional electrical activation mapping to predict cardiac resynchronization therapy response: site of latest left ventricular activation relative to pacing site.

AIMS: Pacing remote from the latest electrically activated site (LEAS) in the left ventricle (LV) may diminish response to cardiac resynchronization therapy (CRT). We tested whether proximity of LV pacing site (LVPS) to LEAS, determined by non-invasive three-dimensional electrical activation mapping [electrocardiographic Imaging (ECGI)], increased likelihood of CRT response. METHODS AND RESULTS: Consecutive CRT patients underwent ECGI and chest/heart computed tomography 6-24 months of post-implant. Latest electrically activated site and the distance to LVPS (dp) were assessed. Left ventricular end-systolic volume (LVESV) reduction of ≥15% at clinical follow-up defined response. Logistic regression probabilistically modelled non-response; variables included demographics, heart failure classification, left bundle branch block (LBBB), ischaemic heart disease (IHD), atrial fibrillation, QRS duration, baseline ejection fraction (EF) and LVESV, comorbidities, use of CRT optimization algorithm, angiotensin-converting enzyme inhibitor(ACE)/angiotensin-receptor blocker (ARB), beta-blocker, diuretics, and dp. Of 111 studied patients [64 ± 11 years, EF 28 ± 6%, implant duration 12 ± 5 months (mean ± SD), 98% had LBBB, 38% IHD], 67% responded at 10 ± 3 months post CRT-implant. Latest electrically activated sites were outside the mid-to-basal lateral segments in 35% of the patients. dp was 42 ± 23 mm [31 ± 14 mm for responders vs. 63 ± 24 mm non-responders (P < 0.001)]. Longer dp and the lack of use of CRT optimization algorithm were the only independent predictors of non-response [area under the curve (AUC) 0.906]. dp of 47 mm delineated responders and non-responders (AUC 0.931). CONCLUSION: The distance between LV pacing site and latest electrical activation is a strong independent predictor for CRT response. Non-invasive electrical evaluation to characterize intrinsic activation and guide LV lead deployment may improve CRT efficacy.

Reduction in the QRS area after cardiac resynchronization therapy is associated with survival and echocardiographic response.

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.

Prognostic implications of invasive hemodynamics during cardiac resynchronization therapy: Stroke work outperforms dP/dtmax.

Background: Invasive measurements of left ventricular (LV) hemodynamic performance can evaluate acute response to cardiac resynchronization therapy (CRT). Objective: The study sought to determine which metric, maximum rate of LV pressure rise (LV dP/dtmax) or LV stroke work (LVSW), is more strongly associated with long-term prognosis. Methods: CRT patients were prospectively included from 3 academic centers. Invasive pressure-volume loop measurements during implantation were performed, and LV dP/dtmax and LVSW were determined at baseline and during biventricular pacing (BVP) as well as their relative increase (%Δ). Hazard ratios (HRs) for the primary outcome of 8-year all-cause mortality were derived using Cox proportional hazards. The secondary endpoint was echocardiographic response, defined as 6-month LV end-systolic volume reduction ≥15%. Results: Paired data from 82 patients were analyzed (67% male; age 66 ± 9 years; QRS duration 158 ± 22 ms, median survival time 72 months). Survival was better when LVSW during BVP was ≥4400 mL∙mm Hg (HR 0.21, 95% CI 0.08-0.58, P < .003) or when ΔLVSW% was ≥10% (HR 0.22, 95% CI 0.08-0.65, P = .006). In multivariate analysis, following direct comparison of continuous measures of acute ΔLV dP/dtmax% and ΔLVSW%, only ΔLVSW% remained associated with the primary endpoint (HR 0.982 per percentage point, P = .028). In contrast to LV dP/dtmax (all P > .05), significant associations with echocardiographic response were found for stroke work during BVP (area under the receiver-operating characteristic curve 0.745, P = .001) and ΔLVSW% (area under the receiver-operating characteristic curve 0.803, P < .001). Conclusion: Stroke work, but not LV dP/dtmax, is consistently associated with long-term prognosis and response after CRT. Our results therefore favor the use of stroke work as the hemodynamic parameter to predict long-term outcome after CRT.

Vectorcardiographic QRS area as a predictor of response to cardiac resynchronization therapy.

Cardiac resynchronization therapy (CRT) is a good treatment for heart failure accompanied by ventricular conduction abnormalities. Current ECG criteria in international guidelines seem to be suboptimal to select heart failure patients for CRT. The criteria QRS duration and left bundle branch block (LBBB) QRS morphology insufficiently detect left ventricular activation delay, which is required for benefit from CRT. Additionally, there are various definitions for LBBB, in which each one has a different association with CRT benefit and is prone to subjective interpretation. Recent studies have shown that the objectively measured vectorcardiographic QRS area identifies left ventricular activation delay with higher accuracy than any of the current ECG criteria. Indeed, various studies have consistently shown that a high QRS area prior to CRT predicts both echocardiographic and clinical improvement after CRT. The beneficial relation of QRS area with CRT-outcome was largely independent from QRS morphology, QRS duration, and patient characteristics known to affect CRT-outcome including ischemic etiology and sex. On top of QRS area prior to CRT, the reduction in QRS area after CRT further improves benefit. QRS area is easily obtainable from a standard 12-lead ECG though it currently requires off-line analysis. Clinical applicability will be significantly improved when QRS area is automatically determined by ECG equipment.

Cardiovascular outcome 6 months after severe coronavirus disease 2019 infection.

OBJECTIVES: In coronavirus disease 2019 (COVID-19), cardiovascular risk factors and myocardial injury relate to increased mortality. We evaluated the extent of cardiac sequelae 6 months after hospital discharge in patients surviving ICU hospitalization for COVID-19. METHODS: All survivors of Maastricht-ICU were invited for comprehensive cardiovascular evaluation 6 months after discharge from ICU. Cardiac screening included an electrocardiogram, cardiac biomarkers, echocardiography, cardiac magnetic resonance (CMR) and, wherever indicated, cardiac computed tomography or coronary angiogram. RESULTS: Out of 52 survivors, 81% ( n  = 42) participated to the cardiovascular follow-up [median follow-up of 6 months, interquartile range (IQR) 6.1-6.7]. Eight patients (19%) had newly diagnosed coronary artery disease (CAD), of which two required a percutaneous intervention. Echocardiographic global longitudinal strain (GLS) was abnormal in 24% and CMR-derived GLS was abnormal in 12%, despite normal left ventricular ejection fraction in all. None of the patients showed elevated T 1 relaxation times and five patients (14%) had an elevated T 2 relaxation time. Late gadolinium enhancement (LGE) reflecting regional myocardial fibrosis was increased in eight patients (21%), of which three had myocarditis and three had pericarditis. CONCLUSION: Cardiovascular follow-up at 6 months after ICU-admission for severe COVID-19 revealed that one out of five invasively mechanically ventilated survivors had CAD, a quarter had subclinical left ventricular dysfunction defined as reduced echocardiographic GLS, and 42% of the patients had CMR abnormalities (reduced LVEF, reduced GLS, LGE presence, and elevated T 2 ). On the basis of these findings, long-term cardiovascular follow-up is strongly recommended in all post-IC COVID-19 patients. CLINICAL TRIAL REGISTRATION: Trial Register number [NL8613]) https://www.trialregister.nl/trial/8613Video abstract:http://links.lww.com/HJH/B899 .

Serial Assessment of Myocardial Injury Markers in Mechanically Ventilated Patients With SARS-CoV-2 (from the Prospective MaastrICCht Cohort).

Myocardial injury in COVID-19 is associated with in-hospital mortality. However, the development of myocardial injury over time and whether myocardial injury in patients with COVID-19 at the intensive care unit is associated with outcome is unclear. This study prospectively investigates myocardial injury with serial measurements over the full course of intensive care unit admission in mechanically ventilated patients with COVID-19. As part of the prospective Maastricht Intensive Care COVID cohort, predefined myocardial injury markers, including high-sensitivity cardiac troponin T (hs-cTnT), N-terminal pro-B-type natriuretic peptide (NT-proBNP), and electrocardiographic characteristics were serially collected in mechanically ventilated patients with COVID-19. Linear mixed-effects regression was used to compare survivors with nonsurvivors, adjusting for gender, age, APACHE-II score, daily creatinine concentration, hypertension, diabetes mellitus, and obesity. In 90 patients, 57 (63%) were survivors and 33 (37%) nonsurvivors, and a total of 628 serial electrocardiograms, 1,565 hs-cTnT, and 1,559 NT-proBNP concentrations were assessed. Log-hs-cTnT was lower in survivors compared with nonsurvivors at day 1 (ß -0.93 [-1.37; -0.49], p <0.001) and did not change over time. Log-NT-proBNP did not differ at day 1 between both groups but decreased over time in the survivor group (ß -0.08 [-0.11; -0.04] p <0.001) compared with nonsurvivors. Many electrocardiographic abnormalities were present in the whole population, without significant differences between both groups. In conclusion, baseline hs-cTnT and change in NT-proBNP were strongly associated with mortality. Two-thirds of patients with COVID-19 showed electrocardiographic abnormalities. Our serial assessment suggests that myocardial injury is common in mechanically ventilated patients with COVID-19 and is associated with outcome.

Left Ventricular Lead Placement Guided by Reduction in QRS Area.

Background: Reduction in QRS area after cardiac resynchronization therapy (CRT) is associated with improved long-term clinical outcome. The aim of this study was to investigate whether the reduction in QRS area is associated with hemodynamic improvement by pacing different LV sites and can be used to guide LV lead placement. Methods: Patients with a class Ia/IIa CRT indication were prospectively included from three hospitals. Acute hemodynamic response was assessed as the relative change in maximum rate of rise of left ventricular (LV) pressure (%∆LVdP/dtmax). Change in QRS area (∆QRS area), in QRS duration (∆QRS duration), and %∆LVdP/dtmax were studied in relation to different LV pacing locations within a patient. Results: Data from 52 patients paced at 188 different LV pacing sites were investigated. Lateral LV pacing resulted in a larger %∆LVdP/dtmax than anterior or posterior pacing (p = 0.0007). A similar trend was found for ∆QRS area (p = 0.001) but not for ∆QRS duration (p = 0.23). Pacing from the proximal electrode pair resulted in a larger %∆LVdP/dtmax (p = 0.004), and ∆QRS area (p = 0.003) but not ∆QRS duration (p = 0.77). Within patients, correlation between ∆QRS area and %∆LVdP/dtmax was 0.76 (median, IQR 0.35; 0,89). Conclusion: Within patients, ∆QRS area is associated with %∆LVdP/dtmax at different LV pacing locations. Therefore, QRS area, which is an easily, noninvasively obtainable and objective parameter, may be useful to guide LV lead placement in CRT.