Evaluation of the <scp>ECG</scp> based Selvester scoring method to estimate myocardial scar burden and predict clinical outcome in patients with left bundle branch block, with comparison to late gadolinium enhancement <scp>CMR</scp> imaging

Chaudhry, Uzma; Platonov, Pyotr G.; Jablonowski, Robert; Couderc, Jean‐Philippe; Engblom, Henrik; Xia, Xiajuang; Wieslander, Björn; Atwater, Brett D.; Strauss, David G.; Pals, Jesper van der; Carlsson, Marcus; Borgquist, Rasmus

doi:10.1111/anec.12440

Cited by 7 publications

(5 citation statements)

References 29 publications

(35 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Comparing our results with that of the other methods listed in Table 2, it must be taken into account that the underlying cohorts differ in size, structure and time of study. Considering the larger training sets used by Goovaerts et al (2019) and by Dima et al (2013) and the limited number of cases used by Chaudhry et al (2017) and Bignoto et al (2018), our results are similar. For a more substantiated comparison, the methods would have to be applied to the identical data, see Bengio and Grandvalet (2004).…”

Section: Model Performancesupporting

confidence: 62%

Detecting myocardial scar using electrocardiogram data and deep neural networks

Gumpfer

Grün

Hannig

et al. 2020

Biological Chemistry

View full text Add to dashboard Cite

Ischaemic heart disease is among the most frequent causes of death. Early detection of myocardial pathologies can increase the benefit of therapy and reduce the number of lethal cases. Presence of myocardial scar is an indicator for developing ischaemic heart disease and can be detected with high diagnostic precision by magnetic resonance imaging. However, magnetic resonance imaging scanners are expensive and of limited availability. It is known that presence of myocardial scar has an impact on the well-established, reasonably low cost, and almost ubiquitously available electrocardiogram. However, this impact is non-specific and often hard to detect by a physician. We present an artificial intelligence based approach — namely a deep learning model — for the prediction of myocardial scar based on an electrocardiogram and additional clinical parameters. The model was trained and evaluated by applying 6-fold cross-validation to a dataset of 12-lead electrocardiogram time series together with clinical parameters. The proposed model for predicting the presence of scar tissue achieved an area under the curve score, sensitivity, specificity, and accuracy of 0.89, 70.0, 84.3, and 78.0%, respectively. This promisingly high diagnostic precision of our electrocardiogram-based deep learning models for myocardial scar detection may support a novel, comprehensible screening method.

show abstract

Section: Model Performancesupporting

confidence: 62%

Detecting myocardial scar using electrocardiogram data and deep neural networks

Gumpfer

Grün

Hannig

et al. 2020

Biological Chemistry

View full text Add to dashboard Cite

show abstract

“…Therefore, the question about the predisposing factors of this conduction abnormality (function abnormality) is still on the table. A published article conducted in 2017, focused on cardiac MRI and scar burden in LBBB patients to predict their future outcome (16).…”

Section: Discussionmentioning

confidence: 99%

Does Isolated Left Bundle Block Cause Heart Failure With Reduced Ejection Fraction? A Retrospective Cohort Study

Amirzadegan

Hosseini

Tajdini

et al. 2017

Thrita

View full text Add to dashboard Cite

Background: Left bundle branch block (LBBB) is an important and independent determinant of mortality among patients with cardiovascular disease (CVD). Close follow-up and management of isolated LBBB to prevent cardiomyopathy is controversial. Methods: In this retrospective cohort study, patients with isolated LBBB, with no concomitant evident cardiac disease, or risk factors of heart failure with reduced EF such as hypertension or diabetes mellitus (DM) were included. The mean follow-up of the patients was 56 months. At the onset of the study, coronary angiogram and EF of the patients were normal. Patients with reduced EF underwent coronary angiogram at the end of their follow-up interval. Results: In this study, 36 patients, with the mean age 62.1 years (45-81) were followed. LV ejection fraction (EF) was reduced in 24 patients, and the other 11 patients continued to have a normal EF during the follow-up. The follow-up interval between the 2 groups was not statistically different (Mann-Whitney, P = 0.9). Most of the patients with reduced EF were male (Mann-Whitney, P = 0.01). New-onset HTN had a negative correlation with a decrease in EF% (Spearman correlation coefficient =-0.36, P = 0.031). Based on surface ECG parameters, 8 new notched-QRS were detected, all of which had decreased EF during follow-up. Conclusions: Not all patients with isolated LBBB develop cardiomyopathy at a definite time interval. Male gender, notched-QRS in ECG, and longevity of conduction delay are important predictors of cardiomyopathy among these patients. They may benefit from anti-remodeling drugs and routine close follow-ups with echocardiogram.

show abstract

“…CMR was performed as previously described by Chaudhry et al [23]. In short, LVEF was determined by cine imaging in breath hold with semiautomatic tracing of the endocardium in both short-axis and long-axis projections.…”

Section: Methodsmentioning

confidence: 99%

Vectorcardiography Findings Are Associated with Recurrent Ventricular Arrhythmias and Mortality in Patients with Heart Failure Treated with Implantable Cardioverter-Defibrillator Device

et al. 2020

Self Cite

View full text Add to dashboard Cite

Background: There is a need for refined risk stratification of sudden cardiac death and prediction of ventricular arrhythmias to correctly identify patients who are expected to benefit the most from implantable cardioverter-defibrillator (ICD) therapy. Methods: We conducted a registry-based retrospective observational study on patients with either ischemic (ICMP) or nonischemic dilated cardiomyopathy (NICMP) treated with ICD between 2002 and 2013 at a tertiary referral center. We evaluated 3 vectorcardiography (VCG) indices; spatial QRS-T angle, QRS vector magnitude (QRSvm), and T-wave vector magnitude (Twvm), and their association with all-cause mortality and ventricular arrhythmias. The VCG indices were automatically computed from resting 12-lead electrocardiograms before ICD implantation. Results: 178 patients were included in the study; 53.4% had ICMP, 79.2% were male, and mean ejection fraction was 27.4%. During the follow-up (median 89 months), 40 patients (23%) died; 31% had appropriate ICD therapy. In multivariate analysis with dichotomized variables, QRS-T angle >152° and Twvm <0.38 mV were significantly associated with increased mortality: HR 2.64 (95% CI 1.14–6.12, p = 0.02) and HR 5.30 (95% CI 2.31–12.11, p < 0.001), respectively. QRSvm <1.54 mV was borderline significant with mortality outcome (p = 0.10). The composite score of all 3 VCG indices, a score of 3, conferred an increased risk of mortality (including heart failure mortality) in multivariate analysis: HR 13.80 (95% CI 3.44–55.39, p < 0.001). Conclusion: The spatial QRS-T angle and Twvm are emerging VCG indices which are independently associated with mortality in patients with reduced left ventricular ejection fraction due to ICMP or NICMP. Using a composite score of all 3 vector indices, a maximum score was associated with poor long-term survival.

show abstract

Evaluation of the ECG based Selvester scoring method to estimate myocardial scar burden and predict clinical outcome in patients with left bundle branch block, with comparison to late gadolinium enhancement CMR imaging

Cited by 7 publications

References 29 publications

Detecting myocardial scar using electrocardiogram data and deep neural networks

Detecting myocardial scar using electrocardiogram data and deep neural networks

Does Isolated Left Bundle Block Cause Heart Failure With Reduced Ejection Fraction? A Retrospective Cohort Study

Vectorcardiography Findings Are Associated with Recurrent Ventricular Arrhythmias and Mortality in Patients with Heart Failure Treated with Implantable Cardioverter-Defibrillator Device

Contact Info

Product

Resources

About