Electrocardiographic Features of Left Ventricular Diastolic Dysfunction and Heart Failure With Preserved Ejection Fraction: A Systematic Review

Artificial intelligence-enhanced six-lead portable electrocardiogram device for detecting left ventricular systolic dysfunction: a prospective single-centre cohort study

Aims

The real-world effectiveness of the artificial intelligence model based on electrocardiogram (AI-ECG) signals from portable devices for detection of left ventricular systolic dysfunction (LVSD) requires further exploration.

Methods and results

In this prospective, single-centre study, we assessed the diagnostic performance of AI-ECG for detecting LVSD using a six-lead hand-held portable device (AliveCor KardiaMobile 6L). We retrained the AI-ECG model, previously validated with 12-lead ECG, to interpret the 6-lead ECG inputs. Patients aged 19 years or older underwent six-lead ECG recording during transthoracic echocardiography. The primary outcome was the area under the receiver operating characteristic curve (AUROC) for detecting LVSD, defined as an ejection fraction below 40%. Of the 1716 patients recruited prospectively, 1635 were included for the final analysis (mean age 60.6 years, 50% male), among whom 163 had LVSD on echocardiography. The AI-ECG model based on the six-lead portable device demonstrated an AUROC of 0.924 [95% confidence interval (CI) 0.903-0.944], with 83.4% sensitivity (95% CI 77.8-89.0%) and 88.7% specificity (95% CI 87.1-90.4%). Of the 1079 patients evaluated using the AI-ECG model based on the conventional 12-lead ECG, the AUROC was 0.962 (95% CI 0.947-0.977), with 90.1% sensitivity (95% CI 85.0-95.2%) and 91.1% specificity (95% CI 89.3-92.9%).

Conclusion

The AI-ECG model constructed with the six-lead hand-held portable ECG device effectively identifies LVSD, demonstrating comparable accuracy to that of the conventional 12-lead ECG. This highlights the potential of hand-held portable ECG devices leveraged with AI as efficient tools for early LVSD screening.

The Diagnostic Value of ECG Characteristics for Vasospastic and Microvascular Angina: A Systematic Review

BACKGROUND

Coronary vascular dysfunction comprises VSA and/or MVA and is more common in women than in men with angina without obstructive coronary artery disease (ANOCA). Invasive coronary function testing is considered the reference test for diagnosis, but its burden on patients is large. We aimed to investigate the potential of electrocardiography (ECG) as noninvasive marker for vasospastic angina (VSA) and microvascular angina (MVA) diagnosis.

METHODS

We systematically screened Pubmed and EMBASE databases for studies reporting on ECG characteristics in ANOCA patients with (a suspicion of) coronary vascular dysfunction. We assessed study quality using QUADAS-2. We extracted data on diagnostic values of different ECG characteristics and analyzed whether the studies were sex-stratified.

RESULTS

Thirty publications met our criteria, 13 reported on VSA and 17 on MVA. The majority addressed repolarization-related ECG parameters. Only 1 of the 13 VSA papers and 4 of the 17 MVA papers showed diagnostic accuracy measures of the ECG characteristics. The presence of early repolarization, T-wave alternans, and inverted U waves showed of predictive value for VSA diagnosis. The QTc interval was predictive for MVA diagnosis in all six studies reporting on QTc interval. Sex-stratified results were reported in only 5 of the 30 studies and 3 of those observed sex-based differences.

CONCLUSIONS

ECG features are not widely evaluated in diagnostic studies for VSA and MVA. Those features predictive for VSA and MVA diagnosis mostly point to repolarization abnormalities and may contribute to noninvasive risk stratification.

Outcomes with T-wave discordance of left bundle branch block and preserved or mildly reduced ejection fraction

AIMS

Left bundle branch block (LBBB) is associated with an increased risk of adverse outcomes for patients with heart failure. The prognosis of LBBB in patients with a preserved ejection fraction (EF) remains controversial. This study investigated the predictive value of T-wave discordance for the prognosis of patients with LBBB and preserved or mildly reduced EF.

METHODS AND RESULTS

We enrolled 707 patients with complete LBBB and left ventricular (LV) EF ≥ 40% observed using electrocardiograms (ECGs) and echocardiograms between January 2010 and December 2018. Their serial ECGs were reviewed during the follow-up period. The T-wave pattern was classified as discordant LBBB (dLBBB) or concordant LBBB (cLBBB) according to the 12-lead ECG T-wave morphology. The primary outcome was the composite of cardiovascular death or hospitalization for heart failure during a median follow-up period of 3.1 years. A multivariable Cox regression analysis was used to evaluate the independent predictors of the primary outcome. Patients with dLBBB had more comorbidities, a higher heart rate, a longer QRS and QTc duration, a larger LV end-systolic volume and left atrial dimension, a lower LVEF, and a higher mitral E/A ratio and E/e', compared with those with cLBBB. Older age [hazard ratio (HR) = 1.023, 95% confidence interval (CI) = 1.001-1.046, P = 0.023], history of heart failure (HR = 2.440, 95% CI = 1.524-3.905, P = 0.001), chronic kidney disease (HR = 1.917, 95% CI = 1.182-3.110, P = 0.008), larger LV end-systolic volume (HR = 1.046, 95% CI = 1.017-1.075, P = 0.002), lower LVEF (HR = 0.916, 95% CI = 0.885-0.948, P = 0.001), and presence of dLBBB (HR = 1.63, 95% CI = 1.011-2.628, P = 0.032) were independent predictors of the primary outcome in patients with LBBB and LVEF ≥ 40%. The discordant or concordant T-wave morphology of LBBB could transform from one subtype to the other in up to 23% of the study population during the follow-up period, and individuals with persistent or transformed dLBBB faced an increased risk of cardiovascular death or non-fatal heart failure hospitalization.

CONCLUSIONS

In patients with LBBB and EF ≥ 40%, dLBBB serves as an independent predictor of a higher risk of cardiovascular death or non-fatal heart failure hospitalization.

Energy wavelet signal processed ECG and standard 12 lead ECG: Diagnosis of early diastolic dysfunction

BACKGROUND

Left ventricular (LV) diastolic dysfunction (LVDD) is the result of impaired LV relaxation and identifies those at risk of developing heart failure. Echocardiography has been used as the gold standard to identify early LVDD. The signal processed electrocardiogram (hsECG) has demonstrated effectiveness to detect early LVDD. Whether or not the standard 12‑lead electrocardiogram (ECG) can accurately predict early LVDD is not known.

METHODS

A standard 12‑lead ECG including signal processing (hsECG) was performed in 569 patients. Patients with atrial fibrillation, bundle branch block, pre-excitation, left ventricular hypertrophy or known cardiovascular disease were excluded, leaving 464 examinations for analysis. Early LVDD was diagnosed by established methods using echocardiography. Repolarization abnormalities (T wave discordance) in V1, V6, I and aVL and the hsECG were compared to the echocardiographic findings to establish diagnostic accuracy.

RESULTS

A total of 84 (18.1%) patients were diagnosed with early LVDD. A combination of a borderline or abnormal finding on the hsECG produced the best diagnostic model (sensitivity 84.5%, specificity 47.9%). The best performing ECG lead was V1 with a sensitivity of 38.1% and specificity of 92.1%. Regression analysis demonstrated increasing age and V1 to be predictive of LVDD.

CONCLUSIONS

The hsECG displayed reasonable ability to detect early LVDD. Other than V1, repolarization abnormalities on the standard 12‑lead ECG did not. While lead V1 showed promise in detecting LVDD, whether this or any other simple ECG variable can predict future LVDD would be of further interest.

Electrocardiographic Patterns of Depolarization Abnormalities Help to Identify Reduced Left Ventricular Ejection Fraction

The aim of the study was to investigate the relationship between a decrease in the left ventricular ejection fraction (EF) and traditional ECG signs associated with structural changes of the myocardium (pathological Q wave, ventricular arrhythmias) and relatively new and poorly understood (fragmented QRS complex (fQRS), early repolarization pattern (ERP)) and evaluate their significance for identifying patients with mildly reduced EF (mrEF). The study included 148 patients who were treated and examined at the Almazov Medical Research Center. FQRS, ERP, pathological Q wave, and premature ventricular contractions (PVC) were described in the analysis of the ECG, and the results of echocardiography and statistical data were analyzed: Fisher’s test and chi-square, correlation analysis, and ROC analysis. According to the level of EF, patients were divided into three groups: group 1—patients with low EF (lEF) (less than 40%), group 2—patients with mildly reduced EF (mrEF) (40–49%); group 3—patients with preserved EF (pEF) (more than 50%). In the first group (EF), fQRS was registered in 16 (51.6%) patients, in the mrEF in 16 (18.2%). Pathological Q wave was detected in lEF in 20 (65%), in mrEF in 10 (35%), 15 (18%), in pEF in 15 (18%). The fQRS has been found to be more important in identifying patients with mrEF. In lEF in 2 (6.5%) patients, in mrEF in 2 (6.9%), in pEF in 11 (12.5%). There was no relationship between ERP, the amount of PVC, and the presence of ventricular tachycardia with EF. FQRS is significantly more common occurred with a decrease in EF and may be a marker of a mrEF. Thus, fQRS is associated with mrEF and pay close attention in routine clinical practice to identify patients at high risk of developing systolic dysfunction.