Machine Learning of 12-Lead QRS Waveforms to Identify Cardiac Resynchronization Therapy Patients With Differential Outcomes

Abstract

Background: Cardiac resynchronization therapy (CRT) improves heart failure outcomes but has significant nonresponse rates, highlighting limitations in ECG selection criteria: QRS duration (QRSd) ≥150 ms and subjective labeling of left bundle branch block (LBBB). We explored unsupervised machine learning of ECG waveforms to identify CRT subgroups that may differentiate outcomes beyond QRSd and LBBB. Methods: We retrospectively analyzed 946 CRT patients with conduction delay. Principal component analysis (PCA) dimensionality reduction obtained a 2-dimensional representation of preCRT 12-lead QRS waveforms. k -means clustering of the 2-dimensional PCA representation of 12-lead QRS waveforms identified 2 patient subgroups (QRS PCA groups). Vectorcardiographic QRS area was also calculated. We examined following 2 primary outcomes: (1) composite end point of death, left ventricular assist device, or heart transplant, and (2) degree of echocardiographic left ventricular ejection fraction (LVEF) change after CRT. Results: Compared with QRS PCA Group 2 ( n =425), Group 1 ( n =521) had lower risk for reaching the composite end point (HR, 0.44 [95% CI, 0.38–0.53]; P <0.001) and experienced greater mean LVEF improvement (11.1±11.7% versus 4.8±9.7%; P <0.001), even among patients with LBBB with QRSd ≥150 ms (HR, 0.42 [95% CI, 0.30–0.57]; P <0.001; mean LVEF change 12.5±11.8% versus 7.3±8.1%; P =0.001). QRS area also stratified outcomes but had significant differences from QRS PCA groups. A stratification scheme combining QRS area and QRS PCA group identified patients with LBBB with similar outcomes to non-LBBB patients (HR, 1.32 [95% CI, 0.93–1.62]; difference in mean LVEF change: 0.8% [95% CI, −2.1% to 3.7%]). The stratification scheme also identified patients with LBBB with QRSd <150 ms with comparable outcomes to patients with LBBB with QRSd ≥150 ms (HR, 0.93 [95% CI, 0.67–1.29]; difference in mean LVEF change: −0.2% [95% CI, −2.7% to 3.0%]). Conclusions: Unsupervised machine learning of ECG waveforms identified CRT subgroups with relevance beyond LBBB and QRSd. This method may assist in objective classification of bundle branch block morphology in CRT.

Left Atrial Wall Stress and the Long-Term Outcome of Catheter Ablation of Atrial Fibrillation: An Artificial Intelligence-Based Prediction of Atrial Wall Stress

“…In addition, due to the different time of enrollment and follow-up duration between the development and independent cohorts, differences in catheter type, ablation lesion set, and AF recurrence between the two cohorts should be considered. However, there were previous AI-related studies analyzing results with data that have a time discrepancy of enrollment in training cohort and validation cohort (Feeny et al, 2020;Firouznia et al, 2021).…”

Tópicos Emergentes em Insuficiência Cardíaca: O Futuro na Insuficiência Cardíaca: Telemonitoramento, Wearables , Inteligência Artificial e Ensino na Era Pós-Pandemia

“…Isso pode ser feito, por exemplo, na distinção de fenótipos, alocando pacientes em diferentes perfis de assinatura de doença; 12 na melhor acurácia para o diagnóstico de IC aguda em relação ao médico; 13 e no eventual direcionamento para terapias novas ou já estabelecidas, como análise adicional do ECG basal para identificar paciente melhor respondedor à TRC. 14 …”

“…This can occur, for example, by distinguishing phenotypes, allocating patients with different disease profiles; 12 by determining the best acute HF diagnostic accuracy in relation to the doctor; 13 and by targeting new or already established therapies, such as additional analysis of baseline electrocardiograms to identify the best patients for cardiac-resynchronization therapy. 14 …”

Using deep learning algorithms to simultaneously identify right and left ventricular dysfunction from the electrocardiogram

“…Deep learning (DL), a class of machine learning that uses hierarchical networks to extract lower-dimensional features from a higher dimensional data input, has demonstrated significant potential for enabling ECG-based predictions and diagnoses 33 . For example, DL has been used to identify patients with atrial fibrillation while in normal sinus rhythm 34 , predict incident atrial fibrillation 35 , identify patients amenable to cardiac resynchronization therapy 36 , evaluate LV diastolic function 37 , evaluation of patients with echocardiographically concealed long QT syndrome 38 , predict risk of sudden cardiac death 39 , and to predict low LVEF. 40,41 .…”