Aug 2026· Circulation: Heart Failure· pp.
e014177
· 0 citations· 6 references
Medicine
TL;DR
In this single-center exploratory cohort of patients with obstructive hypertrophic cardiomyopathy receiving mavacamten, ECG-Vision left ventricular demonstrated high observed sensitivity and negative predictive value for TTE-defined LVSD, although estimates were imprecise because LVSD events were infrequent.
Abstract
Background
Frequent transthoracic echocardiograms (TTEs) are required to monitor for left ventricular systolic dysfunction (LVSD) in patients with obstructive hypertrophic cardiomyopathy receiving myosin inhibitors. This requirement may be cumbersome and limit access in underserved and rural areas. The objective of this study was to evaluate the performance of an artificial intelligence (AI)-enabled ECG tool in predicting LVSD in hypertrophic cardiomyopathy patients on mavacamten.
Methods
At Morristown Medical Center/Atlantic Health, 147 patients initiated on mavacamten between June 2022 and June 2025 underwent ECGs and TTEs at baseline and clinically available follow-up visits. A validated AI-enabled ECG algorithm predicted the probability of LVSD. Sensitivity, specificity, negative predictive value, positive predictive value, and area under the curve were calculated for left ventricular ejection fraction <50%, with CIs accounting for repeated paired ECG-TTE observations within patients.
Results
In 147 patients, mean age was 65±14 years; 44% were male. Among 453 paired ECG-TTE observations, 8 LVSD event observations occurred. At an AI probability threshold of 20%, sensitivity was 100% (95% CI, 68%-100%), specificity was 75% (95% CI, 69%-82%), positive predictive value was 7% (95% CI, 3%-11%), and negative predictive value was 100% (95% CI, 99%-100%). The area under the curve was 0.94 (95% CI, 0.90-0.98). Patient-level classifications between AI-enabled ECG and echo-confirmed LVSD were concordant in 127 of 147 patients (86%), inconclusive in 17 of 147 (12%), and discordant in 3 of 147 (2%).
Conclusions
In this single-center exploratory cohort of patients with obstructive hypertrophic cardiomyopathy receiving mavacamten, ECG-Vision left ventricular demonstrated high observed sensitivity and negative predictive value for TTE-defined LVSD, although estimates were imprecise because LVSD events were infrequent. These findings support prospective multicenter validation of AI-enabled ECG as a potential adjunctive triage tool.
The AI-ECG model accurately identified LVSD in ED patients in this cohort despite heterogeneous acquisition conditions and retained good discrimination in hemodynamically unstable subgroups, although findings in the smaller hypotensive subgroup should be interpreted as exploratory.
Background: Electrocardiographic (ECG) criteria for detecting left ventricular hypertrophy (LVH) have largely been derived from non-African populations. Their diagnostic performance in Black African adults with untreated hypertension remains uncertain. Objective: To evaluate the diagnostic performance of established ECG-LVH criteria compared with echocardiographically assessed left ventricular mass index (LVMI) in Black African adults with untreated, uncomplicated hypertension enrolled in the coArtHA trial. Methods: In this subanalysis, we included 1,125 participants from rural Tanzania and Lesotho who underwent baseline 12-lead ECG and focused transthoracic echocardiography (fTTE). LVH was defined as LVMI > 95 g/m² in women, and >115 g/m² in men. Diagnostic performance of multiple ECG-LVH criteria was assessed using correlation analyses, sensitivity and specificity estimates, receiver-operating characteristic (ROC) analysis, including calculation of the area under the ROC curve (AUROC), and precision-recall curves (PRC). Results: Echocardiographic LVH was present in 56 (5%) participants. Across continuous ECG indices, Cornell voltage product adjusted by +0.8 mV in women showed the strongest association with LVMI (Spearman’s rho = 0.37, p < 0.001). Among evaluated criteria, Cornell voltage product-based measures demonstrated the most consistent diagnostic performance across evaluated metrics, with an AUROC of approximately 0.76. Using established cut-off values, this criterion yielded a sensitivity of 64% and a specificity of 80%, whereas voltage-only criteria, including Multi-Ethnic Study of Atherosclerosis (MESA)- and Sokolow–Lyon-based indices, showed limited accuracy in this setting. Exploratory analyses of alternative cut-off values demonstrated the expected sensitivity–specificity trade-offs. Conclusions: In this cohort of hypertensive Black African adults, ECG criteria showed a moderate association with LVMI by echocardiography. Among established ECG criteria, Cornell voltage product-based measures demonstrated the most consistent diagnostic performance. Diagnostic characteristics were strongly influenced by cut-off selection and clinical context, underscoring the need for population-specific evaluation and external validation of ECG criteria for LVH in African settings. Trial registration: Clinicaltrials.gov NCT04129840. Registered on October 17, 2019 (https://www.clinicaltrials.gov/).
A. Vischer, V. Nemtsova, Blaise Lukau et al.· Global Heart· 0 citations
Reduced left ventricular ejection fraction (LVEF) is frequently asymptomatic and often detected only after advanced heart failure develops. Electrocardiograms are recorded routinely yet underused for this condition, because reduced LVEF has no single diagnostic waveform. We trained an ensemble of vision transformers from scratch to detect reduced LVEF ($\leq$40%) from 12-lead ECGs, analyzing each heartbeat individually, using 10,142 patients across seven sites in three US health systems. In a held-out external cohort of 4,092 patients from three geographically independent US clinical sites at a real-world reduced-LVEF prevalence of 8.72%, the model achieved an AUROC of 0.88 (95% CI 0.86-0.89), sensitivity 81.2%, specificity 81.0%, and negative predictive value 97.8%. Sensitivity remained high across sex, race, ethnicity, and comorbidity subgroups, while specificity was lower in older patients and those with atrial fibrillation or cardiomyopathy. Beat-level attention maps provided interpretability into the model's predictions, showing consistent focus on the QRS complex rather than the P wave. These findings support the potential of routine ECGs as a scalable first-pass triage step to identify patients who should undergo echocardiography for reduced ejection fraction across diverse patient populations.
B. Ozek, A. Mohan, D. Vorchheimer et al.· 0 citations
Mavacamten is a cardiac myosin inhibitor used in adults with symptomatic obstructive hypertrophic cardiomyopathy (HCM). Echocardiography is central to selecting suitable patients, confirming left ventricular outflow tract (LVOT) obstruction, excluding inappropriate use when left ventricular ejection fraction (LVEF) is < 55% and guiding dose titration during treatment. This narrative review summarises the practical echocardiographic approach to mavacamten therapy, with emphasis on reproducible LVOT gradient assessment, goal‐directed Valsalva manoeuvres, LVEF monitoring, mitral valve and systolic anterior motion assessment, mitral regurgitation, diastolic function and left atrial size. Current regulatory monitoring requires echocardiographic assessment during early titration and permits 6‐monthly maintenance surveillance only in stable patients meeting defined criteria, including LVEF ≥ 55% and Valsalva LVOT gradient < 30 mmHg, or a decision not to uptitrate. The review also discusses unresolved issues, including exercise echocardiography, global longitudinal strain, atrial fibrillation, reverse remodelling, implementation variability and the broader emergence of cardiac myosin inhibitors such as aficamten. Standardised acquisition and reporting are essential to ensure that treatment decisions reflect true physiological response rather than technical variability.
Alı Nızam, I. Antoun, Liz Hodson et al.· Cardiology Research and Prac...· 0 citations
Adding AI-ECG signals to PREVENT-HF improves near-term heart-failure risk discrimination and reclassification, though without demonstrated benefit on clinical outcomes such as heart-failure hospitalization or mortality.
A. Bollmann, V. Pradler, D. Husser et al.· Frontiers in Cardiovascular...· 0 citations
Given its high sensitivity in evaluating left ventricular systolic function in patients with HCM, EF1 represents a promising adjunctive parameter for the multimodal assessment of systolic function in this population.
