Daily Cardiology Research Analysis
Analyzed 31 papers and selected 3 impactful papers.
Summary
Analyzed 31 papers and selected 3 impactful articles.
Selected Articles
1. Extracellular volume fraction associates with long-term outcome in patients with severe symptomatic aortic stenosis: 10-year outcomes of the RELIEF-AS Study.
In a single-center prospective cohort of 168 patients with severe symptomatic aortic stenosis undergoing AVR and nearly 10 years of follow-up, higher preoperative CMR extracellular volume fraction independently predicted all-cause mortality alongside age and atrial fibrillation. Late gadolinium enhancement was greater in those who died, but ECV% remained an independent prognostic marker. Findings support incorporating ECV% into baseline risk stratification.
Impact: This is the longest follow-up study linking CMR-derived diffuse fibrosis to mortality in severe AS after AVR, strengthening the prognostic role of ECV% beyond conventional markers.
Clinical Implications: Preoperative CMR T1 mapping with ECV% could refine risk stratification in severe AS candidates for AVR and identify patients needing intensified perioperative management and follow-up.
Key Findings
- Patients who died had higher ECV% (29.9% vs 27.6%, p=0.014).
- On multivariable analysis, age, atrial fibrillation, and ECV% independently predicted all-cause mortality.
- Late gadolinium enhancement was greater in deaths (3.9% vs 2.0%, p=0.013), but ECV% retained independent prognostic value.
Methodological Strengths
- Prospective cohort with long-term (median ~10 years) follow-up and hard endpoint ascertainment via a national database.
- Comprehensive phenotyping including CMR T1 mapping (ECV%), echocardiography, and cardiac biomarkers with multivariable modeling.
Limitations
- Single-center study with a moderate sample size, potentially limiting generalizability.
- Observational design limits causal inference; cohort restricted to severe symptomatic AS undergoing AVR.
Future Directions: Multicenter validation of ECV%-based risk models and interventional studies testing ECV-guided management pathways in AS should be pursued.
AIMS: Diffuse fibrosis is central to the pathophysiology of aortic stenosis (AS), can be assessed using cardiovascular magnetic resonance (CMR) with extracellular volume fraction (ECV%), and associates with mortality. The relevance of this signal to long-term prognosis remains unclear. We aim to assess predictors of long-term mortality with focus on diffuse fibrosis. METHODS AND RESULTS: Single-centre prospective observational cohort study of patients with severe, symptomatic AS undergoing AVR. Patients were assessed using echocardiography, high-sensitivity cardiac troponin T (hs-cTnT), N-terminal pro-B type natriuretic peptide (NT-proBNP) and CMR including T1 mapping for ECV% quantification. All-cause mortality was identified using the NHS National Spine Database. Univariable and multivariable Cox regression models were fitted to assess all-cause mortality associations. 168 patients (age 72 [65-77] years, 55% male) underwent CMR. Over a follow-up period of 9.7 (6.8-10.9) years, 76 deaths occurred. Patients who died had higher ECV% (29.9% vs 27.6%, p=0.014) and greater LGE (3.9% vs 2.0%, p=0.013). Univariable predictors of mortality were age, atrial fibrillation (AF), left atrial area, left atrial volume, total cholesterol, triglycerides, HDL:LDL ratio, non-bicuspid aortic valve, hs-cTnT, NT-proBNP, EuroSCORE II and ECV%. On multivariable regression, age, AF and ECV% remained significant predictors of mortality, independently of sex. AIC indicated that the model with four covariates was preferable to the one also including EuroSCORE II and coronary artery disease, and this result was confirmed by a likelihood ratio test (p=0.387). CONCLUSIONS: In the longest follow-up cohort of T1 mapping in severe AS, we demonstrate diffuse fibrosis remains an independent predictor of long-term mortality. Integration of ECV% in baseline risk stratification should be explored further in patients with AS undergoing AVR.
2. Multisite, External Validation of an AI-Enabled ECG Algorithm for Detection of Low Ejection Fraction.
Across 13,960 patients from four U.S. sites, an AI-enabled ECG algorithm detected low ejection fraction with AUROC 0.92, sensitivity 84.5%, specificity 83.6%, and NPV 98.4%. In an unselected population, the algorithm yielded negative results in 78% of cases, supporting a rule-out strategy to defer echocardiography when other findings are absent.
Impact: This rigorous, multisite external validation demonstrates regulatory-grade diagnostic performance and real-world scalability of ECG-AI for heart failure screening.
Clinical Implications: ECG-AI can serve as a high-NPV rule-out test to prioritize echocardiography and allocate resources efficiently, pending prospective impact and cost-effectiveness evaluations.
Key Findings
- Diagnostic performance: AUROC 0.92, sensitivity 84.5%, specificity 83.6%.
- Predictive values at 7.9% prevalence: PPV 30.5% and NPV 98.4%.
- 78% of cases were test-negative, supporting use as a rule-out strategy to defer echocardiography in low-suspicion settings.
Methodological Strengths
- Geographically diverse, multisite external validation with standardized data extraction and clear reference standard within 30 days.
- Evaluation of a complete software as a medical device, enhancing reproducibility and translational relevance.
Limitations
- Retrospective data extraction may introduce selection and spectrum biases; temporal gap up to 30 days between ECG and echocardiography.
- Positive predictive value is modest due to low prevalence; prospective implementation and outcomes studies are needed.
Future Directions: Prospective, pragmatic trials to assess clinical impact, workflow integration, subgroup fairness, and cost-effectiveness of ECG-AI–guided screening are warranted.
BACKGROUND: Low left ventricular ejection fraction (LEF) can progress undiagnosed. Artificial intelligence-based electrocardiogram (ECG-AI) screening may provide a scalable means to detect LEF. OBJECTIVES: The purpose of this study was to validate a complete ECG-AI software as a medical device for LEF detection. METHODS: Four geographically diverse sites in the United States identified patients with both ECGs and transthoracic echocardiograms performed within 30 days of each other in clinical practice. Data were electronically extracted to specific guidelines and transmitted to the coordinating center for analysis. RESULTS: Records of 16,000 subjects were extracted, resulting in an evaluable set of 13,960 subjects (mean age 66 years; 52% male). The device demonstrated excellent discrimination (AUROC: 0.92 [95% CI: 0.91-0.93]) and was 84.5% (95% CI: 82.2%-86.6%) sensitive and 83.6% (95% CI: 82.9%-84.2%) specific for LEF. The overall prevalence of LEF in the study data set was 7.9%, with LEF among 1.6% of the ECG-AI negative and 30.5% of ECG-AI positive subjects, contributing to positive and negative predictive values of 30.5% (95% CI: 28.8%-32.1%) and 98.4% (95% CI: 98.2%-98.7%), respectively. CONCLUSIONS: External validation studies such as this one provide a rigorous framework to validate an algorithm's performance. This study demonstrated the algorithm's strong diagnostic accuracy over a geographically diverse, independent set of patients. In this generally unselected population, the algorithm produced a test negative result in 78% of the cases, suggesting potential utility as a rule-out strategy to defer echocardiography when other clinical findings are absent.
3. Wearable device derived electrocardiographic age and its association with atrial fibrillation.
An AI model estimating ECG age from wearable single-lead signals achieved mean absolute errors of about 10–12 years across two registered wearable cohorts. Each 1-year increase in the ECG-age gap was associated with higher odds of AF and a 0.8 percentage point increase in AF burden, supporting ECG age as a digital biomarker for proactive monitoring.
Impact: This work bridges clinical-grade ECG datasets to consumer wearables using generative domain translation and validates a scalable AF risk biomarker in real-world self-monitoring settings.
Clinical Implications: ECG-age gap could inform AF screening intensity and remote monitoring strategies; however, prospective studies are needed to define thresholds and clinical actions.
Key Findings
- Mean absolute errors for ECG-age estimation were 10.01 and 11.88 years in two independent wearable cohorts.
- The ECG-age gap was associated with AF presence (OR 1.03 per 1-year gap).
- Each 1-year increase in ECG-age gap corresponded to a 0.8 percentage point rise in AF burden.
Methodological Strengths
- Training on 1 million clinical 12-lead ECGs with CycleGAN-based domain translation to wearable single-lead signals.
- Independent external validation across two registered wearable cohorts with consistent associations.
Limitations
- Validation cohort sample sizes are not specified in the abstract; potential selection bias in self-monitoring users.
- Associational design with relatively large MAE; actionable thresholds and clinical utility require prospective evaluation.
Future Directions: Prospective trials to evaluate threshold-based decision rules, clinical impact on AF detection and outcomes, and fairness across demographic and device subgroups.
Artificial intelligence (AI)-derived electrocardiographic (ECG) age is a promising marker of atrial fibrillation (AF) risk. We developed PROPHECG-Age Single-an AI model estimating ECG age from wearable single-lead ECGs-and examined whether the ECG-age gap (predicted minus chronological age) is associated with AF presence and burden in real-world self-monitoring context. One million 12-lead ECGs from a hospital were converted to synthetic single-lead signals via Cycle-Consistent Generative Adversarial Network and used to train a residual network-based model. Validation in two independent wearable cohorts (S-Patch [ClinicalTrials.gov: NCT05119725, registered November 2021]; Memo Patch [ClinicalTrials.gov: NCT05355948, registered May 2022]) showed mean absolute errors of 10.01 and 11.88 years, respectively. The pooled association with AF presence was significant (odds ratio 1.03 per 1-year gap), and for AF burden, each 1-year gap increase corresponded to a 0.8 percentage point rise. These findings support wearable-based AI-ECG age as a potential digital biomarker for proactive cardiovascular monitoring.