Artificial intelligence-enabled electrocardiogram for left ventricular diastolic dysfunction and long-term risk of new-onset atrial fibrillation
Key result
AI-ECG-detected grade 3 LVDD linked to ~124% higher risk of new-onset AF.
- aHR 2.24
- 95% CI 2.02-2.48
- n=97,023
Why the study?
While left ventricular diastolic dysfunction is a hallmark of heart failure, whether AI-ECG-detected LVDD correlates with long-term atrial fibrillation risk remains unexplored.
Does AI-ECG-detected left ventricular diastolic dysfunction predict long-term risk of new-onset atrial fibrillation in patients without prior AF?
Key Points
- This study aims to determine the correlation between AI-ECG-detected left ventricular diastolic dysfunction and the long-term risk of new-onset atrial fibrillation.
- Performed a retrospective study on patients assessed for left ventricular diastolic dysfunction (LVDD) from September 2001 to June 2022.
- Excluded patients with prior atrial fibrillation; classified LVDD severity using AI-ECG into normal diastolic function (DF), grade 1 (G1), grade 2 (G2), or grade 3 (G3).
- Assessed atrial fibrillation risk using competing risk models over a median follow-up of 4.8 years.
- Of 97,023 patients free of AF at baseline, 7.0% developed new-onset AF during follow-up.
- G2-LVDD was associated with aHR 1.64 (95% CI 1.52-1.73) for AF risk; G3-LVDD with aHR 2.24 (95% CI 2.02-2.48).
- Higher grades of LVDD correlated with older age, lower left ventricular ejection fraction, and increased prevalence of cardiovascular conditions.
Study Design
Type
Cohort (n=97,023)
Structured PICO
Does AI-ECG-detected left ventricular diastolic dysfunction predict long-term risk of new-onset atrial fibrillation in patients without prior AF?
P
Population
97,023 patients free of atrial fibrillation at baseline with a comprehensive LVDD assessment, followed for a median of 4.8 years.
E
Exposure
Artificial intelligence-enabled electrocardiogram (AI-ECG) detection of left ventricular diastolic dysfunction (LVDD) grades 1, 2, or 3
C
Comparator
Normal diastolic function (DF) as classified by AI-ECG
O
Outcome
New-onset atrial fibrillationhard clinical
Main Result
Hazard Ratio: 2.24 (95% CI 2.02–2.48)
Key expert perspectives
Captured external expert commentary on this paper, strongest first. Original sources are linked where available.
“Our findings suggest that a routine assessment of diastolic function can provide a powerful glimpse into a person's future heart health. Each worsening grade of diastolic dysfunction was associated with a progressively higher risk when compared with normal function. These findings highlight the critical role of diastolic function beyond heart failure diagnosis, supporting earlier testing and timely interventions aimed at reducing risk.”
“AI-ECG diastolic function assessment has the similar prognostic power as an echocardiogram. Future study is needed to demonstrate how AI-ECG and echocardiograms can be integrated clinically to identify patients at a high risk of developing AFib.”
Implication
AI-ECG-detected grade 2 and 3 left ventricular diastolic dysfunction independently predicts long-term risk of new-onset atrial fibrillation, regardless of LVEF and clinical HF status.
Abstract
Background Heart failure (HF) and atrial fibrillation (AF) are intertwined, sharing common risk factors and influencing each other in a reciprocal manner. While left ventricular diastolic dysfunction (LVDD) stands as a hallmark of HF's hemodynamic profile, its direct correlation with heightened AF risk remains uncertain. Our recent validation of an artificial intelligence-enabled electrocardiogram (AI-ECG) algorithm for LVDD detection has opened new avenues. Yet, whether AI-ECG-detected LVDD correlates with long-term AF risk remains unexplored. Methods We performed a retrospective study among all patients with a comprehensive LVDD assessment from the test population of the AI-ECG LVDD study between September 2001 and June 2022. Patients with prior documented AF according to health records or previous ECG were excluded. Patients were classified by AI-ECG as normal diastolic function (DF), grade 1 (G1), grade 2 (G2), or grade 3 (G3) LVDD. We assessed the risk of AF across AI-ECG LVDD grade, with normal DF as reference, with competing risk models. Results Of 97,023 patients free of AF at baseline, 63,533 (65.4%), 10,776 (11.1%), 18,940 (19.5%), and 3,774 (3.9%) were classified as normal DF, G1-LVDD, G2-LVDD, and G3-LVDD, respectively. Worse AI-ECG LVDD was associated with older age, lower left ventricular ejection fraction (LVEF), and higher rates of HF, diabetes, hypertension, chronic pulmonary disease, renal failure, and cardiovascular disease (p-of-trend<0.001 for all). Over a median follow-up of 4.8 years (interquartile range 1.8-9.2 years), new-onset AF occurred in 6,795 (7.0%) patients. In multivariable survival analysis, adjusted to multiple risk factors including LVEF and clinical HF, G2 and G3 LVDD, representing patients with high filling pressures, were independently associated with a higher AF-risk [G2-LVDD: adjusted hazard ratio (aHR) 1.64 (95% confidence interval (95%CI) 1.52-1.73), G3-LVDD: aHR 2.24 (95%CI 2.02-2.48)]. Conclusion The AI-ECG LVDD algorithm independently predicts long-term AF risk, regardless of LVEF and clinical HF status, highlighting its potential for identifying high-risk populations and guiding proactive monitoring and management.
Discussion
No takes yet. Share an insight, caveat, or question.
Cite This Study
Tsaban et al. (2024) conducted a cohort in Left ventricular diastolic dysfunction (n=97,023). AI-ECG-detected LVDD (Grade 3) vs. Normal diastolic function was evaluated on New-onset atrial fibrillation (aHR 2.24, 95% CI 2.02-2.48). AI-ECG-detected grade 3 left ventricular diastolic dysfunction was independently associated with a higher risk of new-onset atrial fibrillation (aHR 2.24; 95% CI 2.02-2.48).