What does this research mean for the field?

Machine-estimated age exceeding chronological age by five years is associated with an 18% increased risk of new-onset atrial fibrillation. Novelty: ClaimNovelty.NOVEL_FINDING. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

This research aims to evaluate how well age can be estimated using AI from transthoracic echocardiography, and its link to atrial fibrillation risk.

February 8, 2026

The discrepancy between machine-estimated age from transthoracic echocardiography and chronological age as a key predictor of increased risk for new-onset atrial fibrillation

Key Result

Machine-estimated age from echocardiography exceeding chronological age by >5 years independently predicts 18% higher risk of new-onset atrial fibrillation (HR=1.17).

Key Points

This research aims to evaluate how well age can be estimated using AI from transthoracic echocardiography, and its link to atrial fibrillation risk.
Utilized convolutional neural networks for age estimation.
Trained on 76,342 patients and validated with 22,825 patients.
Tested on 20,960 patients and employed multivariate Cox regression analysis.
Excluded patients with prior atrial fibrillation diagnoses.
Mean average error of age estimation was 4.9 years, with RMSE of 6.33.
Achieved a Pearson correlation coefficient of 0.922.
Machine-based age prediction exceeding chronological age by 5 years correlated with an 18% increased risk of new-onset atrial fibrillation (p<0.001).
After adjustments, the hazard ratio for age prediction was 1.17 (95% CI 1.02-1.34, p=0.02).

Structured PICO

Does a machine-estimated age from transthoracic echocardiography exceeding chronological age predict the risk of new-onset atrial fibrillation in patients without prior AF?

Population

120,127 patients (76,342 training, 22,825 validation, 20,960 testing) in sinus rhythm without prior diagnosis of atrial fibrillation undergoing standard transthoracic echocardiography

Intervention

Machine-estimated age derived from standard transthoracic echocardiography using convolutional neural networks (CNNs)

Comparator

Chronological age

Outcome

New-onset atrial fibrillationhard clinical

Artificial intelligence-derived biological age from routine transthoracic echocardiograms that exceeds chronological age by more than 5 years independently predicts the development of new-onset atrial fibrillation.

Main Result

Absolute Event Rate: 0% vs 0%

Abstract

Abstract Background Age estimation utilizing artificial intelligence can be derived from a variety of sources. Objectives This study aimed to assess the efficacy of convolutional neural networks (CNNs) in estimating age through standard transthoracic echocardiography (TTE) and to evaluate its predictive capability regarding the onset of atrial fibrillation (AF) while in sinus rhythm. Methods The algorithm underwent training with a cohort of 76,342 patients, was validated with an additional 22,825 patients, and tested on 20,960 patients. A multivariate Cox regression model was utilized to examine the association between machine-estimated age and chronological age in relation to the diagnosis of new-onset atrial fibrillation. Patients with prior diagnosis of atrial fibrillation were excluded. Results The model demonstrated a mean average error of 4.9 years for age estimation, root-mean-square-error (RMSE) of 6.33 and achieved a Pearson correlation coefficient of 0.922 (Figure 1). Furthermore, multivariate analysis indicated that a machine-based age prediction exceeding five years of chronological age correlates with an independent 18% increased risk of developing new-onset atrial fibrillation during follow-up (p0.001) (Figure 2). Consistent results were obtained in a multivariate analysis after adjustment for age, sex, mortality predictors, left ventricular ejection fraction (LVEF), left atrial dimensions and echocardiographic diastolic parameters HR=1.17, 95% CI 1.02-1.34, p=0.02. Conclusions The integration of artificial intelligence into standard TTE facilitates the estimation of biological age. Machine-based age estimation serves as an independent predictor of the emergence of new-onset atrial fibrillation. Such predictive models can be instrumental for risk stratification and suggesting its potential utility to identify individuals for AF prevention.Model description and age estimation Figure 2.Cumulative AFib incidence

AIに質問

Bookmark