Key result
Deep learning model predicts chronological age within ~2.8 years using heart MRIs and ECGs.
Why the study?
Heart disease is the primary cause of death after age 65, and its prevalence is expected to starkly increase with global population aging.
Can deep learning accurately predict heart age using cardiac magnetic resonance videos and electrocardiograms in a large biobank cohort?
Observational (n=45,000)
Can deep learning accurately predict heart age using cardiac magnetic resonance videos and electrocardiograms in a large biobank cohort?
Answers are grounded in this paper and cite their sources.
Deep learning can accurately predict heart age from cardiac MRI and ECGs, demonstrating that accelerated heart aging is highly heritable and primarily driven by anatomical features such as the aorta, mitral valve, and interventricular septum.
Heart disease is the first cause of death after age 65 and, with the world population aging, its prevalence is expected to starkly increase. We used deep learning to build a heart age predictor on 45,000 heart magnetic resonance videos [MRI] and electrocardiograms [ECG] from the UK Biobank cohort (age range 45-81 years). We predicted age with a root mean squared error [RMSE] of 2.81±0.02 years (R-Squared=85.6±0.2%) and found that accelerated heart aging is heritable at more than 35%. MRI-based anatomical features predicted age better than ECG-based electro-physiological features (RMSE=2.89±0.02 years vs. 6.09±.0.02 years), and heart anatomical and electrical aging are weakly correlated (Pearson correlation=.249±.002). Our attention maps highlighted the aorta, the mitral valve, and the interventricular septum as key anatomical features driving heart age prediction. We identified genetic (e.g titin gene) and non-genetic correlates (e.g smoking) of accelerated heart aging.
No takes yet. Share an insight, caveat, or question.
Goallec et al. (2021) conducted an observational in General population (n=45,000). Deep learning model using heart MRI videos, ECGs, and scalar biomarkers was evaluated on Prediction of chronological age (RMSE 2.81±0.02 years). A deep learning model trained on heart MRI videos, ECGs, and biobank data predicted chronological age with a root mean squared error of 2.81±0.02 years and an R-squared of 85.6±0.2%.
Synapse has enriched 10 related papers. Consider them for comparative context: