AI-based measurement better predicts all-cause mortality over more than five years
FRIDAY, Nov. 6, 2026 (HealthDay News) — Using artificial intelligence (AI) to assess heart function from magnetic resonance imaging (MRI) scans more strongly predicts survival than interpretation by clinicians, according to a study published online Nov. 2 in The Lancet Digital Health.
George Joy, Ph.D., from City St. George”s University of London, and colleagues assessed whether deep-learning artificial intelligence (AI) segmentation of ejection fraction from cardiac MRI outperforms expert clinician segmentation for the prediction of all-cause mortality. The analysis included 27,382 consecutive patients with a baseline cardiac MRI.
The researchers found that during 5.6 years of follow-up, AI ejection fraction showed better model fit (Δ Akaike information criterion [ΔAIC], 161 favoring AI) and marginally better discrimination (ΔC index, 0.033). When added to clinician ejection fraction, AI ejection fraction significantly improved model fit (χ2 = 168), whereas improvement was only slight when clinician ejection fraction was added to AI (χ2 = 7.5). When adjusting for age and sex, AI-derived ejection fraction showed better model fit (ΔAIC, 59) and had marginally better discrimination (ΔC index, 0.004).
“Our findings suggest AI can measure this important marker with remarkable consistency and precision, resulting in a small but meaningful improvement in identifying patients at higher risk,” Joy said in a statement.
Pre-Prostate Biopsy MRI Use Increased From 2017 to 2026 
PET/MRI Offers Diagnostic, Prognostic Value in Pediatric Epilepsy 
Dense Breast Notification Linked to Increase in Use of Supplemental Ultrasound 
Nighttime Light Exposure Linked to Adverse Cardiac Remodeling 
Cardiac Remodeling May Portend Cancer Risk 
Volume Rendering of Myocardium, Cardiac Valves Enables Visualization 
CMR-Modeled PCWP Independent Risk Factor for Heart Failure 
Non-MRI-Conditional ICDs Still Function After MRI 
