AI CT chamber volumes sharpen heart failure prediction over risk scores

AI-enabled chamber volumetry from coronary calcium CT boosted 10-year heart failure prediction: combined model AUC 0.80 vs PREVENT 0.76 (Δ0.04, P<.001) and vs CAC score 0.70 (Δ0.10, P<.001) in 5892 asymptomatic patients. Diastolic volumes conferred higher risk than systolic volu…

• Larger left atrial, left ventricular, right atrial, and LV myocardial volumes each independently associated with increased HF risk (all P<.001).
• Composite Cox model integrating all chamber volumes, CAC score, and PREVENT-HF yielded the highest discriminative performance across 3-, 5-, 8-, and 10-year horizons.
• Phase-volume interaction identified: diastolic volumes carried significantly higher HF risk than systolic volumes after adjusting for PREVENT-HF (P<.001).

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.