TrialsgrambetaRCTs are beautiful

AI in echocardiography & cardiac imaging

AI versus sonographer ejection fraction, AI-augmented stress echo, opportunistic calcium scoring, machine-learning CT-FFR, AI-guided AF ablation and device telemonitoring.

  • 2026AI-Echo RCT⁠EchocardiographyIn 585 patients undergoing echocardiography, AI-based automatic measurement of echocardiographic parameters improved examination efficiency (time per patient and examinations per day) compared with manual measurement workflow.Read →
  • 2025TAILORED-AF⁠Rhythm & devicesIn 370 patients with drug-refractory persistent atrial fibrillation, AI-guided ablation of electrogram dispersion added to pulmonary vein isolation improved freedom from atrial fibrillation at 12 months compared with pulmonary vein isolation alone.88% vs 70%Read →
  • 2024PROTEUS⁠EchocardiographyIn 2,341 patients undergoing stress echocardiography, AI-augmented clinical decision-making did not show non-inferiority to standard clinical decision-making for appropriate referral for coronary angiography.Read →
  • 2023EchoNet-RCT Core⁠EchocardiographyIn 3,495 echocardiograms undergoing quantification of cardiac function, initial AI assessment of left ventricular ejection fraction was non-inferior to initial sonographer assessment for the proportion of readings the cardiologist substantially changed, and superior.16.8% vs 27.2%Read →
  • 2023NOTIFY-1⁠CT & coronary physiologyIn 173 patients with incidental coronary artery calcium on a previous chest CT and no statin, deep-learning detection with notification of clinician and patient increased statin prescription within 6 months compared with usual care.51.2% vs 6.9%Read →
  • 2023TARGET (CT-FFR)⁠CT & coronary physiologyIn 1,216 patients with stable coronary disease and an intermediate stenosis on CT angiography, an on-site machine-learning CT-FFR care pathway reduced invasive angiography without obstructive disease or intervention within 90 days compared with standard care.28.3% vs 46.2%Read →
  • 2023Ginder ML remote monitoring⁠Rhythm & devicesIn 2,413 patients with heart failure and an ICD or CRT-D, a neural network reading the 30 days of remote-monitoring data before device therapy improved prediction of appropriate ICD therapy for VT/VF compared with multivariable logistic regression.Read →