Kim, Eun Kyoung

Abstract Aims To assess the performance of an artificial intelligence-enabled electrocardiogram (AI-ECG) algorithm in identifying patients with moderate to severe aortic stenosis (AS) in an Asian cohort from a tertiary care centre. Methods and results We identified a randomly selected patients ≥60 years old who underwent echocardiography and ECG within in 31 days between 2012 and 2021 at the Samsung Medical Center in Korea. Patients with previous cardiac surgery, prosthetic valves, or pacemakers were excluded. The AI-ECG model, originally developed and validated by Mayo Clinic in the USA, was applied without fine-tuning. Performance metrics, including the area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy, were calculated to compare AI-ECG predictions with TTE-confirmed AS status. Among 5425 patients, 1095 had moderate to severe AS, and 4330 age- and sex-matched patients without AS were included as controls. The AI-ECG model achieved an AUC of 0.85 (95% CI: 0.84–0.87) in detecting moderate to severe AS. Sensitivity, specificity, PPV, NPV, and accuracy were 0.83, 0.65, 0.37, 0.94, and 68.29%, respectively. The model's performance was consistent across various age and sex subgroups, with sensitivity increasing in older patients. Conclusion The AI-ECG model developed in the USA demonstrated comparable performance in detecting moderate to severe AS in an Asian cohort compared with its original validation population. These findings highlight the potential utility of AI-ECG as a non-invasive screening tool for AS across diverse patient populations.

Background— Coronary collateral flow is an alternative source of myocardial perfusion in patients with totally occluded coronary arteries. Clinical evaluation of collateral flow has been limited by the need of invasive measurements. We investigated whether noninvasive coronary computed tomographic angiography can evaluate the angiographic extent of coronary collateral flow. Methods and Results— We enrolled 325 coronary computed tomographic angiography cases with angiographically confirmed chronic total occlusion (median age, 63 years; men 83%). Transluminal attenuation gradient (TAG), which reflects the kinetics of contrast media in coronary artery, of an entire artery as well as of a distal vessel was assessed to evaluate the flow in entire vessel and distal vessel. TAGs were validated against visually assessed angiographic collateral connection and Rentrop grading. TAG of an entire artery increased consistently according to the angiographic extent of collateral flow ( P <0.001). Well-developed collaterals, defined by highest collateral connection and Rentrop grades (n=103), could be predicted by TAG of an entire artery (cutoff, ≥−7.6 Hounsfield units/10 mm; c -statistics, 0.72; sensitivity, 65%; specificity, 73%; positive predictive value, 52%; negative predictive value, 82%). TAG of a distal vessel could discriminate the antegrade (n=143) and retrograde (n=182) flows in distal artery (cutoff, 0.0 Hounsfield unit/10 mm; c -statistics, 0.88; sensitivity, 78%; specificity, 85%; positive predictive value, 87%; negative predictive value, 75%). Conclusions— TAG, an intracoronary attenuation-based analysis of coronary computed tomographic angiography, moderately reflected the functional extent and direction of collateral flow.