Are artificial intelligence derived coronary atherosclerotic characteristics associated with subsequent development of acute coronary syndrome (ACS)

Abstract Funding Acknowledgements Type of funding sources: Public hospital(s). Main source(s): Scripps Health Krueger Wyeth Grant Background ACS results from unstable atherosclerotic plaques. Current measures to assess risk do not consider the patient’s coronary composition. This was a case control study using prospective single-center registry patients undergoing CCTA (N=2,700) 2017–2020 association between plaque characterization and occurrence ACS. Methods cases were adjudicated independently by two cardiologists data EMR. Patients with prior CCTA, excluded. Controls selected 1:1 nearest neighbor propensity matching (R. v. 4.0.3.) based on age, sex, smoking, HTN, HLD, DM. Plaque burden stenosis features calculated commercially available artificial intelligence (AI) analysis (Figure 1). Results There 21 controls. Mean age 68, 43% women, 5% Hispanic, 29% smoking hx, 76% 81% 24% DM, CAD-RADS score 2.3, CAC 487. Median time CT for 329 days. Presence total non-calcified plaque, calcified fibro-fatty maximum diameter percentage each associated greater (Table Conclusion AI assessment characteristics shows derived development in highlights potential utility AI-driven predict