1. Artificial Intelligence-Enabled Quantitative Coronary Plaque and Hemodynamic Analysis for Predicting Acute Coronary Syndrome.
- Author
-
Koo BK, Yang S, Jung JW, Zhang J, Lee K, Hwang D, Lee KS, Doh JH, Nam CW, Kim TH, Shin ES, Chun EJ, Choi SY, Kim HK, Hong YJ, Park HJ, Kim SY, Husic M, Lambrechtsen J, Jensen JM, Nørgaard BL, Andreini D, Maurovich-Horvat P, Merkely B, Penicka M, de Bruyne B, Ihdayhid A, Ko B, Tzimas G, Leipsic J, Sanz J, Rabbat MG, Katchi F, Shah M, Tanaka N, Nakazato R, Asano T, Terashima M, Takashima H, Amano T, Sobue Y, Matsuo H, Otake H, Kubo T, Takahata M, Akasaka T, Kido T, Mochizuki T, Yokoi H, Okonogi T, Kawasaki T, Nakao K, Sakamoto T, Yonetsu T, Kakuta T, Yamauchi Y, Bax JJ, Shaw LJ, Stone PH, and Narula J
- Subjects
- Aged, Female, Humans, Male, Middle Aged, Coronary Circulation, Coronary Vessels physiopathology, Coronary Vessels diagnostic imaging, Hemodynamics, Multidetector Computed Tomography, Predictive Value of Tests, Prognosis, Radiographic Image Interpretation, Computer-Assisted, Reproducibility of Results, Risk Assessment, Risk Factors, Rupture, Spontaneous, Severity of Illness Index, Time Factors, Acute Coronary Syndrome physiopathology, Acute Coronary Syndrome diagnostic imaging, Artificial Intelligence, Computed Tomography Angiography, Coronary Angiography, Coronary Artery Disease physiopathology, Coronary Artery Disease diagnostic imaging, Plaque, Atherosclerotic
- Abstract
Background: A lesion-level risk prediction for acute coronary syndrome (ACS) needs better characterization., Objectives: This study sought to investigate the additive value of artificial intelligence-enabled quantitative coronary plaque and hemodynamic analysis (AI-QCPHA)., Methods: Among ACS patients who underwent coronary computed tomography angiography (CTA) from 1 month to 3 years before the ACS event, culprit and nonculprit lesions on coronary CTA were adjudicated based on invasive coronary angiography. The primary endpoint was the predictability of the risk models for ACS culprit lesions. The reference model included the Coronary Artery Disease Reporting and Data System, a standardized classification for stenosis severity, and high-risk plaque, defined as lesions with ≥2 adverse plaque characteristics. The new prediction model was the reference model plus AI-QCPHA features, selected by hierarchical clustering and information gain in the derivation cohort. The model performance was assessed in the validation cohort., Results: Among 351 patients (age: 65.9 ± 11.7 years) with 2,088 nonculprit and 363 culprit lesions, the median interval from coronary CTA to ACS event was 375 days (Q1-Q3: 95-645 days), and 223 patients (63.5%) presented with myocardial infarction. In the derivation cohort (n = 243), the best AI-QCPHA features were fractional flow reserve across the lesion, plaque burden, total plaque volume, low-attenuation plaque volume, and averaged percent total myocardial blood flow. The addition of AI-QCPHA features showed higher predictability than the reference model in the validation cohort (n = 108) (AUC: 0.84 vs 0.78; P < 0.001). The additive value of AI-QCPHA features was consistent across different timepoints from coronary CTA., Conclusions: AI-enabled plaque and hemodynamic quantification enhanced the predictability for ACS culprit lesions over the conventional coronary CTA analysis. (Exploring the Mechanism of Plaque Rupture in Acute Coronary Syndrome Using Coronary Computed Tomography Angiography and Computational Fluid Dynamics II [EMERALD-II]; NCT03591328)., Competing Interests: Funding Support and Author Disclosures This study received funding from HeartFlow Inc. The company performed the computational fluid dynamics, and artificial intelligence quantitative coronary plaque analysis but was not involved in the study design, collection, analysis, and interpretation of data; the writing of this paper; or the decision to submit it for publication. Dr Koo has received institutional research grants from Abbott, Philips, and HeartFlow Inc. Dr Nam has received institutional research grants from Abbott and Genoss. Dr Merkely has received direct personal payments for speaker fees or studies from Abbott, AstraZeneca, Biotronik, Boehringer Ingelheim, CSL Behring, Daiichi Sankyo, DUKE Clinical Institute, Medtronic, and Novartis and institutional grants from Abbott, AstraZeneca, Biotronik, Boehringer Ingelheim, Boston Scientific, Bristol Myers Squibb, CSL Behring, Daiichi Sankyo, DUKE Clinical Institute, Eli Lilly, Medtronic, Novartis, Terumo, and VIFOR Pharma. Dr de Bruyne has received institutional unrestricted research grants from Abbott, Boston Scientific, and Biotronik; has received consulting fees from Abbott, Opsens, and Boston Scientific; and is a shareholder for Siemens, GE, Bayer, Philips, HeartFlow Inc, Edwards Life Sciences, Sanofi, and Omega Pharma. Dr Ko has equity in Artrya and has received honoraria from Medtronic, Abbott Vascular, and Canon Medical. Dr Leipsic is a consultant for and holds stock options in HeartFlow Inc and modest personal core lab fees from Arineta. Dr Shah has received honoraria as a speaker for HeartFlow Inc. Dr Bax has received unrestricted research grants from Abbott and Edwards Lifesciences to the Department of Cardiology, Leiden University Medical Center, the Netherlands. Dr Shaw has received honoraria from HeartFlow Inc and Elucid Imaging. All other authors have reported that they have no relationships relevant to the contents of this paper to disclose., (Copyright © 2024 American College of Cardiology Foundation. Published by Elsevier Inc. All rights reserved.)
- Published
- 2024
- Full Text
- View/download PDF