Original Research
A Boosted Ensemble Algorithm for Determination of Plaque Stability in High-Risk Patients on Coronary CTA

https://doi.org/10.1016/j.jcmg.2020.03.025Get rights and content
Under an Elsevier user license
open archive

Abstract

Objectives

This study sought to identify culprit lesion (CL) precursors among acute coronary syndrome (ACS) patients based on qualitative and quantitative computed tomography–based plaque characteristics.

Background

Coronary computed tomography angiography (CTA) has been validated for patient-level prediction of ACS. However, the applicability of coronary CTA to CL assessment is not known.

Methods

Utilizing the ICONIC (Incident COroNary Syndromes Identified by Computed Tomography) study, a nested case-control study of 468 patients with baseline coronary CTA, the study included ACS patients with invasive coronary angiography–adjudicated CLs that could be aligned to CL precursors on baseline coronary CTA. Separate blinded core laboratories adjudicated CLs and performed atherosclerotic plaque evaluation. Thereafter, the study used a boosted ensemble algorithm (XGBoost) to develop a predictive model of CLs. Data were randomly split into a training set (80%) and a test set (20%). The area under the receiver-operating characteristic curve of this model was compared with that of diameter stenosis (model 1), high-risk plaque features (model 2), and lesion-level features of CL precursors from the ICONIC study (model 3). Thereafter, the machine learning (ML) model was applied to 234 non-ACS patients with 864 lesions to determine model performance for CL exclusion.

Results

CL precursors were identified by both coronary angiography and baseline coronary CTA in 124 of 234 (53.0%) patients, with a total of 582 lesions (containing 124 CLs) included in the analysis. The ML model demonstrated significantly higher area under the receiver-operating characteristic curve for discriminating CL precursors (0.774; 95% confidence interval [CI]: 0.758 to 0.790) compared with model 1 (0.599; 95% CI: 0.599 to 0.599; p < 0.01), model 2 (0.532; 95% CI: 0.501 to 0.563; p < 0.01), and model 3 (0.672; 95% CI: 0.662 to 0.682; p < 0.01). When applied to the non-ACS cohort, the ML model had a specificity of 89.3% for excluding CLs.

Conclusions

In a high-risk cohort, a boosted ensemble algorithm can be used to predict CL from non-CL precursors on coronary CTA.

Key Words

acute coronary syndrome
coronary computed tomography angiography
diameter stenosis
machine learning

Abbreviations and Acronyms

ACS
acute coronary syndrome
APCs
atherosclerotic plaque characteristics
AUC
area under the receiver-operating characteristic curve
CAD
coronary artery disease
CI
confidence interval
CL
culprit lesion
CTA
computed tomography angiography
HU
Hounsfield unit
ICA
invasive coronary angiography
LAP
low-attenuation plaque
MI
myocardial infarction
ML
machine learning

Cited by (0)

This trial was supported by National Institutes of Health Grant No. HL115150 (to Dr. Min) and the Leading Foreign Research Institute Recruitment Program of the National Research Foundation of Korea, Ministry of Science, ICT and Future Planning (Seoul, Korea). The research reported in this manuscript was also supported, in part by, the Dalio Institute of Cardiovascular Imaging (New York, New York). Dr. Signh is an employee of GlaxoSmithKline. Dr. Bax has received speaker fees from Abbott Vascular; and received institutional research grant support from Abbott Vascular, Edwards Lifesciences, Biotronik, Bioventrix, Boston Scientific, Medtronic, and GE Healthcare. Dr. Chinnaiyan has received institutional research grant support and served as a consultant for HeartFlow. Dr. Chow is the Saul and Edna Goldfarb Chair in Cardiac Imaging Research; and has received research grant support from TD Bank, CV Diagnostics and AusculSciences, Siemens Healthineers, and TeraRecon; and owns equity in GE Healthcare. Dr. Cury has served as a consultant for GE Healthcare, Cleerly Health, and Spreemo Health. Dr. Leipsic has served as a consultant for and owns stock options in HeartFlow and Circle CVI; and received research grant support from and served on the Speakers Bureau for GE Healthcare. Dr. Pontone has a research grant and/or honorarium as a speaker from GE Healthcare, Bracco, Bayer, Medtronic, and HeartFlow. Dr. Berman has received research grant support from HeartFlow and software royalties from Cedars-Sinai Medical Center. Dr. Budoff received research grant support from the National Institutes of Health and GE Healthcare. Dr. Samady has served as a consultant and received research grant support from Philips; has received institutional research grant support from Abbott Vascular, Medtronic, and Philips; is co-founder of Covanos; and owns equity in Covanos and SIG. Dr. Shaw owns equity in Cleerly Health. Dr. Min has received funding from the Dalio Foundation, the National Institutes of Health, and GE Healthcare; has served on the scientific advisory board of Arineta and GE Healthcare; and previously worked at Weill Cornell Medicine but is now an employee of and owns equity in Cleerly Health. All other authors have reported that they have no relationships relevant to the contents of this paper to disclose. Harvey Hecht, MD, was Guest Editor on this paper.

The authors attest they are in compliance with human studies committees and animal welfare regulations of the authors’ institutions and Food and Drug Administration guidelines, including patient consent where appropriate. For more information, visit the JACC: Cardiovascular Imaging author instructions page.

© 2020 by the American College of Cardiology Foundation. Published by Elsevier.