Title

Machine learning of clinical variables and coronary artery calcium scoring for the prediction of obstructive coronary artery disease on coronary computed tomography angiography: Analysis from the CONFIRM registry

Authors

Subhi J. Al'Aref, New York Presbyterian Hospital
Gabriel Maliakal, New York Presbyterian Hospital
Gurpreet Singh, New York Presbyterian Hospital
Alexander R. van Rosendael, New York Presbyterian Hospital
Xiaoyue Ma, New York Presbyterian Hospital
Zhuoran Xu, New York Presbyterian Hospital
Omar Al Hussein Alawamlh, New York Presbyterian Hospital
Benjamin Lee, New York Presbyterian Hospital
Mohit Pandey, New York Presbyterian Hospital
Stephan Achenbach, Friedrich-Alexander-Universität Erlangen-Nürnberg
Mouaz H. Al-Mallah, Methodist Hospital Houston
Daniele Andreini, IRCCS Centro Cardiologico Monzino
Jeroen J. Bax, Leiden University Medical Center - LUMC
Daniel S. Berman, Cedars-Sinai Medical Center
Matthew J. Budoff, The Lundquist Institute
Filippo Cademartiri, IRCCS Fondazione SDN
Tracy Q. Callister, Tennessee Heart and Vascular Institute
Hyuk Jae Chang, Severance Hospital
Kavitha Chinnaiyan, William Beaumont Hospital
Benjamin J.W. Chow, University of Ottawa, Canada
Ricardo C. Cury, Baptist Cardiac and Vascular Institute
Augustin DeLago, Capitol Cardiology Associates
Gudrun Feuchtner, Medizinische Universitat Innsbruck
Martin Hadamitzky, Deutsches Herzzentrum München
Joerg Hausleiter, Klinikum der Universität München
Philipp A. Kaufmann, UniversitatsSpital Zurich
Yong Jin Kim, Seoul National University Hospital
Jonathon A. Leipsic, The University of British Columbia
Erica Maffei
Hugo Marques, Hospital da Luz
Pedro de Araújo Gonçalves, Hospital da Luz
Gianluca Pontone, IRCCS Centro Cardiologico Monzino
Gilbert L. Raff, William Beaumont Hospital

Document Type

Article

Publication Date

1-14-2020

Publication Title

European Heart Journal

Abstract

© The Author(s) 2019. Published by Oxford University Press on behalf of the European Society of Cardiology. Aims Symptom-based pretest probability scores that estimate the likelihood of obstructive coronary artery disease (CAD) in stable chest pain have moderate accuracy. We sought to develop a machine learning (ML) model utilizing clinical factors and the coronary artery calcium score (CACS), to predict the presence of obstructive CAD on coronary computed tomography angiography (CCTA). Methods The study screened 35 281 participants enrolled in the CONFIRM registry, who underwent >_64 detector row and results CCTA evaluation because of either suspected or previously established CAD. A boosted ensemble algorithm (XGBoost) was used, with data split into a training set (80%) on which 10-fold cross-validation was done and a test set (20%). Performance was assessed of the (1) ML model (using 25 clinical and demographic features), (2) ML þ CACS, (3) CAD consortium clinical score, (4) CAD consortium clinical score þ CACS, and (5) updated Diamond-Forrester (UDF) score. The study population comprised of 13 054 patients, of whom 2380 (18.2%) had obstructive CAD (>_50% stenosis). Machine learning with CACS produced the best performance [area under the curve (AUC) of 0.881] compared with ML alone (AUC of 0.773), CAD consortium clinical score (AUC of 0.734), and with CACS (AUC of 0.866) and UDF (AUC of 0.682), P < 0.05 for all comparisons. CACS, age, and gender were the highest ranking features. Conclusion A ML model incorporating clinical features in addition to CACS can accurately estimate the pretest likelihood of obstructive CAD on CCTA. In clinical practice, the utilization of such an approach could improve risk stratification and help guide downstream management.

Volume

41

Issue

3

First Page

359

Last Page

367

DOI

10.1093/eurheartj/ehz565

ISSN

0195668X

This document is currently not available here.

Share

COinS