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

Subhi J. Al'Aref, Gabriel Maliakal, Gurpreet Singh, Alexander R. van Rosendael, Xiaoyue Ma, Zhuoran Xu, Omar Al Hussein Alawamlh, Benjamin Lee, Mohit Pandey, Stephan Achenbach, Mouaz H. Al-Mallah, Daniele Andreini, Jeroen J. Bax, Daniel S. Berman, Matthew J. Budoff, Filippo Cademartiri, Tracy Q. Callister, Hyuk Jae Chang, Kavitha Chinnaiyan, Benjamin J.W. ChowRicardo C. Cury, Augustin DeLago, Gudrun Feuchtner, Martin Hadamitzky, Joerg Hausleiter, Philipp A. Kaufmann, Yong Jin Kim, Jonathon A. Leipsic, Erica Maffei, Hugo Marques, Pedro de Araújo Gonçalves, Gianluca Pontone, Gilbert L. Raff, Ronen Rubinshtein, Todd C. Villines, Heidi Gransar, Yao Lu, Erica C. Jones, Jessica M. Peña, Fay Y. Lin, James K. Min, Leslee J. Shaw

Research output: Contribution to journalArticlepeer-review

95 Citations (Scopus)


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.

Original languageEnglish
Pages (from-to)359-367
Number of pages9
JournalEuropean heart journal
Issue number3
Publication statusPublished - 2020 Jan 14

Bibliographical note

Funding Information:
from the National Institutes of Health and General Electric. D.S.B. receives a research grant from Heartflow and software royalties from Cedars-Sinai Medical Center. Gianluca Pontone has a research grant and/ or honorarium as speaker from GE, Bracco, Bayer, Medtronic, and Heartflow. All other authors have reported that they have no relationships relevant to the contents of this paper to disclose.

Funding Information:
The research reported in this publication was funded, in part, by the National Institute of Health (Bethesda, MD, USA) under award number R01 HL115150. This research was also supported, in part, by the Dalio Institute of Cardiovascular Imaging (New York, NY, USA) and the Michael Wolk Foundation (New York, NY, USA).

Publisher Copyright:
© The Author(s) 2019. Published by Oxford University Press on behalf of the European Society of Cardiology.

All Science Journal Classification (ASJC) codes

  • Cardiology and Cardiovascular Medicine


Dive into the research topics of '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'. Together they form a unique fingerprint.

Cite this