Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Randomized Controlled Trial
. 2020 Jun 25;15(6):e0233791.
doi: 10.1371/journal.pone.0233791. eCollection 2020.

Machine learning insight into the role of imaging and clinical variables for the prediction of obstructive coronary artery disease and revascularization: An exploratory analysis of the CONSERVE study

Lohendran Baskaran  1   2   3 , Xiaohan Ying  2 , Zhuoran Xu  1   2 , Subhi J Al'Aref  1   2 , Benjamin C Lee  1   2 , Sang-Eun Lee  4 , Ibrahim Danad  5 , Hyung-Bok Park  6 , Ravi Bathina  7 , Andrea Baggiano  8 , Virginia Beltrama  8 , Rodrigo Cerci  9 , Eui-Young Choi  10 , Jung-Hyun Choi  11 , So-Yeon Choi  12 , Jason Cole  13 , Joon-Hyung Doh  14 , Sang-Jin Ha  15 , Ae-Young Her  16 , Cezary Kepka  17 , Jang-Young Kim  18 , Jin-Won Kim  19 , Sang-Wook Kim  20 , Woong Kim  21 , Yao Lu  2 , Amit Kumar  2 , Ran Heo  22 , Ji Hyun Lee  2   23 , Ji-Min Sung  23 , Uma Valeti  24 , Daniele Andreini  8 , Gianluca Pontone  8 , Donghee Han  25 , Todd C Villines  26 , Fay Lin  1   2 , Hyuk-Jae Chang  4 , James K Min  1   2   27 , Leslee J Shaw  1   2
Affiliations
Randomized Controlled Trial

Machine learning insight into the role of imaging and clinical variables for the prediction of obstructive coronary artery disease and revascularization: An exploratory analysis of the CONSERVE study

Lohendran Baskaran et al. PLoS One. .

Abstract

Background: Machine learning (ML) is able to extract patterns and develop algorithms to construct data-driven models. We use ML models to gain insight into the relative importance of variables to predict obstructive coronary artery disease (CAD) using the Coronary Computed Tomographic Angiography for Selective Cardiac Catheterization (CONSERVE) study, as well as to compare prediction of obstructive CAD to the CAD consortium clinical score (CAD2). We further perform ML analysis to gain insight into the role of imaging and clinical variables for revascularization.

Methods: For prediction of obstructive CAD, the entire ICA arm of the study, comprising 719 patients was used. For revascularization, 1,028 patients were randomized to invasive coronary angiography (ICA) or coronary computed tomographic angiography (CCTA). Data was randomly split into 80% training 20% test sets for building and validation. Models used extreme gradient boosting (XGBoost).

Results: Mean age was 60.6 ± 11.5 years and 64.3% were female. For the prediction of obstructive CAD, the AUC was significantly higher for ML at 0.779 (95% CI: 0.672-0.886) than for CAD2 (0.696 [95% CI: 0.594-0.798]) (P = 0.01). BMI, age, and angina severity were the most important variables. For revascularization, the model obtained an overall area under the receiver-operation curve (AUC) of 0.958 (95% CI = 0.933-0.983). Performance did not differ whether the imaging parameters used were from ICA (AUC 0.947, 95% CI = 0.903-0.990) or CCTA (AUC 0.941, 95% CI = 0.895-0.988) (P = 0.90). The ML model obtained sensitivity and specificity of 89.2% and 92.9%, respectively. Number of vessels with ≥70% stenosis, maximum segment stenosis severity (SSS) and body mass index (BMI) were the most important variables. Exclusion of imaging variables resulted in performance deterioration, with an AUC of 0.705 (95% CI 0.614-0.795) (P <0.0001).

Conclusions: For obstructive CAD, the ML model outperformed CAD2. BMI is an important variable, although currently not included in most scores. In this ML model, imaging variables were most associated with revascularization. Imaging modality did not influence model performance. Removal of imaging variables reduced model performance.

PubMed Disclaimer

Conflict of interest statement

The authors have read the journal's policy and the authors of this paper have the following competing interests: James K. Min is founder, paid employee, and has equity interest in Cleerly Health. However, he was an employee of the Dalio Institute of Cardiovascular Imaging at the time of the study. James K. Min also serves on the scientific advisory board of Arineta and GE Healthcare. Leslee Shaw has an equity interest in Cleerly Health. All other authors have reported that they have no relationships relevant to the contents of this paper to disclose. There are no patents, products in development or marketed products associated with this research to declare. This does not alter our adherence to PLOS ONE policies on sharing data and materials.

Figures

Fig 1
Fig 1. Patient selection.
The cohort for revascularization analysis is in the red box, and the cohort for obstructive CAD prediction is in the green box. Abbreviations: CAD = coronary artery disease, CCTA = Coronary computed tomographic angiography, ICA = Invasive Coronary Angiography.
Fig 2
Fig 2. Receiver Operating Characteristics (ROC) analysis for the prediction of obstructive coronary artery disease using non-imaging variables.
Abbreviations: AUC = Area under curve, CAD = Coronary artery disease.
Fig 3
Fig 3. The relative importance of clinical variables in the developed machine learning–based model for the prediction of obstructive coronary artery disease.
Abbreviations: BMI = body mass index, CAD = coronary artery disease.
Fig 4
Fig 4. Receiver Operating Characteristics (ROC) analysis for the prediction of 1-year revascularization using non-imaging variables only (orange) and incorporating imaging variables (blue shades).
Abbreviations: AUC = Area under curve, CCTA = Coronary computed tomographic angiography, ICA = Invasive coronary angiography.
Fig 5
Fig 5. The relative importance of clinical (red) and image-based (blue) variables in the developed machine learning–based model for the prediction of 1-year revascularization.
Abbreviations: BMI = body mass index, LAD = left anterior descending coronary artery, RCA = right coronary artery, SSS = maximum segment stenosis severity.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Douglas PS, Patel MR, Bailey SR, Dai D, Kaltenbach L, Brindis RG, et al. Hospital Variability in the Rate of Finding Obstructive Coronary Artery Disease at Elective, Diagnostic Coronary Angiography. Journal of the American College of Cardiology. 2011;58(8):801–809. 10.1016/j.jacc.2011.05.019 - DOI - PubMed
    1. Patel MR, Dai D, Hernandez AF, Douglas PS, Messenger J, Garratt KN, et al. Prevalence and predictors of nonobstructive coronary artery disease identified with coronary angiography in contemporary clinical practice. American Heart Journal. 2014;167(6):846–852.e2. 10.1016/j.ahj.2014.03.001 - DOI - PubMed
    1. Patel MR, Bailey SR, Bonow RO, Chambers CE, Chan PS, Dehmer GJ, et al. ACCF/SCAI/AATS/AHA/ASE/ASNC/HFSA/HRS/SCCM/SCCT/SCMR/STS 2012 appropriate use criteria for diagnostic catheterization: a report of the American College of Cardiology Foundation Appropriate Use Criteria Task Force, Society for Cardiovascular Angiography and Interventions, American Association for Thoracic Surgery, American Heart Association, American Society of Echocardiography, American Society of Nuclear Cardiology, Heart Failure Society of America, Heart Rhythm Society, Society of Critical Care Medicine, Society of Cardiovascular Computed Tomography, Society for Cardiovascular Magnetic Resonance, and Society of Thoracic Surgeons. J Am Coll Cardiol. 2012;59(22):1995–2027. 10.1016/j.jacc.2012.03.003 - DOI - PubMed
    1. Mohareb MM, Qiu F, Cantor WJ, Kingsbury KJ, Ko DT, Wijeysundera HC. Validation of the Appropriate Use Criteria for Coronary Angiography: A Cohort Study. Annals of Internal Medicine. 2015;162(8):549 10.7326/M14-1889 - DOI - PubMed
    1. Budoff MJ, Dowe D, Jollis JG, Gitter M, Sutherland J, Halamert E, et al. Diagnostic performance of 64-multidetector row coronary computed tomographic angiography for evaluation of coronary artery stenosis in individuals without known coronary artery disease: results from the prospective multicenter ACCURACY (Assessment by Coronary Computed Tomographic Angiography of Individuals Undergoing Invasive Coronary Angiography) trial. J Am Coll Cardiol. 2008;52(21):1724–1732. 10.1016/j.jacc.2008.07.031 - DOI - PubMed

Publication types