Skip to main content

Improved long-term prognostic value of coronary CT angiography-derived plaque measures and clinical parameters on adverse cardiac outcome using machine learning

Abstract

Objectives

To evaluate the long-term prognostic value of coronary CT angiography (cCTA)-derived plaque measures and clinical parameters on major adverse cardiac events (MACE) using machine learning (ML).

Methods

Datasets of 361 patients (61.9 ± 10.3 years, 65% male) with suspected coronary artery disease (CAD) who underwent cCTA were retrospectively analyzed. MACE was recorded. cCTA-derived adverse plaque features and conventional CT risk scores together with cardiovascular risk factors were provided to a ML model to predict MACE. A boosted ensemble algorithm (RUSBoost) utilizing decision trees as weak learners with repeated nested cross-validation to train and validate the model was used. Performance of the ML model was calculated using the area under the curve (AUC).

Results

MACE was observed in 31 patients (8.6%) after a median follow-up of 5.4 years. Discriminatory power was significantly higher for the ML model (AUC 0.96 [95%CI 0.93–0.98]) compared with conventional CT risk scores including Agatston calcium score (AUC 0.84 [95%CI 0.80–0.87]), segment involvement score (AUC 0.88 [95%CI 0.84–0.91]), and segment stenosis score (AUC 0.89 [95%CI 0.86–0.92], all p < 0.05). Similar results were shown for adverse plaque measures (AUCs 0.72–0.82, all p < 0.05) and clinical parameters including the Framingham risk score (AUCs 0.71–0.76, all p < 0.05). The ML model yielded significantly higher diagnostic performance compared with logistic regression analysis (AUC 0.96 vs. 0.92, p = 0.024).

Conclusion

Integration of a ML model improves the long-term prediction of MACE when compared with conventional CT risk scores, adverse plaque measures, and clinical information. ML algorithms may improve the integration of patient’s information to enhance risk stratification.

Key Points

A machine learning (ML) model portends high discriminatory power to predict major adverse cardiac events (MACE).

• ML-based risk stratification shows superior diagnostic performance for MACE prediction over coronary CT angiography (cCTA)-derived risk scores or clinical parameters alone.

• A ML model outperforms conventional logistic regression analysis for the prediction of MACE.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3

Abbreviations

AUC:

Area under the curve

CAD:

Coronary artery disease

cCTA:

Coronary CT angiography

CV:

Cross-validation

ICA:

Invasive coronary angiography

MACE:

Major adverse cardiac events

ML:

Machine learning

NPV:

Negative predictive value

NSTEMI:

Non-ST segment elevation myocardial infarction

PPV:

Positive predictive value

RI:

Remodeling Index

ROC:

Receiver-operating characteristics

STEMI:

ST segment elevation myocardial infarction

References

  1. 1.

    Min JK, Shaw LJ, Devereux RB et al (2007) Prognostic value of multidetector coronary computed tomographic angiography for prediction of all-cause mortality. J Am Coll Cardiol 50:1161–1170

    Article  Google Scholar 

  2. 2.

    Tesche C, Plank F, De Cecco CN et al (2016) Prognostic implications of coronary CT angiography-derived quantitative markers for the prediction of major adverse cardiac events. J Cardiovasc Comput Tomogr 10:458–465

    Article  Google Scholar 

  3. 3.

    Chow BJ, Wells GA, Chen L et al (2010) Prognostic value of 64-slice cardiac computed tomography severity of coronary artery disease, coronary atherosclerosis, and left ventricular ejection fraction. J Am Coll Cardiol 55:1017–1028

    Article  Google Scholar 

  4. 4.

    Bauer RW, Thilo C, Chiaramida SA, Vogl TJ, Costello P, Schoepf UJ (2009) Noncalcified atherosclerotic plaque burden at coronary CT angiography: a better predictor of ischemia at stress myocardial perfusion imaging than calcium score and stenosis severity. AJR Am J Roentgenol 193:410–418

    Article  Google Scholar 

  5. 5.

    Motoyama S, Kondo T, Sarai M et al (2007) Multislice computed tomographic characteristics of coronary lesions in acute coronary syndromes. J Am Coll Cardiol 50:319–326

    Article  Google Scholar 

  6. 6.

    Andreini D, Pontone G, Mushtaq S et al (2017) Long-term prognostic impact of CT-Leaman score in patients with non-obstructive CAD: results from the COronary CT Angiography EvaluatioN For Clinical Outcomes InteRnational Multicenter (CONFIRM) study. Int J Cardiol 231:18–25

    Article  Google Scholar 

  7. 7.

    Dey D, Slomka PJ, Leeson P et al (2019) Artificial intelligence in cardiovascular imaging: JACC state-of-the-art review. J Am Coll Cardiol 73:1317–1335

    Article  Google Scholar 

  8. 8.

    Al’Aref SJ, Anchouche K, Singh G et al (2019) Clinical applications of machine learning in cardiovascular disease and its relevance to cardiac imaging. Eur Heart J 40(24):1975–1986

  9. 9.

    Dey D, Gaur S, Ovrehus KA et al (2018) Integrated prediction of lesion-specific ischaemia from quantitative coronary CT angiography using machine learning: a multicentre study. Eur Radiol 28:2655–2664

    Article  Google Scholar 

  10. 10.

    Motwani M, Dey D, Berman DS et al (2017) Machine learning for prediction of all-cause mortality in patients with suspected coronary artery disease: a 5-year multicentre prospective registry analysis. Eur Heart J 38(7):500–507

  11. 11.

    Task Force on the management of ST-segment elevation acute myocardial infarction of the European Society of Cardiology (ESC), Steg PG, James SK et al (2012) ESC Guidelines for the management of acute myocardial infarction in patients presenting with ST-segment elevation. Eur Heart J 33:2569–2619

  12. 12.

    D’Agostino RB Sr, Vasan RS, Pencina MJ et al (2008) General cardiovascular risk profile for use in primary care: the Framingham Heart Study. Circulation 117:743–753

    Article  Google Scholar 

  13. 13.

    Cury RC, Abbara S, Achenbach S et al (2016) CAD-RADS(TM) coronary artery disease - reporting and data system. An expert consensus document of the Society of Cardiovascular Computed Tomography (SCCT), the American College of Radiology (ACR) and the north American Society for Cardiovascular Imaging (NASCI). Endorsed by the American College of Cardiology. J Cardiovasc Comput Tomogr 10:269–281

  14. 14.

    Achenbach S, Ropers D, Hoffmann U et al (2004) Assessment of coronary remodeling in stenotic and nonstenotic coronary atherosclerotic lesions by multidetector spiral computed tomography. J Am Coll Cardiol 43:842–847

    Article  Google Scholar 

  15. 15.

    Maurovich-Horvat P, Schlett CL, Alkadhi H et al (2012) The napkin-ring sign indicates advanced atherosclerotic lesions in coronary CT angiography. JACC Cardiovasc Imaging 5:1243–1252

    Article  Google Scholar 

  16. 16.

    Park HB, Heo R, o Hartaigh B et al (2015) Atherosclerotic plaque characteristics by CT angiography identify coronary lesions that cause ischemia: a direct comparison to fractional flow reserve. JACC Cardiovasc Imaging 8:1–10

    Article  Google Scholar 

  17. 17.

    Min JK, Feignoux J, Treutenaere J, Laperche T, Sablayrolles J (2010) The prognostic value of multidetector coronary CT angiography for the prediction of major adverse cardiovascular events: a multicenter observational cohort study. Int J Cardiovasc Imaging 26:721–728

    Article  Google Scholar 

  18. 18.

    Yamamoto H, Kihara Y, Kitagawa T et al (2018) Coronary plaque characteristics in computed tomography and 2-year outcomes: the PREDICT study. J Cardiovasc Comput Tomogr 12:436–443

    Article  Google Scholar 

  19. 19.

    Seiffert C, Khoshgoftaar TM, Van Hulse J, Napolitano A (2010) RUSBoost: a hybrid approach to alleviating class imbalance. IEEE Trans Syst Man Cybern Part A Syst Hum 40:185–197

    Article  Google Scholar 

  20. 20.

    van Rosendael AR, Maliakal G, Kolli KK et al (2018) Maximization of the usage of coronary CTA derived plaque information using a machine learning based algorithm to improve risk stratification; insights from the CONFIRM registry. J Cardiovasc Comput Tomogr 12:204–209

    Article  Google Scholar 

  21. 21.

    Hastie T, Tibshirani R, Friedman JH (2009) The elements of statistical learning : data mining, inference, and prediction, 2nd edn. Springer, New York

    Book  Google Scholar 

  22. 22.

    Ruschhaupt M, Huber W, Poustka A, Mansmann U (2004) A compendium to ensure computational reproducibility in high-dimensional classification tasks. Stat Appl Genet Mol Biol 3:Article37

    Article  Google Scholar 

  23. 23.

    Krstajic D, Buturovic LJ, Leahy DE, Thomas S (2014) Cross-validation pitfalls when selecting and assessing regression and classification models. J Cheminform 6:10

  24. 24.

    DeLong ER, DeLong DM, Clarke-Pearson DL (1988) Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 44:837–845

    CAS  Article  Google Scholar 

  25. 25.

    Johnson KM, Johnson HE, Zhao Y, Dowe DA, Staib LH (2019) Scoring of coronary artery disease characteristics on coronary CT angiograms by using machine learning. Radiology 292:354–362

    Article  Google Scholar 

  26. 26.

    Tesche C, Caruso D, De Cecco CN et al (2017) Coronary computed tomography angiography-derived plaque quantification in patients with acute coronary syndrome. Am J Cardiol 119:712–718

    Article  Google Scholar 

Download references

Funding

No funding was received.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Christian Tesche.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Dr. Christian Tesche.

Conflict of interest

The authors of this manuscript declare relationships with the following companies:

Dr. Schoepf receives institutional research support and/or honoraria for speaking and consulting from Astellas, Bayer, Bracco, Elucid BioImaging, Guerbet, HeartFlow Inc., and Siemens Healthineers. Dr. Tesche has received speaker’s fees from Siemens Healthineers and Heartflow Inc. The other authors have no conflict of interest to disclose.

The other authors declare no conflict of interest.

Statistics and biometry

No complex statistical methods were necessary for this paper.

Informed consent

Written informed consent was waived by the Institutional Review Board.

Ethical approval

Institutional Review Board approval was obtained.

Methodology

• retrospective

• observational

• performed at one institution

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Tesche, C., Bauer, M.J., Baquet, M. et al. Improved long-term prognostic value of coronary CT angiography-derived plaque measures and clinical parameters on adverse cardiac outcome using machine learning. Eur Radiol 31, 486–493 (2021). https://doi.org/10.1007/s00330-020-07083-2

Download citation

Keywords

  • Multidetector computed tomography
  • Coronary artery disease
  • Machine learning
  • Outcome measures