Prediction of cardiac death after adenosine myocardial perfusion SPECT based on machine learning

  • David Haro Alonso
  • Miles N. Wernick
  • Yongyi Yang
  • Guido Germano
  • Daniel S. Berman
  • Piotr Slomka
Original Article



We developed machine-learning (ML) models to estimate a patient’s risk of cardiac death based on adenosine myocardial perfusion SPECT (MPS) and associated clinical data, and compared their performance to baseline logistic regression (LR). We demonstrated an approach to visually convey the reasoning behind a patient’s risk to provide insight to clinicians beyond that of a “black box.”


We trained multiple models using 122 potential clinical predictors (features) for 8321 patients, including 551 cases of subsequent cardiac death. Accuracy was measured by area under the ROC curve (AUC), computed within a cross-validation framework. We developed a method to display the model’s rationale to facilitate clinical interpretation.


The baseline LR (AUC = 0.76; 14 features) was outperformed by all other methods. A least absolute shrinkage and selection operator (LASSO) model (AUC = 0.77; p = .045; 6 features) required the fewest features. A support vector machine (SVM) model (AUC = 0.83; p < .0001; 49 features) provided the highest accuracy.


LASSO outperformed LR in both accuracy and simplicity (number of features), with SVM yielding best AUC for prediction of cardiac death in patients undergoing MPS. Combined with presenting the reasoning behind the risk scores, our results suggest that ML can be more effective than LR for this application.


Cardiac death risk model machine learning feature selection data visualization 



Single-photon emission computed tomography


Myocardial perfusion SPECT


Summed stress score


Summed rest score


Left ventricular


Receiver operating characteristic


Area under the curve


Support vector machine


Least absolute shrinkage and selection operator


Logistic regression



Research reported in this article was supported by the National Heart, Lung, and Blood Institute of the National Institutes of Health under Award Numbers R01HL122484 and R01HL089765. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.


DH.A., Y.Y., and M.N.W. from the Illinois Institute of Technology have nothing to disclose. G.G., D.S.B., and P.S. from the Cedars-Sinai Medical Center have nothing to disclose.

Supplementary material

12350_2018_1250_MOESM1_ESM.pptx (54.4 mb)
Supplementary material 1 (PPTX 55,672 kb)


  1. 1.
    Wernick MN, Aarsvold JN. Emission tomography: The engineering and physics of PET and SPECT. San Diego: Academic Press; 2004. p. 596.Google Scholar
  2. 2.
    Hachamovitch R, Berman DS, Kiat H, Cohen I, Lewin H, Amanullah A, et al. Incremental prognostic value of adenosine stress myocardial perfusion single-photon emission computed tomography and impact on subsequent management in patients with or suspected of having myocardial ischemia. Am J Cardiol 1997;80:426-33.CrossRefPubMedGoogle Scholar
  3. 3.
    Hachamovitch R, Berman DS, Shaw LJ, Kiat H, Cohen I, Cabico JA, et al. Incremental prognostic value of myocardial perfusion single photon emission computed tomography for the prediction of cardiac death. Circulation 1998;97:535-43.CrossRefPubMedGoogle Scholar
  4. 4.
    Klocke FJ, Baird MG, Lorell BH, Bateman TM, Messer JV, Berman DS, et al. ACC/AHA/ASNC guidelines for the clinical use of cardiac radionuclide imaging—executive summary. Circulation 2003;108:1404-18.CrossRefPubMedGoogle Scholar
  5. 5.
    Sharir T, Ben-Haim S, Merzon K, Prochorov V, Dickman D, Ben-Haim S, et al. High-speed myocardial perfusion imaging: initial clinical comparison with conventional dual detector anger camera imaging. JACC: Cardiovasc Imaging 2008;1:156-63.Google Scholar
  6. 6.
    Heller GV, Herman SD, Travin MI, Baron JI, Santos-Ocampo C, Mcclellan JR. Independent prognostic value of intravenous dipyridamole with technetium-99 m sestamibi tomographic imaging in predicting cardiac events and cardiac-related hospital admissions. J Am Coll Cardiol 1995;26:1202-8.CrossRefPubMedGoogle Scholar
  7. 7.
    Arsanjani R, Xu Y, Dey D, Fish M, Dorbala S, Hayes S, et al. Improved accuracy of myocardial perfusion SPECT for the detection of coronary artery disease using a support vector machine algorithm. J Nuclear Med 2013;54:549-55.CrossRefGoogle Scholar
  8. 8.
    Bishop CM. Pattern recognition. Mach Learn 2006;128:1-58.Google Scholar
  9. 9.
    Duda RO, Hart PE, Stork DG. Pattern classification. New York: Wiley; 2012.Google Scholar
  10. 10.
    Wernick MN, Yang Y, Brankov JG, Yourganov G, Strother SC. Machine learning in medical imaging. Signal Process Mag IEEE 2010;27:25-38.CrossRefGoogle Scholar
  11. 11.
    Hastie T, Tibshirani R, Friedman J, Hastie T, Friedman J, Tibshirani R. The elements of statistical learning. Berlin: Springer; 2009.CrossRefGoogle Scholar
  12. 12.
    Hachamovitch R, Hayes SW, Friedman JD, Cohen I, Berman DS. Stress myocardial perfusion single-photon emission computed tomography is clinically effective and cost effective in risk stratification of patients with a high likelihood of coronary artery disease (CAD) but no known CAD. J Am Coll Cardiol 2004;43:200-8.CrossRefPubMedGoogle Scholar
  13. 13.
    Nakajima K, Matsuo S, Okuyama C, Hatta T, Tsukamoto K, Nishimura S, et al. Cardiac event risk in Japanese subjects estimated using gated myocardial perfusion imaging, in conjunction with diabetes mellitus and chronic kidney disease. Circ J 2012;76:168-75.CrossRefPubMedGoogle Scholar
  14. 14.
    Hachamovitch R, Hayes SW, Friedman JD, Cohen I, Berman DS. Comparison of the short-term survival benefit associated with revascularization compared with medical therapy in patients with no prior coronary artery disease undergoing stress myocardial perfusion single photon emission computed tomography. Circulation 2003;107:2900-7.CrossRefPubMedGoogle Scholar
  15. 15.
    Berman DS, Kang X, Hayes SW, Friedman JD, Cohen I, Abidov A, et al. Adenosine myocardial perfusion single-photon emission computed tomography in women compared with men: Impact of diabetes mellitus on incremental prognostic value and effect on patient management. J Am Coll Cardiol 2003;41:1125-33.CrossRefPubMedGoogle Scholar
  16. 16.
    Berman DS, Kiat H, Friedman JD, Wang FP, Van Train K, Matzer L, et al. Separate acquisition rest thallium-201/stress technetium-99 m sestamibi dual-isotope myocardial perfusion single-photon emission computed tomography: A clinical validation study. J Am Coll Cardiol 1993;22:1455-64.CrossRefPubMedGoogle Scholar
  17. 17.
    Raschka S. Python machine learning. Birmingham: Packt Publishing Ltd; 2015.Google Scholar
  18. 18.
    DeLong ER, DeLong DM, Clarke-Pearson DL. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 1988;44:837-45.CrossRefPubMedGoogle Scholar
  19. 19.
    Tibshirani R. Regression shrinkage and selection via the lasso. J R Stat Soc Ser B (Methodol) 1996;58:267-88.Google Scholar
  20. 20.
    Vapnik VN, Vapnik V. Statistical learning theory. New York: Wiley; 1998.Google Scholar
  21. 21.
    El-Naqa I, Yang Y, Wernick MN, Galatsanos NP, Nishikawa RM. A support vector machine approach for detection of microcalcifications. Med Imaging IEEE Trans 2002;21:1552-63.CrossRefGoogle Scholar
  22. 22.
    Breiman L. Random forests. Mach Learn 2001;45:5-32.CrossRefGoogle Scholar
  23. 23.
    Freund Y, Schapire RE. A desicion-theoretic generalization of on-line learning and an application to boosting. Eur Conf Comput Learn Theory. 1995. Scholar
  24. 24.
    Cox DR. Regression models and life-tables. Breakthr Stat 1992;527-541.Google Scholar
  25. 25.
    Greenland S. Modeling and variable selection in epidemiologic analysis. Am J Public Health 1989;79:340-9.CrossRefPubMedPubMedCentralGoogle Scholar
  26. 26.
    Ho TK. The random subspace method for constructing decision forests. IEEE Trans Pattern Anal Mach Intell 1998;20:832-44.CrossRefGoogle Scholar
  27. 27.
    Schapire RE. The boosting approach to machine learning: An overview. Nonlinear Estim Classif 2003;149-71.Google Scholar
  28. 28.
    Pudil P, Novovičová J, Kittler J. Floating search methods in feature selection. Pattern Recognit Lett 1994;15:1119-25.CrossRefGoogle Scholar
  29. 29.
    Scholkopf B, Smola AJ. Learning with kernels: Support vector machines, regularization, optimization, and beyond. Cambridge: MIT Press; 2001.Google Scholar
  30. 30.
    Park MY, Hastie T. L1-regularization path algorithm for generalized linear models. J R Stat Soc 2007;69:659-77.CrossRefGoogle Scholar
  31. 31.
    Niculescu-Mizil A, Caruana R. Predicting good probabilities with supervised learning. In: Proceedings of the 22nd international conference on machine learning; 2005. p. 625–632.Google Scholar
  32. 32.
    Platt J. Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Adv Large Margin Classif 1999;10:61-74.Google Scholar
  33. 33.
    Rozanski A, Gransar H, Hayes SW, Min J, Friedman JD, Thomson LE, et al. Temporal trends in the frequency of inducible myocardial ischemia during cardiac stress testing: 1991 to 2009. J Am Coll Cardiol 2013;61:1054-65.CrossRefPubMedGoogle Scholar
  34. 34.
    Mogensen UB, Ishwaran H, Gerds TA. Evaluating random forests for survival analysis using prediction error curves. J Stat Softw 2012;50:1.CrossRefPubMedPubMedCentralGoogle Scholar

Copyright information

© American Society of Nuclear Cardiology 2018

Authors and Affiliations

  • David Haro Alonso
    • 1
  • Miles N. Wernick
    • 1
  • Yongyi Yang
    • 1
  • Guido Germano
    • 2
  • Daniel S. Berman
    • 2
  • Piotr Slomka
    • 2
  1. 1.Medical Imaging Research Center, Illinois Institute of TechnologyChicagoUSA
  2. 2.Departments of Imaging and MedicineCedars-Sinai Medical CenterLos AngelesUSA

Personalised recommendations