Bayesian Network vs. Cox’s Proportional Hazard Model of PAH Risk: A Comparison

  • Jidapa KraisangkaEmail author
  • Marek J. Druzdzel
  • Lisa C. Lohmueller
  • Manreet K. Kanwar
  • James F. Antaki
  • Raymond L. Benza
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11526)


Pulmonary arterial hypertension (PAH) is a severe and often deadly disease, originating from an increase in pulmonary vascular resistance. The REVEAL risk score calculator [3] has been widely used and extensively validated by health-care professionals to predict PAH risks. The calculator is based on the Cox’s Proportional Hazard (CPH) model, a popular statistical technique used in risk estimation and survival analysis. In this study, we explore an alternative approach to the PAH patient risk assessment based on a Bayesian network (BN) model using the same variables and discretization cut points as the REVEAL risk score calculator. We applied a Tree Augmented Naïve Bayes algorithm for structure and parameter learning from a data set of 2,456 adult patients from the REVEAL registry. We compared our BN model against the original CPH-based calculator quantitatively and qualitatively. Our BN model relaxes some of the CPH model assumptions, which seems to lead to a higher accuracy (AUC = 0.77) than that of the original calculator (AUC = 0.71). We show that hazard ratios, expressing strength of influence in the CPH model, are static and insensitive to changes in context, which limits applicability of the CPH model to personalized medical care.


Bayesian networks Risk assessment Cox’s proportional hazard model Hazard ratios Pulmonary arterial hypertension 



We acknowledge the support of the National Institute of Health (1R01HL134673-01), Department of Defence (W81XWH-17-1-0556), and the Faculty of Information and Communication Technology, Mahidol University, Thailand. Implementation of this work is based on GeNIe and SMILE, a Bayesian inference engine developed at the Decision Systems Laboratory, University of Pittsburgh. It is currently a commercial product but is still available free of charge for academic research and teaching at While we are taking full responsibility for any remaining errors and shortcomings of the paper, we would like to thank Dr. Carol Zhao of Actelion Pharmaceuticals US, Inc., for her assistance in learning the TAN model from the REVEAL data set. We also thank the anonymous reviewers for their valuable input that has greatly improved the quality of this paper.


  1. 1.
    Bandyopadhyay, S., et al.: Data mining for censored time-to-event data: a Bayesian network model for predicting cardiovascular risk from electronic health record data. Data Min. Knowl. Disc. 29(4), 1033–1069 (2015)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Benza, R.L., et al.: The REVEAL registry risk score calculator in patients newly diagnosed with pulmonary arterial hypertension. CHEST 141(2), 354–362 (2012)CrossRefGoogle Scholar
  3. 3.
    Benza, R.L., et al.: Predicting survival in pulmonary arterial hypertension: insights from the Registry to Evaluate Early and Long-Term Pulmonary Arterial Hypertension Disease Management (REVEAL). Circulation 122(2), 164–172 (2010)CrossRefGoogle Scholar
  4. 4.
    Cox, D.R.: Regression models and life-tables. J. Roy. Stat. Soc. Ser. B (Methodol.) 34(2), 187–220 (1972)MathSciNetzbMATHGoogle Scholar
  5. 5.
    Friedman, N., Geiger, D., Goldszmidt, M.: Bayesian network classifiers. Mach. Learn. 29(2–3), 131–163 (1997)CrossRefGoogle Scholar
  6. 6.
    Hernán, M.A.: The hazards of hazard ratios. Epidemiology (Cambridge, Mass.) 21(1), 13 (2010)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Husmeier, D., Dybowski, R., Roberts, S.: Probabilistic Modeling in Bioinformatics and Medical Informatics. Springer, London (2005)CrossRefGoogle Scholar
  8. 8.
    Kanwar, M.K., et al.: A Bayesian model to predict survival after left ventricular assist device implantation. JACC Heart Fail. 6(9), 771–779 (2018)CrossRefGoogle Scholar
  9. 9.
    Kraisangka, J., Druzdzel, M.J.: A Bayesian network interpretation of the Cox’s proportional hazard model. Int. J. Approximate Reasoning 103, 195–211 (2018)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Kraisangka, J., Druzdzel, M.J., Benza, R.L.: A risk calculator for the pulmonary arterial hypertension based on a Bayesian network. In: Proceedings of the 13th UAI Bayesian Modeling Applications Workshop, pp. 1–6 (2016)Google Scholar
  11. 11.
    Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann Publishers Inc., San Francisco (1988)zbMATHGoogle Scholar
  12. 12.
    Štajduhar, I., Dalbelo-Bašić, B.: Learning Bayesian networks from survival data using weighting censored instances. J. Biomed. Inform. 43(4), 613–622 (2010)CrossRefGoogle Scholar
  13. 13.
    Štajduhar, I., Dalbelo-Bašić, B.: Uncensoring censored data for machine learning: a likelihood-based approach. Expert Syst. Appl. 39(8), 7226–7234 (2012)CrossRefGoogle Scholar
  14. 14.
    Zhang, Z., Reinikainen, J., Adeleke, K.A., Pieterse, M.E., Groothuis-Oudshoorn, C.G.: Time-varying covariates and coefficients in Cox regression models. Ann. Transl. Med. 6(7), 121 (2018)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Jidapa Kraisangka
    • 1
    Email author
  • Marek J. Druzdzel
    • 1
    • 2
  • Lisa C. Lohmueller
    • 3
  • Manreet K. Kanwar
    • 4
  • James F. Antaki
    • 5
  • Raymond L. Benza
    • 4
  1. 1.University of PittsburghPittsburghUSA
  2. 2.Białystok University of TechnologyBiałystokPoland
  3. 3.Carnegie Mellon UniversityPittsburghUSA
  4. 4.Cardiovascular InstituteAllegheny General HospitalPittsburghUSA
  5. 5.Cornell UniversityIthacaUSA

Personalised recommendations