Development of Predictive Models for Continuous Flow Left Ventricular Assist Device Patients using Bayesian Networks
DOI:
https://doi.org/10.6000/1929-6029.2014.03.04.11Keywords:
Risk Stratification, Heart Failure, Bayesian, Decision Support, Prognosis, VAD, Risk Score.Abstract
Background: Existing prognostic tools for patient selection for ventricular assist devices (VADs) such as the Destination Therapy Risk Score (DTRS) and newly published HeartMate II Risk Score (HMRS) have limited predictive ability, especially with the current generation of continuous flow VADs (cfVADs). This study aims to use a modern machine learning approach, employing Bayesian Networks (BNs), which overcomes some of the limitations of traditional statistical methods.
Methods: Retrospective data from 144 patients at Allegheny General Hospital and Integris Health System from 2007 to 2011 were analyzed. 43 data elements were grouped into four sets: demographics, laboratory tests, hemodynamics, and medications. Patients were stratified by survival at 90 days post LVAD.
Results: The independent variables were ranked based on their predictive power and reduced to an optimal set of 10: hematocrit, aspartate aminotransferase, age, heart rate, transpulmonary gradient, mean pulmonary artery pressure, use of diuretics, platelet count, blood urea nitrogen and hemoglobin. Two BNs, Naïve Bayes (NB) and Tree-Augmented Naïve Bayes (TAN) outperformed the DTRS in identifying low risk patients (specificity: 91% and 93% vs. 78%) and outperformed HMRS predictions of high risk patients (sensitivity: 80% and 60% vs. 25%). Both models were more accurate than DTRS and HMRS (90% vs. 73% and 84%), Kappa (NB: 0.56 TAN: 0.48, DTRS: 0.14, HMRS: 0.22), and AUC (NB: 80%, TAN: 84%, DTRS: 59%, HMRS: 59%).
Conclusion: The Bayesian Network models developed in this study consistently outperformed the DTRS and HMRS on all metrics. An added advantage is their intuitive graphical structure that closely mimics natural reasoning patterns. This warrants further investigation with an expanded patient cohort, and inclusion of adverse event outcomes.
References
Lietz K, Miller LW. Destination therapy: Current results and future promise. Seminars in thoracic and cardiovascular surgery 2008; 20(3): 225-33. http://dx.doi.org/10.1053/j.semtcvs.2008.08.004 DOI: https://doi.org/10.1053/j.semtcvs.2008.08.004
Bonde P, Dew MA, Meyer D, Tallaj JJ, Martin T, Hollifield KA, et al. 4 national trends in readmission(rea) rates following left ventricular assist device (lvad) therapy. The Journal of heart and lung transplantation: the official publication of the International Society for Heart Transplantation 2011; 30(4): S9. DOI: https://doi.org/10.1016/j.healun.2011.01.011
Rose EA, Frazier OH. Resurrection after mechanical circulatory support. Circulation 1997; 96(2): 393-5.
Schocken DD, Arrieta MI, Leaverton PE, Ross EA. Prevalence and mortality rate of congestive heart failure in the united states. J Am Coll Cardiol 1992; 20(2): 301-6. http://dx.doi.org/10.1016/0735-1097(92)90094-4 DOI: https://doi.org/10.1016/0735-1097(92)90094-4
Murali S. Mechanical circulatory support with the novacor lvas: World-wide clinical results. The Thoracic and cardiovascular surgeon 1999; 47 Suppl 2: 321-5. http://dx.doi.org/10.1055/s-2007-1013191 DOI: https://doi.org/10.1055/s-2007-1013191
Miller LW. Left ventricular assist devices are underutilized. Circulation 2011; 123(14): 1552-8. http://dx.doi.org/10.1161/CIRCULATIONAHA.110.958991 DOI: https://doi.org/10.1161/CIRCULATIONAHA.110.958991
Stewart GC, Stevenson LW. Keeping left ventricular assist device acceleration on track. Circulation 2011; 123(14): 1559-68. http://dx.doi.org/10.1161/CIRCULATIONAHA.110.982512 DOI: https://doi.org/10.1161/CIRCULATIONAHA.110.982512
Teuteberg JJ, Ewald GA, Adamson RM, Lietz K, Miller LW, Tatooles AJ, et al. Risk assessment for continuous flow left ventricular assist devices: Does the destination therapy risk score work? J Am Coll Cardiol 2012; 60(1): 44-51. http://dx.doi.org/10.1016/j.jacc.2012.02.032 DOI: https://doi.org/10.1016/j.jacc.2012.02.032
Lietz K, Long JW, Kfoury AG, Slaughter MS, Silver MA, Milano CA, et al. Outcomes of left ventricular assist device implantation as destination therapy in the post-rematch era - implications for patient selection. Circulation 2007; 116(5): 497-505. http://dx.doi.org/10.1161/CIRCULATIONAHA.107.691972 DOI: https://doi.org/10.1161/CIRCULATIONAHA.107.691972
Cowger J, Sundareswaran K, Rogers JG, Park SJ, Pagani FD, Bhat G, et al. Predicting survival in patients receiving
continuous flow left ventricular assist devicesthe heartmate ii risk score. J Am Coll Cardiol 2013; 61(3): 313-21. http://dx.doi.org/10.1016/j.jacc.2012.09.055 DOI: https://doi.org/10.1016/j.jacc.2012.09.055
Santelices LC, Wang Y, Severyn D, Druzdzel MJ, Kormos RL, Antaki JF. Development of a hybrid decision support model for optimal ventricular assist device weaning. The Annals of thoracic surgery 2010; 90(3): 713-20. http://dx.doi.org/10.1016/j.athoracsur.2010.03.073 DOI: https://doi.org/10.1016/j.athoracsur.2010.03.073
Wang Y, Simon MA, Bonde P, Harris BU, Teuteberg JJ, Kormos RL, et al. Decision tree for adjuvant right ventricular support in patients receiving a left ventricular assist device. J Heart Lung Transplant 2012; 31(2): 140-9. http://dx.doi.org/10.1016/j.healun.2011.11.003 DOI: https://doi.org/10.1016/j.healun.2011.11.003
Wang Y, Simon M, Bonde P, Harris BU, Teuteberg JJ, Kormos RL, et al. Prognosis of right ventricular failure in patients with left ventricular assist device based on decision tree with smote. IEEE transactions on information technology in biomedicine: a publication of the IEEE Engineering in Medicine and Biology Society 2012; 16(3): 383-90. http://dx.doi.org/10.1109/TITB.2012.2187458 DOI: https://doi.org/10.1109/TITB.2012.2187458
Wang Y, Rose CP, Ferreira A, McNamara DM, Kormos RL, Antaki JF. A classification approach for risk prognosis of patients on mechanical ventricular assistance. Proceedings of the International Conference on Machine Learning and Applications International Conference on Machine Learning and Applications 2010: 293-8. DOI: https://doi.org/10.1109/ICMLA.2010.50
Pearl J. Probabilistic reasoning in intelligent systems: Networks of plausible inference: Morgan Kaufmann; 1988. DOI: https://doi.org/10.1016/B978-0-08-051489-5.50008-4
John GH, Langley P, editors. Estimating continuous distributions in bayesian classifiers. Proceedings of the Eleventh conference on Uncertainty in artificial intelligence; 1995: Morgan Kaufmann Publishers Inc.
Friedman N, Geiger D, Goldszmidt M. Bayesian network classifiers. Machine Learning 1997; 29(2-3): 131-63. http://dx.doi.org/10.1023/A:1007465528199 DOI: https://doi.org/10.1023/A:1007465528199
Chow C, Liu C. Approximating discrete probability distributions with dependence trees. Information Theory, IEEE Transactions on 1968; 14(3): 462-7. http://dx.doi.org/10.1109/TIT.1968.1054142 DOI: https://doi.org/10.1109/TIT.1968.1054142
Heckerman D. A tutorial on learning with bayesian networks: Springer; 1998. DOI: https://doi.org/10.1007/978-94-011-5014-9_11
Fisher RA. Statistical methods for research workers 1934.
Kaplan EL, Meier P. Nonparametric-estimation from incomplete observations. J Am Stat Assoc 1958; 53(282): 457-81. http://dx.doi.org/10.1080/01621459.1958.10501452 DOI: https://doi.org/10.1080/01621459.1958.10501452
Ashby D. Bayesian statistics in medicine: A 25 year review. Statistics in medicine 2006; 25(21): 3589-631. http://dx.doi.org/10.1002/sim.2672 DOI: https://doi.org/10.1002/sim.2672
Hoot N, Aronsky D, editors. Using bayesian networks to predict survival of liver transplant patients. AMIA annual symposium proceedings; 2005: American Medical Informatics Association.
Lucas P, editor. Bayesian networks in medicine: A model-based approach to medical decision making. Proceedings of the EUNITE workshop on Intelligent Systems in patient Care; 2001.
Eom J-H, Kim S-C, Zhang B-T. Aptacdss-e: A classifier ensemble-based clinical decision support system for cardiovascular disease level prediction. Expert Systems with Applications 2008; 34(4): 2465-79. http://dx.doi.org/10.1016/j.eswa.2007.04.015 DOI: https://doi.org/10.1016/j.eswa.2007.04.015
Sadeghi S, Barzi A, Sadeghi N, King B. A bayesian model for triage decision support. International Journal of Medical Informatics 2006; 75(5): 403-11. http://dx.doi.org/10.1016/j.ijmedinf.2005.07.028 DOI: https://doi.org/10.1016/j.ijmedinf.2005.07.028
Gevaert O, De Smet F, Timmerman D, Moreau Y, De Moor B. Predicting the prognosis of breast cancer by integrating clinical and microarray data with bayesian networks. Bioinformatics 2006; 22(14): e184-e90. DOI: https://doi.org/10.1093/bioinformatics/btl230
Charitos T, van der Gaag LC, Visscher S, Schurink KA, Lucas PJ. A dynamic bayesian network for diagnosing ventilator-associated pneumonia in icu patients. Expert Systems with Applications 2009; 36(2): 1249-58. http://dx.doi.org/10.1016/j.eswa.2007.11.065 DOI: https://doi.org/10.1016/j.eswa.2007.11.065
Holman WL, Kormos RL, Naftel DC, Miller MA, Pagani FD, Blume E, et al. Predictors of death and transplant in patients with a mechanical circulatory support device: A multi-institutional study. The Journal of Heart and Lung Transplantation 2009; 28(1): 44-50. http://dx.doi.org/10.1016/j.healun.2008.10.011 DOI: https://doi.org/10.1016/j.healun.2008.10.011
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2014 Natasha A. Loghmanpour, Manreet K. Kanwar, Raymond L. Benza, Srinivas Murali, James F. Antaki
This work is licensed under a Creative Commons Attribution 4.0 International License.
Policy for Journals/Articles with Open Access
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are permitted and encouraged to post links to their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
Policy for Journals / Manuscript with Paid Access
Authors who publish with this journal agree to the following terms:
- Publisher retain copyright .
- Authors are permitted and encouraged to post links to their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work .
