Predicting heart transplantation outcomes through data analytics

Predicting the survival of heart transplant patients is an important, yet challenging problem since it plays a crucial role in understanding the matching procedure between a donor and a recipient. Data mining models can be used to effectively analyze and extract novel information from large/complex transplantation datasets. The objective of this study is to predict the 1-, 5-, and 9-year patient's graft survival following a heart transplant surgery via the deployment of analytical models that are based on four powerful classification algorithms (i.e. decision trees, artificial neural networks, support vector machines, and logistic regression). Since the datasets used in this study has a much larger number of survival cases than deaths for 1- and 5-year survival analysis and vice versa for 9-year survival analysis, random under sampling (RUS) and synthetic minority over-sampling (SMOTE) are employed to overcome the data-imbalance problems. The results indicate that logistic regression combined with SMOTE achieves the best classification for the 1-, 5-, and 9-year outcome prediction, with area-under-the-curve (AUC) values of 0.624, 0.676, and 0.838, respectively. By applying sensitivity analysis to the data analytical models, the most important predictors and their associated contribution for the 1-, 5-, and 9-year graft survival of heart transplant patients are identified. By doing so, variables, whose importance changes over time, are differentiated. Not only this proposed hybrid approach gives superior results over the literature but also the models and identification of the variables present important retrospective findings, which can be the basis for a prospective medical study. A data-driven approach for predicting survival outcomes at multiple time-points is developed.The method successfully predicted short-, mid-, & long-term heart transplantation outcomes.The proposed method is unique in that it fills an important gap in the published literature.The approach is generic so it can be applied to other organ transplantation cases.

[1]  Scott A. Brubaker,et al.  Results of the clinical donor case and quality system case workshops of the European Association of Tissue Banks annual meeting 2009 , 2011, Cell and Tissue Banking.

[2]  Andrew Kusiak,et al.  Predicting survival time for kidney dialysis patients: a data mining approach , 2005, Comput. Biol. Medicine.

[3]  Hilde Beele,et al.  Physical examination of the potential tissue donor, what does literature tell us? , 2008, Cell and Tissue Banking.

[4]  W. Weimar,et al.  Population pharmacokinetics of cyclosporine in kidney and heart transplant recipients and the influence of ethnicity and genetic polymorphisms in the MDR‐1, CYP3A4, and CYP3A5 genes , 2004, Clinical pharmacology and therapeutics.

[5]  Dong-Ling Xu,et al.  A belief rule-based decision support system for clinical risk assessment of cardiac chest pain , 2012, Eur. J. Oper. Res..

[6]  Josef Stehlik,et al.  The Registry of the International Society for Heart and Lung Transplantation: Thirtieth Official Adult Heart Transplant Report--2013; focus theme: age. , 2013, The Journal of heart and lung transplantation : the official publication of the International Society for Heart Transplantation.

[7]  Roberto Somolinos,et al.  Heart failure in the family practice: a study of the prevalence and co-morbidity. , 2011, Family practice.

[8]  James W Long,et al.  Multivariate predictors of heart transplantation outcomes in the era of chronic mechanical circulatory support. , 2007, The Annals of thoracic surgery.

[9]  Afshin Jamshidi,et al.  A new dynamic integrated framework for surgical patients' prioritization considering risks and uncertainties , 2016, Decis. Support Syst..

[10]  Josef Stehlik,et al.  The Registry of the International Society for Heart and Lung Transplantation: 29th official adult heart transplant report--2012. , 2012, The Journal of heart and lung transplantation : the official publication of the International Society for Heart Transplantation.

[11]  Diane J. Cook,et al.  RACOG and wRACOG: Two Probabilistic Oversampling Techniques , 2015, IEEE Transactions on Knowledge and Data Engineering.

[12]  J. Kiley,et al.  How the National Heart, Lung, and Blood Institute (NHLBI) Develops Research Priorities and Supports Critical Care Research , 2012, Physical Therapy.

[13]  Robert C. Holte,et al.  C4.5, Class Imbalance, and Cost Sensitivity: Why Under-Sampling beats Over-Sampling , 2003 .

[14]  Rodney X. Sturdivant,et al.  Logistic Regression for Matched Case‐Control Studies , 2005 .

[15]  D. McPhee,et al.  Predicting cytomegalovirus disease after renal transplantation: an artificial neural network approach , 1999, Int. J. Medical Informatics.

[16]  Michael J. Pazzani,et al.  Reducing Misclassification Costs , 1994, ICML.

[17]  Amir Hassan Zadeh,et al.  Predicting overall survivability in comorbidity of cancers: A data mining approach , 2015, Decis. Support Syst..

[18]  Victoria J. Hodge,et al.  A Survey of Outlier Detection Methodologies , 2004, Artificial Intelligence Review.

[19]  Ashish S Shah,et al.  What predicts long-term survival after heart transplantation? An analysis of 9,400 ten-year survivors. , 2012, The Annals of thoracic surgery.

[20]  G. W. Davis,et al.  Sensitivity analysis in neural net solutions , 1989, IEEE Trans. Syst. Man Cybern..

[21]  Yoshifumi Naka,et al.  Who is the high-risk recipient? Predicting mortality after heart transplant using pretransplant donor and recipient risk factors. , 2011, The Annals of thoracic surgery.

[22]  L. Boschiero,et al.  An objective method for detecting time‐dependent effects in graft survival , 2000, Transplant international : official journal of the European Society for Organ Transplantation.

[23]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[24]  Dimitris Kanellopoulos,et al.  Handling imbalanced datasets: A review , 2006 .

[25]  Tai-Hsi Wu,et al.  Using data mining techniques to predict hospitalization of hemodialysis patients , 2011, Decis. Support Syst..

[26]  Jiawei Han,et al.  Data Mining: Concepts and Techniques , 2000 .

[27]  Hongnian Yu,et al.  A combination selection algorithm on forecasting , 2014, Eur. J. Oper. Res..

[28]  R. Clemen.  Combining forecasts: A review and annotated bibliography , 1989 .

[29]  Ayan R Patel,et al.  Influence of donor cocaine use on outcome after cardiac transplantation: analysis of the United Network for Organ Sharing Thoracic Registry. , 2008, The Journal of heart and lung transplantation : the official publication of the International Society for Heart Transplantation.

[30]  A. Singhal,et al.  Impact of donor cause of death on transplant outcomes: UNOS registry analysis. , 2009, Transplantation Proceedings.

[31]  Vicenç Torra,et al.  Trends in Information fusion in Data Mining , 2003 .

[32]  Ajay K Israni,et al.  Hepatitis C virus seropositivity in organ donors and survival in heart transplant recipients. , 2006, JAMA.

[33]  John F. Hurdle,et al.  Single and multiple time-point prediction models in kidney transplant outcomes , 2008, J. Biomed. Informatics.

[34]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[35]  J.C. Principe,et al.  Innovating adaptive and neural systems instruction with interactive electronic books , 2000, Proceedings of the IEEE.

[36]  Shih-Jen Hwang,et al.  The Postmortem Sociomedical Interview: Uncertainty in Confirming Infectious Disease Risks of Young Tattooed Donors , 2002, Cornea.

[37]  S. Gunn.  Support Vector Machines for Classification and Regression , 1998 .

[38]  Dipin Gupta,et al.  Effect of older donor age on risk for mortality after heart transplantation. , 2004, The Annals of thoracic surgery.

[39]  Stefano Tarantola,et al.  Sensitivity Analysis in Practice: A Guide to Assessing Scientific Models , 2004 .

[40]  Kirk R. Kanter,et al.  The effect of age, diagnosis, and previous surgery in children and adults undergoing heart transplantation for congenital heart disease. , 2009, Journal of the American College of Cardiology.

[41]  G. Laufer,et al.  Pre- and early postoperative risk factors for death after cardiac transplantation: A single center analysis , 2000, Transplant international : official journal of the European Society for Organ Transplantation.

[42]  A. Saltelli,et al.  Making best use of model evaluations to compute sensitivity indices , 2002 .

[43]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[44]  Josef Stehlik,et al.  Interactions among donor characteristics influence post-transplant survival: a multi-institutional analysis. , 2010, The Journal of heart and lung transplantation : the official publication of the International Society for Heart Transplantation.

[45]  S. Geller,et al.  The Influence of Psychosocial Factors on Heart Transplantation Decisions and Outcomes , 1997, Journal of transplant coordination : official publication of the North American Transplant Coordinators Organization.

[46]  Julien Clinton Sprott,et al.  Artificial neural networks: powerful tools for modeling chaotic behavior in the nervous system , 2014, Front. Comput. Neurosci..

[47]  Kevin N. Gurney,et al.  An introduction to neural networks , 2018 .

[48]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.

[49]  Andreas Graefe,et al.  Combining Forecasts: An Application to Elections , 2013 .

[50]  Gustavo E. A. P. A. Batista,et al.  A study of the behavior of several methods for balancing machine learning training data , 2004, SKDD.

[51]  Bruce Kaplan,et al.  Transplantation: Neural networks for predicting graft survival , 2009, Nature Reviews Nephrology.

[52]  V. Roger,et al.  The Heart Failure Epidemic , 2010, International journal of environmental research and public health.

[53]  Gongping Yang,et al.  On the Class Imbalance Problem , 2008, 2008 Fourth International Conference on Natural Computation.

[54]  W. Boyd,et al.  The role of donor age and ischemic time on survival following orthotopic heart transplantation. , 1999, The Journal of heart and lung transplantation : the official publication of the International Society for Heart Transplantation.

[55]  B Efron,et al.  Infectious complications among 620 consecutive heart transplant patients at Stanford University Medical Center. , 2001, Clinical infectious diseases : an official publication of the Infectious Diseases Society of America.

[56]  Vicenc Torra,et al.  Information Fusion in Data Mining , 2003 .

[57]  Dursun Delen,et al.  Predicting the graft survival for heart-lung transplantation patients: An integrated data mining methodology , 2009, Int. J. Medical Informatics.

[58]  Haibo He,et al.  Learning from Imbalanced Data , 2009, IEEE Transactions on Knowledge and Data Engineering.

[59]  C. Goodman.  United Network for Organ Sharing , 1988 .

[60]  Stuart Russell,et al.  Listing criteria for heart transplantation: International Society for Heart and Lung Transplantation guidelines for the care of cardiac transplant candidates--2006. , 2006, The Journal of heart and lung transplantation : the official publication of the International Society for Heart Transplantation.

[61]  P Dirschedl,et al.  Analysis of time-dependent covariates in failure time data. , 1999, Statistics in medicine.

[62]  H. Tsubouchi,et al.  Algorithm to determine the outcome of patients with acute liver failure: a data-mining analysis using decision trees , 2012, Journal of Gastroenterology.

[63]  Samuel Jacob,et al.  Is bicaval orthotopic heart transplantation superior to the biatrial technique? , 2009, Interactive cardiovascular and thoracic surgery.

[64]  Dursun Delen,et al.  Development of a structural equation modeling-based decision tree methodology for the analysis of lung transplantations , 2011, Decis. Support Syst..

[65]  P A Shapiro,et al.  Psychosocial evaluation and prediction of compliance problems and morbidity after heart transplantation. , 1995, Transplantation.

[66]  Ali Dag,et al.  A probabilistic data-driven framework for scoring the preoperative recipient-donor heart transplant survival , 2016, Decis. Support Syst..

[67]  Yi Yang,et al.  Personal health indexing based on medical examinations: A data mining approach , 2016, Decis. Support Syst..