A machine learning framework for predicting long-term graft survival after kidney transplantation

Abstract Kidney transplantation (KT) is an optimal treatment for end-stage renal disease (ESRD). Currently, short-term KT outcomes are indeed excellent, but long-term successful outcomes are still difficult to achieve, and improving them is crucial for kidney recipients. An early and accurate prediction of long-term graft survival helps healthcare practitioners to create a more personalized treatment plans for patients and facilitates the performance of clinical trials. In this study, we propose a machine learning framework to early predict graft survival after five years of KT and determine the most influential parameters that affect the survival. Our dataset was collected from Charles Nicolle Hospital in Tunis in Tunisia and it included pre, peri, post KT aspects. We utilized four machine learning algorithms to select the most important features: the least absolute shrinkage and selection operator logistic regression (Lasso-LR), Random Forrest (RF), Decision Tree (DT), and Chi-square (Chi-sq). We utilized three Scikit-learn functions to implement those algorithms: SelectFromModel (SFM), Recursive Feature Elimination (RFE), and SelectKBest (SKB). Five algorithms were utilized to builds prediction models based on the data groups resulted from the feature selection step: logistic regression (LR), k-nearest neighbors (KNN), extreme gradient boosting (XGB), and artificial neural network (ANN). We evaluated the models using five performance measures: accuracy, sensitivity, specificity, F1 measure, and area under the curve (AUC). XGBoost resulted the best model with the highest AUC (89.7%). It was based ten features selected by RF algorithm and SFM function. The accuracy, sensitivity, specificity, and F1 of the best model were 91.5%, 91.9%, 87.5%, and 89.6%, respectively. This study proposes a novel approach for investigating long-term allograft survival while considering the complex relationship between all KT aspects and long-term outcomes. Our framework can be used as a decision support system for Nephrologists to early detect graft status, which helps in developing safer recommendations for kidney patients and consequently obtaining positive KT outcomes and mitigating the risks of graft failure.

[1]  Forsythe,et al.  Global trends and challenges in deceased donor kidney allocation. , 2017, Kidney international.

[2]  Anjana Gosain,et al.  Handling class imbalance problem using oversampling techniques: A review , 2017, 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI).

[3]  Yueting Zhuang,et al.  Heterogeneous feature selection by group lasso with logistic regression , 2010, ACM Multimedia.

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

[5]  G. Russell,et al.  Dialysis modality and delayed graft function after cadaveric renal transplantation. , 1999, Journal of the American Society of Nephrology : JASN.

[6]  Jonathan H. Chen,et al.  Machine Learning and Prediction in Medicine - Beyond the Peak of Inflated Expectations. , 2017, The New England journal of medicine.

[7]  J. Bromberg,et al.  An update on the impact of pre-transplant transfusions and allosensitization on time to renal transplant and on allograft survival , 2013, BMC Nephrology.

[8]  D. Heisey,et al.  Association of Cytomegalovirus Disease and Acute Rejection with Graft Loss in Kidney Transplantation , 2004, Transplantation.

[9]  R. Wolfe,et al.  Long-term survival in renal transplant recipients with graft function. , 2000, Kidney international.

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

[11]  Nina Singh,et al.  Preemptive therapy versus universal prophylaxis with ganciclovir for cytomegalovirus in solid organ transplant recipients. , 2001, Clinical infectious diseases : an official publication of the Infectious Diseases Society of America.

[12]  P. Aljama,et al.  The impact of donor age on the results of renal transplantation. , 2004, Nephrology, dialysis, transplantation : official publication of the European Dialysis and Transplant Association - European Renal Association.

[13]  Alan B Leichtman,et al.  Kidney transplantation as primary therapy for end-stage renal disease: a National Kidney Foundation/Kidney Disease Outcomes Quality Initiative (NKF/KDOQITM) conference. , 2008, Clinical journal of the American Society of Nephrology : CJASN.

[14]  Yongdai Kim,et al.  Logistic LASSO regression for the diagnosis of breast cancer using clinical demographic data and the BI-RADS lexicon for ultrasonography , 2017, Ultrasonography.

[15]  T. Rimmele,et al.  Prognostic value for long-term graft survival of estimated glomerular filtration rate and proteinuria quantified at 3 months after kidney transplantation , 2020, Clinical kidney journal.

[16]  M. Zeier,et al.  Hypertension after renal transplantation , 2001, Annals of transplantation.

[17]  Ron Kohavi,et al.  Data mining tasks and methods: Classification: decision-tree discovery , 2002 .

[18]  J. Dhanapriya,et al.  Impact of acute kidney injury on renal allograft survival , 2016, Renal failure.

[19]  F. Kern,et al.  Mechanisms of human cytomegalovirus (HCMV) (re)activation and its impact on organ transplant patients , 1999, Transplant infectious disease : an official journal of the Transplantation Society.

[20]  R. Selgas,et al.  La infección por citomegalovirus postrasplante renal y pérdida del injerto a largo plazo , 2017 .

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

[22]  Ali Dag,et al.  Predicting graft survival among kidney transplant recipients: A Bayesian decision support model , 2018, Decis. Support Syst..

[23]  A. Matas,et al.  The association between acute rejection and chronic rejection in kidney transplantation. , 1999, Transplantation proceedings.

[24]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[25]  Sergey Krikov,et al.  Predicting Kidney Transplant Survival Using Tree-Based Modeling , 2007, ASAIO journal.

[26]  T. Papalia,et al.  Decisional trees in renal transplant follow-up. , 2010, Transplantation proceedings.

[27]  M. Gershwin,et al.  Role of cytomegalovirus infection in allograft rejection: a review of possible mechanisms. , 1999, Transplant Immunology.

[28]  N. A. Khovanova,et al.  Decision tree and random forest models for outcome prediction in antibody incompatible kidney transplantation , 2017, Biomed. Signal Process. Control..

[29]  Da-ping Yu,et al.  Copy number variation in plasma as a tool for lung cancer prediction using Extreme Gradient Boosting (XGBoost) classifier , 2019, Thoracic cancer.

[30]  Pramod K. Varshney,et al.  Decision tree regression for soft classification of remote sensing data , 2005 .

[31]  Jianping Gou,et al.  A generalized mean distance-based k-nearest neighbor classifier , 2019, Expert Syst. Appl..

[32]  Leon N. Cooper,et al.  Neighborhood size selection in the k-nearest-neighbor rule using statistical confidence , 2006, Pattern Recognit..

[33]  Ling-I Chen,et al.  Modification of Diet in Renal Disease (MDRD) Study and CKD Epidemiology Collaboration (CKD-EPI) Equations for Taiwanese Adults , 2014, PloS one.

[34]  David B. Leake,et al.  An Ensemble Approach to Instance-Based Regression Using Stretched Neighborhoods , 2013, FLAIRS Conference.

[35]  R. Selgas,et al.  Cytomegalovirus infection after kidney transplantation and long-term graft loss , 2017 .

[36]  G. Canaud,et al.  Factors influencing long‐term outcome after kidney transplantation , 2014, Transplant international : official journal of the European Society for Organ Transplantation.

[37]  Ana Cristina Carvalho de Matos,et al.  Hospital Admission following Acute Kidney Injury in Kidney Transplant Recipients Is Associated with a Negative Impact on Graft Function after 1-Year , 2015, PloS one.

[38]  G. Seki,et al.  Acute Kidney Injury as a Risk Factor for Transplant Graft Failure , 2014 .

[39]  N. Mousavinasab,et al.  The Impact of Acute Rejection in Kidney Transplantation on Long-Term Allograft and Patient Outcome , 2015, Nephro-urology monthly.

[40]  J. Ringers,et al.  Increased immunogenicity and cause of graft loss of old donor kidneys. , 2001, Journal of the American Society of Nephrology : JASN.

[41]  K. I. Ramachandran,et al.  Feature selection using Decision Tree and classification through Proximal Support Vector Machine for fault diagnostics of roller bearing , 2007 .

[42]  P. Bastard,et al.  Artificial Intelligence in Nephrology: Core Concepts, Clinical Applications, and Perspectives. , 2019, American journal of kidney diseases : the official journal of the National Kidney Foundation.

[43]  Martin Vingron,et al.  Predicting the outcome of renal transplantation , 2012, J. Am. Medical Informatics Assoc..

[44]  M. Linton,et al.  Atherosclerosis in chronic kidney disease: the role of macrophages , 2011, Nature Reviews Nephrology.

[45]  I. Macdougall,et al.  How important is transfusion avoidance in 2013? , 2013, Nephrology, dialysis, transplantation : official publication of the European Dialysis and Transplant Association - European Renal Association.

[46]  Bin Yu,et al.  Improving protein-protein interactions prediction accuracy using XGBoost feature selection and stacked ensemble classifier , 2020, Comput. Biol. Medicine.

[47]  V. Jha,et al.  A single number for advocacy and communication-worldwide more than 850 million individuals have kidney diseases. , 2019, Nephrology, dialysis, transplantation : official publication of the European Dialysis and Transplant Association - European Renal Association.

[48]  Michael E Brier,et al.  Prediction of delayed renal allograft function using an artificial neural network. , 2003, Nephrology, dialysis, transplantation : official publication of the European Dialysis and Transplant Association - European Renal Association.

[49]  D. Mendrinos,et al.  Hypertension in the elderly. , 2012, World journal of cardiology.

[50]  P. Reinke,et al.  Intensive blood pressure control is associated with improved patient and graft survival after renal transplantation , 2019, Scientific Reports.

[51]  Thomas Blaschke,et al.  Evaluation of Feature Selection Methods for Object-Based Land Cover Mapping of Unmanned Aerial Vehicle Imagery Using Random Forest and Support Vector Machine Classifiers , 2017, ISPRS Int. J. Geo Inf..

[52]  M. Joffe,et al.  Arterial hypertension and renal allograft survival. , 2000, JAMA.

[53]  L. Mateu,et al.  Acute rejection and late renal transplant failure: Risk factors and prognosis , 2004 .

[54]  Muhammad Hisyam Lee,et al.  Penalized logistic regression with the adaptive LASSO for gene selection in high-dimensional cancer classification , 2015, Expert Syst. Appl..

[55]  Nicole White,et al.  Machine learning in predicting graft failure following kidney transplantation: A systematic review of published predictive models , 2019, Int. J. Medical Informatics.

[56]  A. Ojo.  Cardiovascular Complications After Renal Transplantation and Their Prevention , 2006, Transplantation.

[57]  R. Riggio,et al.  Hypertension in kidney transplant recipients. Effect on long-term renal allograft survival. , 1989, American journal of hypertension.

[58]  D. Serón,et al.  Long-term graft function changes in kidney transplant recipients , 2010, NDT plus.

[59]  Leila Shahmoradi,et al.  Comparing Three Data Mining Methods to Predict Kidney Transplant Survival , 2016, Acta informatica medica : AIM : journal of the Society for Medical Informatics of Bosnia & Herzegovina : casopis Drustva za medicinsku informatiku BiH.

[60]  J. Schold,et al.  Lack of Improvement in Renal Allograft Survival Despite a Marked Decrease in Acute Rejection Rates Over the Most Recent Era , 2004, American journal of transplantation : official journal of the American Society of Transplantation and the American Society of Transplant Surgeons.

[61]  W. Vaughn,et al.  COMPARATIVE EFFECTS OF PREGNANCY, TRANSFUSION, AND PRIOR GRAFT REJECTION ON SENSITIZATION AND RENAL TRANSPLANT RESULTS , 1982, Transplantation.

[62]  Ying Ju,et al.  Predicting Diabetes Mellitus With Machine Learning Techniques , 2018, Front. Genet..

[63]  R. Akbari,et al.  Classification Models to Predict Survival of Kidney Transplant Recipients Using Two Intelligent Techniques of Data Mining and Logistic Regression , 2017, International journal of organ transplantation medicine.

[64]  Tom Dhaene,et al.  Prediction of delayed graft function after kidney transplantation: comparison between logistic regression and machine learning methods , 2015, BMC Medical Informatics and Decision Making.

[65]  Matthew Franchetti,et al.  Bayes Net Classifiers for Prediction of Renal Graft Status and Survival Period , 2010 .

[66]  F. Moreso,et al.  Donor age and delayed graft function as predictors of renal allograft survival in rejection-free patients. , 1999, Nephrology, dialysis, transplantation : official publication of the European Dialysis and Transplant Association - European Renal Association.

[67]  A. Goldfarb-Rumyantzev,et al.  Prediction of 3‐yr cadaveric graft survival based on pre‐transplant variables in a large national dataset , 2003, Clinical transplantation.

[68]  J. Park,et al.  The impact of early and late acute rejection on graft survival in renal transplantation , 2015, Kidney research and clinical practice.

[69]  C. Ahn,et al.  Chronic asymptomatic pyuria precedes overt urinary tract infection and deterioration of renal function in autosomal dominant polycystic kidney disease , 2013, BMC Nephrology.

[70]  Mohamed Ghoneim,et al.  Prediction of Graft Survival of Living-Donor Kidney Transplantation: Nomograms or Artificial Neural Networks? , 2008, Transplantation.

[71]  S. Bhandari,et al.  The role of patient portals in enhancing self-care in patients with renal conditions , 2019, Clinical kidney journal.

[72]  M. Stegall,et al.  Developing New Immunosuppression for the Next Generation of Transplant Recipients: The Path Forward , 2016, American journal of transplantation : official journal of the American Society of Transplantation and the American Society of Transplant Surgeons.

[73]  M. Tonelli,et al.  Incidence and consequences of acute kidney injury in kidney transplant recipients. , 2012, American journal of kidney diseases : the official journal of the National Kidney Foundation.

[74]  Gunhee Kim,et al.  A Machine Learning Approach Using Survival Statistics to Predict Graft Survival in Kidney Transplant Recipients: A Multicenter Cohort Study , 2017, Scientific Reports.

[75]  N. Patino-Jaramillo,et al.  Acute Kidney Injury in Hospitalized Kidney Transplant Recipients. , 2020, Transplantation proceedings.

[76]  Alok Kumar,et al.  Ensemble Learning for AI Developers: Learn Bagging, Stacking, and Boosting Methods with Use Cases , 2020 .