Survival of Dialysis Patients Using Random Survival Forest Model in Low-Dimensional Data with Few-Events

Document Type: Original Article


1 Student in Biostatistics, Department of Biostatistics and Epidemiology, Kerman University of Medical Sciences, Kerman, Iran

2 Professor of Biostatistics, Physiology Research Center, Institute of Basic and Clinical Physiology Sciences & Modeling in Health Research Center, Faculty of Health, Institute for Futures Studies in Health, Kerman University of Medical Sciences, Kerman, Iran

3 Assistant Professor of Health Education and Health Promotion, Mother and Child Welfare Research Center, Hormozgan University of Medical Sciences, Bandar Abbas, Iran

4 Professor of Biostatistics, Modeling in Health Research Center, Institute for Futures Studies in Health, Kerman University of Medical Sciences, Kerman, Iran


Background:Dialysis is a process for eliminating extra uremic fluids of patients with chronic renal failure. The present study aimed to determine the variables that influence the survival of dialysis patients using random survival forest model (RSFM) in low-dimensional data with low events per variable (EPV).
Methods:In this historical cohort study, information was collected from 252 dialysis patients in Bandar Abbas hospitals, Iran. The survival time of the patients was calculated in years from the onset of dialysis to death or until the end of the study in 2016. RSFM was used as the number of events per variable (EPV) was low. The data collected from 252 patients were randomly divided into training and testing sets, and this process was repeated 100 times. C-index and Brier Score (BS) were used to assess the performance of the model in the test set.
 Results: In this study, 35 (13.9%) mortality cases were observed. Based on the findings, the mean C-index value in training and testing sets was 0.640 and 0.687, and the mean BS value in training and testing sets was 0.017 and 0.023, respectively. The results of the RSFM revealed that BMI, education, occupation, dialysis duration, number of dialysis sessions and age at dialysis onset were the most important factors.
Conclusion: RSFM can be used to determine the survival of dialysis patients and manage low-dimensional data with few-events if the researcher desires to select a nonparametric model.


  1. Shiba N, Shimokawa H. Chronic kidney disease and heart failure—Bidirectional close link and common therapeutic goal. J Cardiol 2011; 57(1):8-17.
  2. Lesan Pezshki M, Matini SM, Tagadosi M, Moosavi SG. Evaluation of the sufficiency of dialysis in patients with renal disease in Kashan from 1997 to 1998. FEYZ 2001; 5(1):82-7. [In Persian].
  3. Arefzadeh A, Lessanpezeshki M, Seifi S. The cost of hemodialysis in Iran. Saudi J Kidney Dis Transpl 2009; 20(2):307-11.
  4. Aghighi M, Heidary Rouchi A, Zamyadi M, Mahdavi-Mazdeh M, Rajolani H, Ahrabi S, et al. Dialysis in Iran. Iran J Kidney Dis 2008; 2(1):11-5.
  5. Esmaili H, Majlessi F, Montazeri A, Sadeghi R, Nedjat S, Zeinali J. Dialysis adequacy and necessity of implement health education models to its promotion in Iran. International Journal of Medical Research and Health Sciences 2016; 5(10):116-21.
  6. Ogundimu EO, Altman DG, Collins GS. Adequate sample size for developing prediction models is not simply related to events per variable. J Clin Epidemiol 2016; 76:175-82.
  7. Ojeda FM, Müller C, Börnigen D, Tregouet DA, Schillert A, Heinig M, et al. Comparison of Cox model methods in a low-dimensional setting with few events. Genomics, Proteomics & Bioinformatics 2016; 14(4):235-43.
  8. Ishwaran H, Kogalur UB, Blackstone EH, Lauer MS. Random survival forests. The Annals of Applied Statistics 2008; 2(3):841-60.
  9. Ishwaran H, Kogalur UB. Package ‘randomForestSRC’. [cited ?????] Available from:
  10. Ambler G, Seaman S, Omar RZ. An evaluation of penalised survival methods for developing prognostic models with rare events. Statistics in Medicine 2012; 31(11-12):1150-61.
  11. Gerds TA, Cai T, Schumacher M. The performance of risk prediction models. Biom J 2008; 50(4):457-79.
  12. Ishwaran H, Kogalur UB, Chen X, Minn AJ. Random survival forests for high‐dimensional data. Statistical Analysis and Data Mining 2011; 4(1):115-32.
  13. Hsich E, Gorodeski EZ, Blackstone EH, Ishwaran H, Lauer MS. Identifying important risk factors for survival in patient with systolic heart failure using random survival forests. Circ Cardiovasc Qual Outcomes 2011; 4(1):39-45.
  14. Ishwaran H, Kogalur UB, Gorodeski EZ, Minn AJ, Lauer MS. High-dimensional variable selection for survival data. J Am Stat Assoc 2010; 105(489):205-17.
  15. Hamidi O, Poorolajal J, Farhadian M, Tapak L. Identifying important risk factors for survival in kidney graft failure patients using random survival forests. Iran J Public Health 2016; 45(1):27-33.
  16. Mark E, Goldsman D, Gurbaxani B, Keskinocak P, Sokol J. Using machine learning and an ensemble of methods to predict kidney transplant survival. PloS One 2019; 14(1):e0209068.
  17. Nasejje JB, Mwambi H. Application of random survival forests in understanding the determinants of under-five child mortality in Uganda in the presence of covariates that satisfy the proportional and non-proportional hazards assumption. BMC Res Notes 2017; 10(1):459.
  18. Heaf J, Nielsen AH, Hansen HP. Long-term haemodialysis survival. Clin Kidney J 2012; 5(2):168-9.
  19. Iseki K, Kawazoe N, Osawa A, Fukiyama K. Survival analysis of dialysis patients in Okinawa, Japan (1971–1990). Kidney Int 1993; 43(2):404-9.
  20. Huang CC, Cheng KF, Wu HD. Survival analysis: comparing peritoneal dialysis and hemodialysis in Taiwan. Perit Dial Int 2008; 28(Suppl 3):S15-20.
  21. Abbott KC, Glanton CW, Trespalacios FC, Oliver DK, Ortiz MI, Agodoa LY, et al. Body mass index, dialysis modality, and survival: analysis of the United States renal data system dialysis morbidity and mortality wave II study. Kidney Int 2004; 65(2):597-605.
  22. Soleymanian T, Niyazi H, Dehkordi SNJ, Savaj S, Argani H, Najafi I. Predictors of clinical outcomes in hemodialysis patients: a multicenter observational study. Iran J Kidney Dis 2017; 11(3):229-36.
  23. Dada SA, Inubile AJ, Thomas AA, Dada OE, Akinyemi RO. Survival Pattern of Patients on Maintenance Haemodialysis for End Stage Renal Disease in a Nigerian Dialysis Centre. Archives of Nephrology and Urology 2019; 2:001-12.
  24. Beladi-Mousavi SS, Alemzadeh-Ansari MJ, Alemzadeh-Ansari MH, Beladi-Mousavi M. Long-term survival of patients with end-stage renal disease on maintenance hemodialysis: a multicenter study in Iran. Iran J Kidney Dis 2012; 6(6):452-6.
  25. Akhlaghi AA, Najafi I, Mahmoodi M, Shojaee A, Yousefifard M, Hosseini M. Survival analysis of Iranian patients undergoing continuous ambulatory peritoneal dialysis using cure model. J Res Health Sci 2013; 13(1):32-6.
  26. Rahimlu M, Shab-Bidar S, Djafarian K. Body mass index and all-cause mortality in chronic kidney disease: a dose–response meta-analysis of observational studies. J Ren Nutr 2017; 27(4):225-32.
  27. Vahedi M, Mahmoodi M, Mohammad K, Ossareh S, Zeraati H. What is the best parametric survival models for analyzing hemodialysis data? Glob J Health Sci 2016; 8(10):56161.
  28. Kusztal M, Nowak K, Magott-Procelewska M, Weyde W, Penar J. Evaluation of health-related quality of life in dialysis patients. Personal experience using questionnaire SF-36. Pol Merkur Lekarski 2003; 14(80):113-7. [In Polish]
  29. Shabankhani B, Kazemnejad A, Zaeri F, Espahbodi F, Ahmadi MH, Mirkazemi R. Survival factors in patients with end-stage renal disease in Mazandaran Province, Iran. Iran J Kidney Dis 2016; 10(2):79-84.
  30. Goh A, Vathsala A. Native renal cysts and dialysis duration are risk factors for renal cell carcinoma in renal transplant recipients. Am J Transplant 2011; 11(1):86-92.
  31. Amini M, Aghighi M, Masoudkabir F, Zamyadi M, Norouzi S, Rajolani H, et al. Hemodialysis adequacy and treatment in Iranian patients: a national multicenter study. Iran J Kidney Dis 2011; 5(2):103-9.
  32. Chandrashekar A, Ramakrishnan S, Rangarajan D. Survival analysis of patients on maintenance hemodialysis. Indian J Nephrol 2014; 24(4):206-13.
  33. Shafiee M, Chamanian P, Shaker P, Shahideh Y, Broumand B. The impact of hemodialysis frequency and duration on blood pressure management and quality of life in end-stage renal disease patients. Healthcare (Basel) 2017; 5(3):E52.
  34. Roudbari M, Foruzandeh F, Roudbari S. Survival analysis of dialysis patients and its associated factors in Zahedan, Iran. Saudi Med J 2010; 31(1):91-3.