Author Credentials

Zeid Khitan MD Alexis D. Jacob MD Courtney Balentine MD Adam N. Jacob BS Juan R. Sanabria MD Joseph I. Shapiro MD




We examined machine learning methods to predict death within six months using data derived from the United States Renal Data System (USRDS). We specifically evaluated a generalized linear model, a support vector machine, a decision tree and a random forest evaluated within the context of K-10 fold validation using the CARET package available within the open source architecture R program. We compared these models with the feed forward neural network strategy that we previously reported on with this data set.

Conflict(s) of Interest


References with DOI

1. Lowrie EG, Lazarus JM, Mocelin AJ, Bailey GL, Hampers CL, Wilson RE, et al. Survival of patients undergoing chronic hemodialysis and renal transplantation. N Engl J Med. 1973;288(17):863-7. https://doi.org/10.1056/nejm197304262881701

2. Foley RN, Murray AM, Li S, Herzog CA, McBean AM, Eggers PW, et al. Chronic kidney disease and the risk for cardiovascular disease, renal replacement, and death in the United States Medicare population, 1998 to 1999. J Am Soc Nephrol. 2005;16(2):489-95. https://doi.org/10.1681/asn.2004030203

3. Port FK, Orzol SM, Held PJ, Wolfe RA. Trends in treatment and survival for hemodialysis patients in the United States. Am J Kidney Dis. 1998;32(6 Suppl 4):S34-8.

4. Block GA, Klassen PS, Lazarus JM, Ofsthun N, Lowrie EG, Chertow GM. Mineral metabolism, mortality, and morbidity in maintenance hemodialysis. J Am Soc Nephrol. 2004;15(8):2208-18. https://doi.org/10.1097/01.asn.0000133041.27682.a2

5. Teng M, Wolf M, Lowrie E, Ofsthun N, Lazarus JM, Thadhani R. Survival of patients undergoing hemodialysis with paricalcitol or calcitriol therapy. N Engl J Med. 2003;349(5):446-56. https://doi.org/10.1056/nejmoa022536

6. Szczech LA, Reddan DN, Klassen PS, Coladonato J, Chua B, Lowrie EG, et al. Interactions between dialysisrelated volume exposures, nutritional surrogates and mortality among ESRD patients. Nephrol Dial Transplant. 2003;18(8):1585-91. https://doi.org/10.1093/ndt/gfg225

7. Lowrie EG, Li Z, Ofsthun N, Lazarus JM. Body size, dialysis dose and death risk relationships among hemodialysis patients. Kidney Int. 2002;62(5):1891-7. https://doi.org/10.1046/j.1523-1755.2002.00642.x

8. Chertow GM, Johansen KL, Lew N, Lazarus JM, Lowrie EG. Vintage, nutritional status, and survival in hemodialysis patients. Kidney Int. 2000;57(3):1176-81. https://doi.org/10.1046/j.1523-1755.2000.00945.x

9. Jacob AN, Khuder S, Malhotra N, Sodeman T, Gold JP, Malhotra D, et al. Neural network analysis to predict mortality in end-stage renal disease: application to United States Renal Data System. Nephron Clin Pract. 2010;116(2):c148-58. https://doi.org/10.1159/000315884

10. Description of the USRDS and its data base. Am J Kidney Dis. 1991;18(5 Suppl 2):17-20.

11. USRDS research studies. Am J Kidney Dis. 1991;18(5 Suppl 2):105-10.

12. Gullo CA, McCarthy MJ, Shapiro JI, Miller BL. Predicting Medical Student Success on Licensure Exams. Med Sci Educ. 2015;25:447-53. https://doi.org/10.1007/s40670-015-0179-6

13. Tirelli T, Gamba M, Pessani D. Support vector machines to model presence/absence of Alburnus alburnus alborella (Teleostea, Cyprinidae) in North-Western Italy: comparison with other machine learning techniques. C R Biol. 2012;335(10-11):680-6. https://doi.org/10.1016/j.crvi.2012.09.001

14. Chen T, Cao Y, Zhang Y, Liu J, Bao Y, Wang C, et al. Random forest in clinical metabolomics for phenotypic discrimination and biomarker selection. Evid Based Complement Alternat Med. 2013;2013:298183. https://doi.org/10.1155/2013/298183

15. Khondoker MR, Bachmann TT, Mewissen M, Dickinson P, Dobrzelecki B, Campbell CJ, et al. Multi-factorial analysis of class prediction error: estimating optimal number of biomarkers for various classification rules. J Bioinform Comput Biol. 2010;8(6):945-65. https://doi.org/10.1142/s0219720010005063

16. Tsiliki G, Munteanu CR, Seoane JA, Fernandez-Lozano C, Sarimveis H, Willighagen EL. RRegrs: an R package for computer-aided model selection with multiple regression models. J Cheminform. 2015;7:46. https://doi.org/10.1186/s13321-015-0094-2

17. Liu R, Li X, Zhang W, Zhou HH. Comparison of Nine Statistical Model Based Warfarin Pharmacogenetic Dosing Algorithms Using the Racially Diverse International Warfarin Pharmacogenetic Consortium Cohort Database. PLoS One. 2015;10(8):e0135784. https://doi.org/10.1371/journal.pone.0135784

18. Khitan Z, Shapiro AP, Shah PT, Sanabria JR, Santhanam P, Sodhi K, Abraham NG, Shapiro JI. Predicting adverse outcomes in chronic kidney disease using machine learning methods: data from the modification of diet in renal disease. Marshall Journal of Medicine. 2017;3(4):67-79. https://doi.org/10.18590/mjm.2017.vol3.iss4.10

19. Provost F. Machine Learning from imbalanced data sets 101 pages.stern.nyu.edu/~fprovost/Papers/skew.PDF2000

Creative Commons License

Creative Commons Attribution 4.0 License
This work is licensed under a Creative Commons Attribution 4.0 License.