Objectives: Chronic kidney disease (CKD) is one of the main causes of morbidity and mortality worldwide. Detecting survival modifiable factors could help in prioritizing the clinical care and offers a treatment decision-making for hemodialysis patients. The aim of this study was to develop the best predictive model to explain the predictors of death in Hemodialysis patients by using data mining techniques.
Methods: In this study, we used a dataset included records of 857 dialysis patients. Thirty-one potential risk factors, that might be associated with death in dialysis patients, were selected. The performances of four classifiers of support vector machine, neural network, logistic regression and decision tree were compared in terms of sensitivity, specificity, total accuracy, positive likelihood ratio and negative likelihood ratio.
Results: The average total accuracy of all methods was over 61%; the greatest total accuracy belonged to logistic regression (0.71). Also, logistic regression produced the greatest specificity (0.72), sensitivity (0.69), positive likelihood ratio (2.48) and the lowest negative likelihood ratio (0.43).
Conclusions: Logistic regression had the best performance in comparison to other methods for predicting death among hemodialysis patients. According to this model female gender, increasing age, addiction, low Iron level, C-reactive protein positive and low urea reduction ratio were the main predictors of death in hemodialysis patients.
2. Bello AK, Levin A, Tonelli M, Okpechi IG, Feehally J, Harris D, et al. Assessment of global kidney health care status. Jama. 2017;317(18):1864-81.
3. Trillini M, Perico N, Remuzzi G. Epidemiology of end-stage renal failure: the burden of kidney diseases to global health. Kidney Transplantation, Bioengineering and Regeneration: Elsevier; 2017. p. 5-11.
4. Floege J, Gillespie IA, Kronenberg F, Anker SD, Gioni I, Richards S, et al. Development and validation of a predictive mortality risk score from a European hemodialysis cohort. Kidney international. 2015;87(5):996-1008.
5. Onofriescu M, Siriopol D, Voroneanu L, Hogas S, Nistor I, Apetrii M, et al. Overhydration, cardiac function and survival in hemodialysis patients. PLoS One. 2015;10(8):e0135691.
6. Dekker M, Marcelli D, Canaud B, Konings C, Leunissen K, Levin N, et al. Unraveling the relationship between mortality, hyponatremia, inflammation and malnutrition in hemodialysis patients: results from the international MONDO initiative. European journal of clinical nutrition. 2016;70(7):779.
7. Cooper BA, Branley P, Bulfone L, Collins JF, Craig JC, Fraenkel MB, et al. A randomized, controlled trial of early versus late initiation of dialysis. New England Journal of Medicine. 2010;363(7):609-19.
8. Iseki K, Tozawa M, Yoshi S, Fukiyama K. Serum C-reactive protein (CRP) and risk of death in chronic dialysis patients. Nephrology Dialysis Transplantation. 1999;14(8):1956-60.
9. Bandehelahi K, Khoshravesh S, Barati M, Tapak L. Psychological and Sociodemographic Predictors of Fertility Intention among Childbearing-Aged Women in Hamadan, West of Iran: An Application of the BASNEF Model. Korean journal of family medicine. 2019;40(3):182.
10. Tapak L, Shirmohammadi-Khorram N, Amini P, Alafchi B, Hamidi O, Poorolajal J. Prediction of survival and metastasis in breast cancer patients using machine learning classifiers. Clinical Epidemiology and Global Health. 2018.
11. Tapak L, Hamidi O, Amini P, Poorolajal J. Prediction of kidney graft rejection using artificial neural network. Healthcare informatics research. 2017;23(4):277-84.
12. Hamidi O, Poorolajal J, Farhadian M, Tapak L. Identifying important risk factors for survival in kidney graft failure patients using random survival forests. Iranian journal of public health. 2016;45(1):27.
13. Chiang P-Y, Chao PC-P, Tu T-Y, Kao Y-H, Yang C-Y, Tarng D-C, et al. Machine Learning Classification for Assessing the Degree of Stenosis and Blood Flow Volume at Arteriovenous Fistulas of Hemodialysis Patients Using a New Photoplethysmography Sensor Device. Sensors. 2019;19(15):3422.
14. Tsai Y-T, Yang F-J, Lin H-M, Yeh J-C, Cheng B-W. Constructing a prediction model for physiological parameters for malnutrition in hemodialysis patients. Scientific reports. 2019;9(1):1-6.
15. Martínez-Martínez JM, Escandell-Montero P, Barbieri C, Soria-Olivas E, Mari F, Martínez-Sober M, et al. Prediction of the hemoglobin level in hemodialysis patients using machine learning techniques. Computer methods and programs in biomedicine. 2014;117(2):208-17.
16. Lacson R, editor Predicting hemodialysis mortality utilizing blood pressure trends. AMIA Annual Symposium Proceedings; 2008: American Medical Informatics Association.
17. Chandola V, Banerjee A, Kumar V. Anomaly detection: A survey. ACM computing surveys (CSUR). 2009;41(3):15.
18. IBM. IBM Knowledge Center. Available from: https://www.ibm.com/support/knowledgecenter/SS3RA7_15.0.0/com.ibm.spss.modeler.help/anomalydetectionnode_general.htm.
19. Han J, Pei J, Kamber M. Data mining: concepts and techniques: Elsevier; 2011.
20. Duda RO, Hart PE, Stork DG. Pattern classification: John Wiley & Sons; 2012.
21. Prabha DR, Prasad G. Predictors of mortality among patients on maintenance hemodialysis. Journal of Dr NTR University of Health Sciences. 2016;5(4):255.
22. Depner T, Daugirdas J, Greene T, Allon M, Beck G, Chumlea C, et al. Dialysis dose and the effect of gender and body size on outcome in the HEMO Study. Kidney international. 2004;65(4):1386-94.
23. Shedler J, Block J. Adolescent drug use and psychological health: A longitudinal inquiry. American psychologist. 1990;45(5):612.
24. Chen C-Y, Lin K-M. Health consequences of illegal drug use. Current opinion in psychiatry. 2009;22(3):287-92.
25. Coric A, Resic H, Celik D, Masnic F, Ajanovic S, Prohic N, et al. Mortality in hemodialysis patients over 65 years of age. Materia socio-medica. 2015;27(2):91.
26. Xue JL, Ma JZ, Louis TA, Collins AJ. Forecast of the number of patients with end-stage renal disease in the United States to the year 2010. Journal of the American Society of Nephrology. 2001;12(12):2753-8.
27. Yeun JY, Levine RA, Mantadilok V, Kaysen GA. C-reactive protein predicts all-cause and cardiovascular mortality in hemodialysis patients. American Journal of Kidney Diseases. 2000;35(3):469-76.
28. Wasserman S, Rosanio S, Tiblier E, Sperger H, Tocchi M, Christenson R, et al. Cardiac troponin T and C-reactive protein for predicting prognosis, coronary atherosclerosis, and cardiomyopathy in patients undergoing long-term hemodialysis. Jama. 2003;290(3):353-9.
29. Macdougall IC, Dahl NV, Bernard K, Li Z, Batycky A, Strauss WE. The Ferumoxytol for Anemia of CKD Trial (FACT)—a randomized controlled trial of repeated doses of ferumoxytol or iron sucrose in patients on hemodialysis: background and rationale. BMC nephrology. 2017;18(1):117.
30. Motonishi S, Tanaka K, Ozawa T. Iron deficiency associates with deterioration in several symptoms independently from hemoglobin level among chronic hemodialysis patients. PloS one. 2018;13(8).
31. Zitt E, Sturm G, Kronenberg F, Neyer U, Knoll F, Lhotta K, et al. Iron supplementation and mortality in incident dialysis patients: an observational study. PLoS One. 2014;9(12):e114144.
32. Feldman HI, Santanna J, Guo W, Furst H, Franklin E, Joffe M, et al. Iron administration and clinical outcomes in hemodialysis patients. Journal of the American Society of Nephrology. 2002;13(3):734-44.
33. Wolfe RA, Ashby VB, Daugirdas JT, Agodoa LY, Jones CA, Port FK. Body size, dose of hemodialysis, and mortality. American journal of kidney diseases. 2000;35(1):80-8.
34. Port FK, Ashby VB, Dhingra RK, Roys EC, Wolfe RA. Dialysis dose and body mass index are strongly associated with survival in hemodialysis patients. Journal of the American Society of Nephrology. 2002;13(4):1061-6.