Advertisement

Applying the Temporal Abstraction Technique to the Prediction of Chronic Kidney Disease Progression

Systems-Level Quality Improvement
  • 182 Downloads
Part of the following topical collections:
  1. Systems-Level Quality Improvement

Abstract

Chronic kidney disease (CKD) has attracted considerable attention in the public health domain in recent years. Researchers have exerted considerable effort in attempting to identify critical factors that may affect the deterioration of CKD. In clinical practice, the physical conditions of CKD patients are regularly recorded. The data of CKD patients are recorded as a high-dimensional time-series. Therefore, how to analyze these time-series data for identifying the factors affecting CKD deterioration becomes an interesting topic. This study aims at developing prediction models for stage 4 CKD patients to determine whether their eGFR level decreased to less than 15 ml/min/1.73m2 (end-stage renal disease, ESRD) 6 months after collecting their final laboratory test information by evaluating time-related features. A total of 463 CKD patients collected from January 2004 to December 2013 at one of the biggest dialysis centers in southern Taiwan were included in the experimental evaluation. We integrated the temporal abstraction (TA) technique with data mining methods to develop CKD progression prediction models. Specifically, the TA technique was used to extract vital features (TA-related features) from high-dimensional time-series data, after which several data mining techniques, including C4.5, classification and regression tree (CART), support vector machine, and adaptive boosting (AdaBoost), were applied to develop CKD progression prediction models. The results revealed that incorporating temporal information into the prediction models increased the efficiency of the models. The AdaBoost+CART model exhibited the most accurate prediction among the constructed models (Accuracy: 0.662, Sensitivity: 0.620, Specificity: 0.704, and AUC: 0.715). A number of TA-related features were found to be associated with the deterioration of renal function. These features can provide further clinical information to explain the progression of CKD. TA-related features extracted by long-term tracking of changes in laboratory test values can enable early diagnosis of ESRD. The developed models using these features can facilitate medical personnel in making clinical decisions to provide appropriate diagnoses and improved care quality to patients with CKD.

Keywords

Chronic kidney disease Delay progression Time-series data Temporal abstraction Data mining 

Notes

Compliance with Ethical Standards

Conflicts of Interest

Authors declare that they have no conflict of interest.

Ethical Approval

All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.

Informed Consent

Written consent from the study was unavailable because the dataset comprises only de-identified secondary data for research purposes, and the Institutional Review Board of St. Martin de Porres Hospital issued a formal written waiver of the need for consent and approved the study.

References

  1. 1.
    Chen, N., Hsu, C.C., Yamagata, K., and Langham, R., Challenging chronic kidney disease: Experience from chronic kidney disease prevention programs in Shanghai, Japan. Taiwan and Australia. Nephrology. 15(s2):31–36, 2010.CrossRefPubMedGoogle Scholar
  2. 2.
    National Kidney Foundation, About chronic kidney disease. Available: http://www.kidney.org/kidneydisease/aboutckd.cfm, 2015.
  3. 3.
    Thomas, R., Kanso, A., and Sedor, J.R., Chronic kidney disease and its complications. Prim. Care. 35(2):329–344, 2008.CrossRefPubMedPubMedCentralGoogle Scholar
  4. 4.
    Kronenberg, F., Emerging risk factors and markers of chronic kidney disease progression. Nat. Rev. Nephrol. 5(12):677–689, 2009.CrossRefPubMedGoogle Scholar
  5. 5.
    Abbasi, M. A., Chertow, G. M., and Hall, Y. N., End-stage renal disease. Clin. Evid., 2010.Google Scholar
  6. 6.
    Yeh, J.Y., Wu, T.H., and Tsao, C.W., Using data mining techniques to predict hospitalization of hemodialysis patients. Decis. Support. Syst. 50(2):439–448, 2011.CrossRefGoogle Scholar
  7. 7.
    Taiwan Society of Nephrology, Available: http://www.tsn.org.tw/, 2015.
  8. 8.
    Collins, G.S., Omar, O., Shanyinde, M., and Yu, L.M., A systematic review finds prediction models for chronic kidney were poorly reported and often developed using inappropriate methods. J. Clin. Epidemiol. 66(3):263–266, 2013.CrossRefGoogle Scholar
  9. 9.
    Yang, W.C., and Hwang, S.J., Incidence, prevalence and mortality trends of dialysis end-stage renal disease in Taiwan from 1990 to 2001: The impact of national health insurance. Nephrol. Dial. Transplant. 23(12):3977–3982, 2008.CrossRefPubMedGoogle Scholar
  10. 10.
    Hsu, C.C., Hwang, S.J., Wen, C.P., Chang, H.Y., Chen, T., Shiu, R.S., et al., High prevalence and low awareness of CKD in Taiwan: A study on the relationship between serum creatinine and awareness from a nationally representative survey. Am. J. Kidney Dis. 48(5):727–738, 2006.CrossRefPubMedGoogle Scholar
  11. 11.
    Haroun, M.K., Jaar, B.G., Hoffman, S.C., Comstock, G.W., Klag, M.J., and Coresh, J., Risk factors for chronic kidney disease: A prospective study of 23,534 men and women in Washington County. Maryland. Journal of the American Society of Nephrology. 14(11):2934–2941, 2003.CrossRefPubMedGoogle Scholar
  12. 12.
    Stengel, B., Tarver-Carr, M.E., Powe, N.R., Eberhardt, M.S., and Brancati, F.L., Lifestyle factors, obesity and the risk of chronic kidney disease. Epidemiology. 14(4):479–487, 2003.PubMedGoogle Scholar
  13. 13.
    Peralta, C.A., Shlipak, M.G., Fan, D., Ordonez, J., Lash, J.P., Chertow, G.M., et al., Risks for end-stage renal disease, cardiovascular events, and death in Hispanic versus non-Hispanic white adults with chronic kidney disease. J. Am. Soc. Nephrol. 17(10):2892–2899, 2006.CrossRefPubMedGoogle Scholar
  14. 14.
    Schaeffner, E.S., Kurth, T., Curhan, G.C., Glynn, R.J., Rexrode, K.M., Baigent, C., et al., Cholesterol and the risk of renal dysfunction in apparently healthy men. J. Am. Soc. Nephrol. 14(8):2084–2091, 2003.PubMedGoogle Scholar
  15. 15.
    Zolbanin, H.M., Delen, D., and Zadeh, A.H., Predicting overall survivability in comorbidity of cancers: A data mining approach. Decis. Support. Syst. 74:150–161, 2015.CrossRefGoogle Scholar
  16. 16.
    Oztekin, A., Delen, D., and Kong, Z.J., Predicting the graft survival for heart–lung transplantation patients: An integrated data mining methodology. Int. J. Med. Inform. 78(12):e84–e96, 2009.CrossRefPubMedGoogle Scholar
  17. 17.
    Yang, C.-S., Wei, C.-P., Yuan, C.-C., and Schoung, J.-Y., Predicting the length of hospital stay of burn patients: Comparisons of prediction accuracy among different clinical stages. Decis. Support. Syst. 50(1):325–335, 2010.CrossRefGoogle Scholar
  18. 18.
    Chen, L., Li, X., Yang, Y., Kurniawati, H., Sheng, Q.Z., Hu, H.Y., and Huang, N., Personal health indexing based on medical examinations: A data mining approach. Decis. Support. Syst. 81:54–65, 2016.Google Scholar
  19. 19.
    Shahar, Y., A framework for knowledge-based temporal abstraction. Artif. Intell. 90(1):79–133, 1997.CrossRefGoogle Scholar
  20. 20.
    Breiman, L., Friedman, J.H., Olshen, R.A., and Stone, C.J., Classification and regression trees. Wadsworth & Brooks, Monterey, 1984.Google Scholar
  21. 21.
    Cortes, C., and Vapnik, V., Support-vector networks. Mach. Learn. 20(3):273–297, 1995.Google Scholar
  22. 22.
    Freund, Y., and Schapire, R.E., A short introduction to boosting introduction to AdaBoost. Journal of Japanese Society for Artificial Intelligence. 14:771–780, 1999.Google Scholar
  23. 23.
    Levey, A.S., Eckardt, K.U., Tsukamoto, Y., Levin, A., Coresh, J., Rossert, J., et al., Definition and classification of chronic kidney disease: A position statement from kidney disease: Improving global outcomes (KDIGO). Kidney Int. 67(6):2089–2100, 2005.CrossRefPubMedGoogle Scholar
  24. 24.
    Levey, A.S., Stevens, L.A., Schmid, C.H., Zhang, Y.L., Castro 3rd, A.F., Feldman, H.I., et al., A new equation to estimate glomerular filtration rate. Ann. Intern. Med. 150(9):604–612, 2009.CrossRefPubMedPubMedCentralGoogle Scholar
  25. 25.
    Lorenzo, V., Saracho, R., Zamora, J., Rufino, M., and Torres, A., Similar renal decline in diabetic and non-diabetic patients with comparable levels of albuminuria. Nephrol. Dial. Transplant. 25:835–841, 2010.CrossRefPubMedGoogle Scholar
  26. 26.
    Hallan, S.I., Ritz, E., Lydersen, S., Romundstad, S., Kvenild, K., and Orth, S.R., Combining GFR and albuminuria to classify CKD improves prediction of ESRD. J. Am. Soc. Nephrol. 20(15):1069–1077, 2009.CrossRefPubMedPubMedCentralGoogle Scholar
  27. 27.
    Othman, M., Kawar, B., and El Nahas, A.M., Influence of obesity on progression of non-diabetic chronic kidney disease: A retrospective cohort study. Nephron Clinical Practice. 113(1):16–23, 2009.CrossRefGoogle Scholar
  28. 28.
    Go, A.S., Chertow, G.M., Fan, D.J., McCulloch, C.E., and Hsu, C.Y., Chronic kidney disease and the risks of death, cardiovascular events, and hospitalization. N. Engl. J. Med. 351(13):1296–1305, 2004.CrossRefPubMedGoogle Scholar
  29. 29.
    Wu, I.W., Hsu, K.H., Lee, C.C., Sun, C.Y., Hsu, H.J., Tsai, C.J., et al., p-Cresyl sulphate and indoxyl sulphate predict progression of chronic kidney disease. Nephrol. Dial. Transplant. 26(3):938–947, 2011.CrossRefPubMedGoogle Scholar
  30. 30.
    Perotte, A., Ranganath, R., Hirsch, J.S., Blei, D., and Elhadad, N., Risk prediction for chronic kidney disease progression using heterogeneous electronic health record data and time series analysis. J. Am. Med. Inform. Assoc. 22(4):872–880, 2015.CrossRefPubMedPubMedCentralGoogle Scholar
  31. 31.
    Bala, S., and Kumar, K., A literature review on kidney disease prediction using data mining classification technique. International Journal of Computer Science and Mobile Computing. 3:960–967, 2014.Google Scholar
  32. 32.
    Vijayarani, S., and Dhayanand, M.S., Data mining classification algorithms for kidney disease prediction. Int. J. Cybern. Inf. 4(4), 2015.Google Scholar
  33. 33.
    Kurbalija, V., Radovanović, M., Ivanović, M., Schmidt, D., von Trzebiatowski, G.L., Burkhard, H.-D., et al., Time-series analysis in the medical domain: A study of Tacrolimus administration and influence on kidney graft function. Comput. Biol. Med. 50:19–31, 2014.CrossRefPubMedGoogle Scholar
  34. 34.
    Chou, H.L., Wang, S.H., and Cheng, C.H., Discovering knowledge of hemodialysis (HD) quality using granularity-based rough set theory. Arch. Gerontol. Geriatr. 54:232–237, 2012.CrossRefPubMedGoogle Scholar
  35. 35.
    Altintas, Y.Y., Gokcen, H., Ulgu, M., and Demirel, N., Analysing interactions of risk factors according to risk levels for hemodialysis patients in Turkey: A data mining application. Gazi University Journal of Science. 24(4):829–839, 2011.Google Scholar
  36. 36.
    Belazzi, R., Larizza, C., Magni, P., and Bellazzi, R., Temporal data mining for the quality assessment of hemodialysis services. Artif. Intell. Med. 34(1):25–39, 2005.CrossRefGoogle Scholar
  37. 37.
    Tan, C., Chen, H., and Xia, C.Y., Early prediction of lung cancer based on the combination of trace element analysis in urine and an Adaboost algorithm. J. Pharm. Biomed. Anal. 49(3):746–752, 2009.CrossRefPubMedGoogle Scholar
  38. 38.
    Tan, C., Li, M.L., and Qin, X., Study of the feasibility of distinguishing cigarettes of different brands using an Adaboost algorithm and near-infrared spectroscopy. Anal. Bioanal. Chem. 389(2):667–674, 2007.CrossRefPubMedGoogle Scholar
  39. 39.
    Zhang, M.H., Xu, Q.S., Daeyaert, F., Lewi, P.J., and Massart, D.L., Application of boosting to classification problems in chemometrics. Anal. Chim. Acta. 544(1):167–176, 2005.CrossRefGoogle Scholar
  40. 40.
    Galar, M., Fernandez, A., Barrenechea, E., Bustince, H., and Herrera, F., A review on ensembles for the class imbalance problem: Bagging-, boosting-, and hybrid-based approaches. IEEE Trans. Syst. Man Cybern. Part C Appl. Rev. 42(4):463–484, 2012.CrossRefGoogle Scholar
  41. 41.
    Levin, A., Djurdjev, O., Beaulieu, M., and Er, L., Variability and risk factors for kidney disease progression and death following attainment of stage 4 CKD in a referred cohort. Am. J. Kidney Dis. 52(4):661–671, 2008.CrossRefPubMedGoogle Scholar
  42. 42.
    Chiu, Y.L., Chien, K.L., Lin, S.L., Chen, Y.M., Tsai, T.J., and Wu, K.D., Outcomes of stage 3-5 chronic kidney disease before end-stage renal disease at a single center in Taiwan. Nephron Clinical Practice. 109(3):109–118, 2008.CrossRefGoogle Scholar
  43. 43.
    Jones, C., Roderick, P., Harris, S., and Rogerson, M., Decline in kidney function before and after nephrology referral and the effect on survival in moderate to advanced chronic kidney disease. Nephrol. Dial. Transplant. 21(8):2133–2143, 2006.CrossRefPubMedGoogle Scholar
  44. 44.
    Yoshida, T., Takei, T., Shirota, S., Tsukada, M., Sugiura, H., Itabashi, M., et al., Risk factors for progression in patients with early-stage chronic kidney disease in the Japanese population. Intern. Med. 47(21):1859–1864, 2008.CrossRefPubMedGoogle Scholar
  45. 45.
    Tsai, S.Y., Tseng, H.F., Tan, H.F., Chien, Y.S., and Chang, C.C., End-stage renal disease in Taiwan: A case-control study. Journal of epidemiology. 19(4):169–176, 2009.CrossRefPubMedPubMedCentralGoogle Scholar
  46. 46.
    Chang, C.L., and Chen, C.H., Applying decision tree and neural network to increase quality of dermatologic diagnosis. Expert Syst. Appl. 36(2):4035–4041, 2009.CrossRefGoogle Scholar
  47. 47.
    Ishani, A., Grandits, G.A., Grimm, R.H., Svendsen, K.H., Collins, A.J., Prineas, R.J., et al., Association of single measurements of dipstick proteinuria, estimated glomerular filtration rate, and hematocrit with 25-year incidence of end-stage renal disease in the multiple risk factor intervention trial. J. Am. Soc. Nephrol. 17(5):1444–1452, 2006.CrossRefPubMedGoogle Scholar
  48. 48.
    Mohanram, A., Zhang, Z., Shahinfar, S., Keane, W.F., Brenner, B.M., and Toto, R.D., Anemia and end-stage renal disease in patients with type 2 diabetes and nephropathy. Kidney Int. 66(3):1131–1138, 2004.CrossRefPubMedGoogle Scholar
  49. 49.
    Ohno, I., Hosoya, T., Gomi, H., Ichida, K., Okabe, H., and Hikita, M., Serum uric acid and renal prognosis in patients with IgA nephropathy. Nephron. 87(4):333–339, 2001.CrossRefPubMedGoogle Scholar
  50. 50.
    Sanchez-Lozada, L.G., Tapia, E., Santamaria, J., Avila-Casado, C., Soto, V., Nepomuceno, T., et al., Mild hyperuricemia induces vasoconstriction and maintains glomerular hypertension in normal and remnant kidney rats. Kidney Int. 67(1):237–247, 2005.CrossRefPubMedGoogle Scholar
  51. 51.
    Keane, W.F., Zhang, Z.X., Lyle, P.A., Cooper, M.E., de Zeeuw, D., Grunfeld, J.P., et al., Risk scores for predicting outcomes in patients with type 2 diabetes and nephropathy: The RENAAL study. Clin. J. Am. Soc. Nephrol. 1:761–767, 2006.CrossRefPubMedGoogle Scholar
  52. 52.
    Ravani, P., Tripepi, G., Malberti, F., Testa, S., Mallamaci, F., and Zoccali, C., Asymmetrical dimethylarginine predicts progression to dialysis and death in patients with chronic kidney disease: A competing risks modeling approach. J. Am. Soc. Nephrol. 16:2449–2455, 2009.CrossRefGoogle Scholar
  53. 53.
    Taal, M.W., and Brenner, B.M., Predicting initiation and progression of chronic kidney disease: Developing renal risk scores. Kidney Int. 70:1694–1705, 2006.CrossRefPubMedGoogle Scholar
  54. 54.
    Narva, A.S., and Briggs, M., The National Kidney Disease Education Program: Improving understanding, detection, and management of CKD. Am. J. Kidney Dis. 53:S115–S120, 2009.CrossRefPubMedGoogle Scholar
  55. 55.
    Young, H.N., Chan, M.R., Yevzlin, A.S., and Becker, B.N., The rationale, implementation, and effect of the Medicare CKD education benefit. Am. J. Kidney Dis. 57:381–386, 2011.CrossRefPubMedGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2017

Authors and Affiliations

  1. 1.Department of Computer Science and Information ManagementSoochow UniversityTaipeiTaiwan
  2. 2.Department of Information Management and Institute of Healthcare Information ManagementNational Chung Cheng UniversityChiayiTaiwan

Personalised recommendations