Dialysate-side urea kinetics. Neural network predicts dialysis dose during dialysis

  • E. A. Fernández
  • R. Valtuille
  • P. Willshaw
  • C. A. Perazzo


Determination of the adequacy of dialysis is a routine but crucial procedure in patient evaluation. The total dialysis dose, expressed as Kt/V, has been widely recognised to be a major determinant of morbidity and mortality in haemodialysed patients. Many different factors influence the correct determination of Kt/V, such as urea sequestration in different body compartments, access and cardiopulmonary recirculation. These factors are responsible for urea rebound after the end of the haemodialysis session, causing poor Kt/V estimation. There are many techniques that try to overcome this problem. Some of them use analysis of blood-side urea samples, and in recent years, on-line urea monitors have become available to calculate haemodialysis dose from dialysate-side urea kinetics. All these methods require waiting until the end of the session to calculate the Kt/V dose. In this work, a neural network (NN) method is presented for early prediction of the Kt/V dose. Two different portions of the dialysate urea concentration-time profile (provided by an on-line urea minitor) were analysed: the entire curve A and the first half B, using an NN to predict the Kt/V and compare this with that provided by the monitor. The NN was able to predict Kt/V is the middle of the 4h session (B data) without a significant increase in the percentage error (B data: 6.69%±2.46%; A data: 5.58%±8.77%, mean±SD) compared with the monitor Kt/V.


Artificial intelligence Urea Monitors Dialysate-side urea kinetics Neural networks 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Akl, A. I., Sobh, M. A., Yehya, M. E., andTattersall, J. (2001): ‘Artificial intelligence: a new approach for prescription and monitoring of hemodialysis therapy’,Am. J. Kidney Dis.,38, pp. 1277–1283Google Scholar
  2. Beto, J. A., Bansal, V. K., Ing, T. S., andDaugirdas, J. T. (1998): ‘Variation in blood sample collection for determination of hemodialysis adequacy (Council on Renal Nutrition National Research Question Collaborative Study Group)’,Am. J. Kidney Dis.,31, pp. 135–141Google Scholar
  3. Cheng, Y. K., Choi, K. S., Chau, K. F., Li, C. S., Yung, C. U., Yu, A. W. Y., andWong, K. K. (2001): ‘Urea reduction ratio that considers effects of ultrafiltration and intradialytic urea generation’,Am. J. Kidney Dis.,37, pp. 544–549Google Scholar
  4. Daugirdas, J. T. (1995): ‘Simplified equations for monitoring Kt/V, PCRn, eKt/V, and ePCRn’,Adv. Ren. Replace. Ther.,2, pp. 295–304Google Scholar
  5. Daugirdas, J. T., Depner, T. A., Gotch, F. A., Greene, T., Keshaviah, P., Levin, N. W., andSchulman, G. (1997): ‘Comparison of methods to predict equilibrated Kt/V in the HEMO pilot study’,Kidney Int.,52, pp. 1395–1405Google Scholar
  6. Demuth, H., andBeale, M. (1997): ‘Neural network toolboxes—user's guide’, Version 3.0Google Scholar
  7. Depner, T. A., Keshaviah, P. R., Ebben, J. P., Emerson, P. F., Collins, A. J., Jindal, K. K., Nissenson, A. R., Lazarus, J. M., andPu, K. (1996): ‘Multicenter clinical validation of an on-line monitor of dialysis adequacy’,J. Am. Soc. Nephrol.,7, pp. 464–471Google Scholar
  8. Fernández, E. A., Valtuille, R., Willshaw, P., andPerrazzo, C. A. (2001): ‘Using artificial intelligence to predict the equilibrated postdialysis blood urea concentration’,Blood Purif.,19, pp. 271–285Google Scholar
  9. Garred, L. J. (1995): ‘Dialysate-based kinetic modeling’,Adv. Ren. Replace. Ther.,2, pp. 305–318Google Scholar
  10. Garred, L. J., Canaud, B., Bosc, J. Y., andTetta, C. (1997): ‘Urea rebound and delivered Kt/V determination with a continuous urea sensor’,Nephrol. Dial. Transplant.,12, pp. 535–542Google Scholar
  11. Gotch, F. A., andSargent, J. A. (1995): ‘A mechanistic analysis of the National Cooperative Dialysis Study (NCDS)’,Kidney Int.,28, pp. 526–534Google Scholar
  12. Guh, J. Y., Yang, C. Y., Yang, J. M., Chen, L. M., andLai, Y. H. (1998): ‘Prediction of equilibrated postdialysis BUN by an artificial neural network in high-efficiency hemodialysis’,Am. J. Kidney Dis.,31, pp. 638–646Google Scholar
  13. Hagan, M., andMenhaj, M. (1994): ‘Training feedforward networks with the Marquardt algorithm’,IEEE Trans Neural Netw.,5, pp. 989–993CrossRefGoogle Scholar
  14. Haykin, S. (Ed.) (1999): ‘Neural networks. A comprehensive foundation’, 2nd edn (Prentice Hall, New Jersey, 1999)Google Scholar
  15. Kauffman, A. M., Schneditz, D., Smye, S., Polaschegg, H. D., andLevin, N. W. (1995): ‘Solute disequilibrium and multicompartment modeling’,Adv. Ren. Rep. Ther.,2, pp. 329–329Google Scholar
  16. Lindsay, R. M., andSternby, J. (2001): ‘Future directions in dialysis quantification’,Semin. Dial.,14, pp. 300–307CrossRefGoogle Scholar
  17. Marshal, M. R., Santamaria, P., andCollins, J. F. (1998): ‘Biostat 1000 and Dougirdas blood-based hemodialysis quantification: agreement and reproducibility’,Am. J. Kidney Dis.,31, pp. 1011–1018Google Scholar
  18. Owen, W. F., Lew, N. L., Liu, Y., Lowrie, E. G., andLazarus, M. (1993): ‘The urea reduction ratio and serum albumin concentration as predictors of mortality in patients undergoing hemodialysis’,New Engl. J. Med.,329, pp. 1001–1006CrossRefGoogle Scholar
  19. Ronco, C., Ghezzi, P. M., andLa Greca, G. (1999): ‘The role of technology in dialysis’,J. Nephrol.,12, pp. S68-S81Google Scholar
  20. Sternby, J. (1999): ‘Urea sensors—a world of possibilities’,Adv. Ren. Replace. Ther.,6, pp. 265–272Google Scholar
  21. Vandeginste B. G. M., Massart, D. L., Buydens, L. M. C., De Jong, A., Lewi, P. J., andSmeyers-Verbeke, J. (1998): ‘Data handling in science and technology 20 B-Handbook of chemometrics and qualimetrics: Part B’ (Elsevier, Amsterdam, 1998)Google Scholar

Copyright information

© IFMBE 2003

Authors and Affiliations

  • E. A. Fernández
    • 1
  • R. Valtuille
    • 2
  • P. Willshaw
    • 1
  • C. A. Perazzo
    • 1
  1. 1.Bioengineering DepartmentFavaloro UniversityBuenos AiresArgentina
  2. 2.RTC AdrogueDialysis Unit CenterBuenos AiresArgentina

Personalised recommendations