Menu

A+ A A-

Download article

DOI: https://doi.org/10.22263/2312-4156.2026.4.62

A.T. Shchastniy, A.S. Osochuk, S.S. Osochuk, A.F. Martsinkevich
A method for predicting kidney allograft rejection
Vitebsk State Order of Peoples’ Friendship Medical University, Vitebsk, Republic of Belarus

Vestnik VGMU. 2026;25(4):62-69.

Abstract.
Objectives. To develop a method for identifying recipients with a high risk of the kidney allograft rejection. Material and methods. The study group consisted of 131 kidney allograft recipients. All patients received a triplecomponent immunosuppressive therapy (tacrolimus + mycophenolate mofetil + glucocorticosteroid). The study analyzed longitudinal (panel) data of patients’ post-operative laboratory parameters tracked over a dynamic observation period of 5 or more years. To identify the parameters with the highest predictive value, the Elastic Net algorithm was applied. For the final mathematical model, the algorithm selected the following variables: minimum creatinine concentration and its standard deviation (SD); maximum (max) platelet count; mean, maximum (max), and coefficient of variation (CV) of calcium concentration; median and SD of hemoglobin concentration; SD of urea level; minimum (min) bilirubin concentration; SD and mean of total protein level; SD and CV of white blood cell (WBC) count; median cholesterol concentration; min Alanine Aminotransferase (ALT) activity; median potassium concentration; and CV of uric acid concentration. Statistical analysis was performed using the R 4.2.2 software package. Results. A model for identifying patients at high risk of kidney allograft rejection was developed. 63 Conclusions. The developed model allows identification of patients at high risk of kidney allograft rejection receiving triple-component immunosuppressive therapy, based on dynamic laboratory blood parameters.

Keywords: kidney transplantation, rejection, tacrolimus, rejection risk, prognostic model, machine learning.

References

  • 1. Tamargo CL, Kant S. Pathophysiology of Rejection in Kidney Transplantation Journal of Clinical Medicine. 2023 Jun;12(12):4130. doi: 10.3390/jcm12124130
  • 2. Gaston RS, Fieberg A, Hunsicker L, Kasiske BL, Leduc R, Cosio FG, et al. Late graft failure after kidney transplantation as the consequence of late versus early events. American Journal of Transplantation. 2018 May;18(5):1158-1167. doi: 10.1111/ajt.14590
  • 3. Redondo-Pachón D, Calatayud E, Buxeda A, PérezSáez MJ, Arias-Cabrales C, Gimeno J, et al. Evolution of kidney allograft loss causes over 40 years (1979-2019). Nefrologia. 2023 May-Jun;43(3):316-327. doi: 10.1016/j. nefroe.2023.07.003
  • 4. Kidney Disease: Improving Global Outcomes (KDIGO) Transplant Work Group (2009). KDIGO clinical practice guideline for the care of kidney transplant recipients. American Journal of Transplantation. 2009 Nov;9 Suppl 3:S1-155. doi: 10.1111/j.1600-6143.2009.02834.x
  • 5. Halloran PF, Madill-Thomsen KS, Böhmig G, Bromberg J, Budde K, Barner M, et al. Subthreshold rejection activity in many kidney transplants currently classified as having no rejection. American Journal of Transplantation. 2025 Jan;25(1):72-87. doi: 10.1016/j.ajt.2024.07.034
  • 6. Colvin RB, Cohen AH, Saiontz C, Bonsib S, Buick M, Burke B, et al. Evaluation of pathologic criteria for acute renal allograft rejection: reproducibility, sensitivity, and clinical correlation. Journal of the American Society of Nephrology. 1997 Dec;8(12):1930-1941. doi: 10.1681/ ASN.V8121930
  • 7. Yao Y, Astor BC, Yang W, Greene T, Li L. Predicting kidney graft function and failure among kidney transplant recipients. BMC Medical Research Methodology. 2024 Dec;24(1):324.
  • 8. Glmulti: model selection and multimodel inference made easy. URL: https://cran.r-project.org/package=glmulti [Accessed 11th August 2026].
  • 9. The R Project for Statistical Computing. R-project. URL: https://www.r-project.org [Accessed 11th August 2026].
  • 10. Youden WJ. Index for rating diagnostic testsю Cancer. 1950 Jan;3(1):32-35. doi: 10.1002/1097-0142(1950)3:13.0.co;2-3
  • 11. Hanley JA, McNeil BJ. The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology. 1982 Apr;143(1):29-36. doi: 10.1148/ radiology.143.1.7063747
  • 12. Surjanovic N, Loughin TM. Improving the Hosmer- 69 Lemeshow goodness-of-fit test in large models with replicated Bernoulli trials. Journal of Applied Statistics. 2023 Oct;51(7):1399-1411. doi: 10.1080/02664763.2023. 2272223
  • 13. Senanayake S, White N, Graves N, Healy H, Baboolal K, Kularatna S. Machine learning in predicting graft failure following kidney transplantation: a systematic review of published predictive models. International Journal of Medical Informatics. 2019;130:103957.
  • 14. Salaün A, Knight S, Wingfield L, Zhu T. Predicting graft and patient outcomes following kidney transplantation using interpretable machine learning models. Scientific Reports. 2024 Jul;14(1):17356.
  • 15. Minato ACDS, Hannun PGC, Barbosa AMP, da Rocha NC, Machado-Rugolo J, Cardoso MMA, et al. Machine Learning Model to Predict Graft Rejection After Kidney Transplantation. Transplantation Proceedings. 2023 Nov;55(9):2058-2062. doi: 10.1016/j. transproceed.2023.07.021
  • 16. Jo SJ, Park JB, Lee KW. Prediction of very early subclinical rejection with machine learning in kidney transplantation. Scientific Reports. 2023 Dec;13:22387.

Submitted 17.06.2026
Accepted 27.08.2026

Information about authors:

A.T. Shchastniy – Doctor of Medical Sciences, professor, head of the Chair of Hospital Surgery with the course of the Faculty for Advanced Training & Retraining, Vitebsk State Order of Peoples’ Friendship Medical University, https:// orcid.org/0000-0003-2796-4240;
A.S. Osochuk – lecturer of the Chair of Hospital Surgery with the course of the Faculty for Advanced Training & Retraining, Vitebsk State Order of Peoples’ Friendship Medical University, https://orcid.org/0000-0002-5942-3601;
Sergey S. Osochuk – Doctor of Medical Sciences, professor, head of the research laboratory, Vitebsk State Order of Peoples’ Friendship Medical University, ORCID: https://orcid.org/0000-0003-2074-3832, e-mail: Этот адрес электронной почты защищён от спам-ботов. У вас должен быть включен JavaScript для просмотра.;
A.F. Martsinkevich – Candidate of Biological Sciences, associate professor of the Chair of General & Clinical Biochemistry with the course of the Faculty for Advanced Training & Retraining, Vitebsk State Order of Peoples’ Friendship Medical University, https://orcid.org/0000-0003-3655-4489.

Поиск по сайту

0