Prediction of Post-donation Renal Function Using Machine Learning Techniques and Conventional Regression Models in Living Kidney Donors

Overview

Journal J Nephrol

Publisher Springer

Specialty Nephrology

Date 2024 Jul 29

PMID 39073700

Authors

Junseok Jeon

Yeejun Song

Jae Yong Yu

Weon Jung

Kyungho Lee

Jung Eun Lee

Wooseong Huh

Won Chul Cha

Hye Ryoun Jang

Affiliations

Soon will be listed here.

Abstract

Background: Accurate prediction of renal function following kidney donation and careful selection of living donors are essential for living-kidney donation programs. We aimed to develop a prediction model for post-donation renal function following living kidney donation using machine learning.

Methods: This retrospective cohort study was conducted with 823 living kidney donors between 2009 and 2020. The dataset was randomly split into training (80%) and test sets (20%). The main outcome was the post-donation estimated glomerular filtration rate (eGFR) 12 months after nephrectomy. We compared the performance of machine learning techniques, traditional regression models, and models from previous studies. The best-performing model was selected based on the mean absolute error (MAE) and root mean square error (RMSE).

Results: The mean age of the participants was 45.2 ± 12.3 years, and 48.4% were males. The mean pre-donation and post-donation eGFRs were 101.3 ± 13.0 and 68.8 ± 12.7 mL/min/1.73 m, respectively. The XGBoost model with the eGFR, age, serum creatinine, 24-h urine creatinine, 24-h urine sodium, creatinine clearance, cystatin C, cystatin C-based eGFR, computed tomography volume of the remaining kidney/body weight, normalized GFR of the remaining kidney measured through a diethylenetriaminepentaacetic acid scan, and sex, showed the best performance with a mean absolute error of 6.23 and root mean square error of 8.06. An easy-to-use web application titled Kidney Donation with Nephrologic Intelligence (KDNI) was developed.

Conclusions: The prediction model using XGBoost accurately predicted the post-donation eGFR after living kidney donation. This model can be applied in clinical practice using KDNI, the developed web application.

Citing Articles

The Use of Machine Learning in the Diagnosis of Kidney Allograft Rejection: Current Knowledge and Applications.

Belcic Mikic T, Arnol M Diagnostics (Basel). 2024; 14(22).

PMID: 39594148 PMC: 11592658. DOI: 10.3390/diagnostics14222482.

References

Thurlow J, Joshi M, Yan G, Norris K, Agodoa L, Yuan C . Global Epidemiology of End-Stage Kidney Disease and Disparities in Kidney Replacement Therapy. Am J Nephrol. 2021; 52(2):98-107. PMC: 8057343. DOI: 10.1159/000514550. View

Hong Y, Ban T, Kang C, Hwang S, Choi S, Lee H . Trends in epidemiologic characteristics of end-stage renal disease from 2019 Korean Renal Data System (KORDS). Kidney Res Clin Pract. 2021; 40(1):52-61. PMC: 8041639. DOI: 10.23876/j.krcp.20.202. View

Hariharan S, Israni A, Danovitch G . Long-Term Survival after Kidney Transplantation. N Engl J Med. 2021; 385(8):729-743. DOI: 10.1056/NEJMra2014530. View

Cho W . Organ donation in Korea in 2018 and an introduction of the Korea national organ donation system. Korean J Transplant. 2022; 33(4):83-97. PMC: 9188944. DOI: 10.4285/jkstn.2019.33.4.83. View

Grams M, Sang Y, Levey A, Matsushita K, Ballew S, Chang A . Kidney-Failure Risk Projection for the Living Kidney-Donor Candidate. N Engl J Med. 2015; 374(5):411-21. PMC: 4758367. DOI: 10.1056/NEJMoa1510491. View

Kang E, Park J, Kim H, Park S, Park M, Kim Y . Metabolic risks in living kidney donors in South Korea. Kidney Res Clin Pract. 2021; 40(4):645-659. PMC: 8685357. DOI: 10.23876/j.krcp.20.271. View

Levey A, Inker L . GFR Evaluation in Living Kidney Donor Candidates. J Am Soc Nephrol. 2017; 28(4):1062-1071. PMC: 5373464. DOI: 10.1681/ASN.2016070790. View

Ibrahim H, Foley R, Tan L, Rogers T, Bailey R, Guo H . Long-term consequences of kidney donation. N Engl J Med. 2009; 360(5):459-69. PMC: 3559132. DOI: 10.1056/NEJMoa0804883. View

Mueller T, Luyckx V . The natural history of residual renal function in transplant donors. J Am Soc Nephrol. 2012; 23(9):1462-6. DOI: 10.1681/ASN.2011111080. View

10.

Kwon H, Kim D, Jang H, Jung S, Han D, Sung H . Predictive Factors of Renal Adaptation After Nephrectomy in Kidney Donors. Transplant Proc. 2017; 49(9):1999-2006. DOI: 10.1016/j.transproceed.2017.09.024. View

11.

Hall I, Shaaban A, Wei G, Sikora M, Bourija H, Beddhu S . Baseline living-donor kidney volume and function associate with 1-year post-nephrectomy kidney function. Clin Transplant. 2019; 33(3):e13485. PMC: 6487946. DOI: 10.1111/ctr.13485. View

12.

Benoit T, Game X, Roumiguie M, Sallusto F, Doumerc N, Beauval J . Predictive model of 1-year postoperative renal function after living donor nephrectomy. Int Urol Nephrol. 2017; 49(5):793-801. DOI: 10.1007/s11255-017-1559-1. View

13.

van Londen M, van der Weijden J, Niznik R, Mullan A, Bakker S, Berger S . Prediction of measured GFR after living kidney donation from pre-donation parameters. Nephrol Dial Transplant. 2022; 38(1):212-221. PMC: 9869859. DOI: 10.1093/ndt/gfac202. View

14.

Levey A, Stevens L, Schmid C, Zhang Y, Castro 3rd A, Feldman H . A new equation to estimate glomerular filtration rate. Ann Intern Med. 2009; 150(9):604-12. PMC: 2763564. DOI: 10.7326/0003-4819-150-9-200905050-00006. View

15.

Benoit T, Prudhomme T, Adypagavane A, Malavaud B, Soulie M, Game X . External Validation of a Predictive Model to Estimate Renal Function After Living Donor Nephrectomy. Transplantation. 2021; 105(11):2445-2450. DOI: 10.1097/TP.0000000000003643. View

16.

Rajula H, Verlato G, Manchia M, Antonucci N, Fanos V . Comparison of Conventional Statistical Methods with Machine Learning in Medicine: Diagnosis, Drug Development, and Treatment. Medicina (Kaunas). 2020; 56(9). PMC: 7560135. DOI: 10.3390/medicina56090455. View

17.

Montomoli J, Romeo L, Moccia S, Bernardini M, Migliorelli L, Berardini D . Machine learning using the extreme gradient boosting (XGBoost) algorithm predicts 5-day delta of SOFA score at ICU admission in COVID-19 patients. J Intensive Med. 2023; 1(2):110-116. PMC: 8531027. DOI: 10.1016/j.jointm.2021.09.002. View

18.

Brar A, Jindal R, Abbott K, Hurst F, Salifu M . Practice patterns in evaluation of living kidney donors in United Network for Organ Sharing-approved kidney transplant centers. Am J Nephrol. 2012; 35(5):466-73. DOI: 10.1159/000338450. View

19.

Kwon H, Jeon J, Kim D, Jang H, Sung H, Han D . Clinical Impact of a Protocolized Kidney Donor Follow-up System. Transplant Proc. 2019; 51(3):692-700. DOI: 10.1016/j.transproceed.2018.10.026. View

20.

Nankivell B, Nankivell L, Elder G, Gruenewald S . How unmeasured muscle mass affects estimated GFR and diagnostic inaccuracy. EClinicalMedicine. 2021; 29-30:100662. PMC: 7788434. DOI: 10.1016/j.eclinm.2020.100662. View