Development of a predictive model for chronic kidney disease

Authors

Keywords:

albuminuria, lymphocytes, logistic models, neutrophils, predictive value of tests, prospective studies, renal insufficiency, chronic

Abstract

Introduction: Predictive models for chronic kidney disease (CKD) have become tools for addressing a health problem that affects 10% of the world's population. Their development is necessary to identify progression patterns and therapeutic options in a disease that is silent in its early stages.

Objective: To develop a predictive model for detecting the progression of chronic kidney disease.

Methods: Type of study: prospective analytical; universe: nephrology patients from January 2022 to March 2024 with CKD stage 1-4 (600); sample: 267 patients obtained by simple random sampling without replacement; variables: age, sex, skin color, history of toxic habits, personal medical history, blood glucose, creatinine, urea, cholesterol, triglycerides, blood count, lymphocytes, neutrophils, neutrophil-lymphocyte ratio (NLR), and albuminuria obtained from the medical record. A temporal partition of the sample (67.5%) was performed to build the model, using ordinal logistic regression (95% confidence interval).

Results: The model classified 81.6% of patients, with errors in 16.4% of cases. It explained 68% of the changes in the dependent variable; increased creatinine, albuminuria, and NLR increase the likelihood of CKD progression.

Conclusion: The prognostic model performs adequately for the risk of CKD progression, and Proper patient classification explains more than fifty percent of the changes in the variable studied. The final model, which included creatinine, albuminuria and NLR, showed discrete results in categories 3 and 4.

Downloads

Download data is not yet available.

References

1. Gallardo LS, Rodríguez AJ, Burgos M, Martínez ML, García P, Villagrán ME, et al. Utilidad de un modelo de predicción para la enfermedad renal crónica en una unidad de primer nivel de atención [Internet]. Nefrología. 2016; 36(2): 89-216. DOI: https://doi.org/10.1016/j.nefro.2015.10.010

2. Lim DKE, Boyd JH, Thomas E, Chakera A, Tippaya S, Irish A, et al. Prediction models used in the Progression of chronic kidney disease: A scoping review [Internet]. PlosOne. 2022;17(7): e0271619. DOI: https://doi.org/10.1371/journal.pone.0271619

3. Reddy S, Roy S, Choy KW, Sharma S, Dwyer KM, Manapragada C, et al. Predicting chronic kidney disease progression using small pathology datasets and explainable machine learning models [Internet]. Computer Methods and Programs in Biomedicine Update. 2024;6: [aprox. 34 p.]. DOI: https://doi.org/10.1016/j.cmpbup.2024.100160

4. Giraldo-Castrillón Y, Arango C, Molina CF, Segura A. Usability of predictive models of kidney failure in chronic kidney disease: a scoping review [Internet]. CES Med. 2022;36(3): 69-85. DOI: https://doi.org/10.21615/cesmedicina.6987

5. Collins GS, Moons KGM. Reporting of artificial intelligence prediction models [Internet]. Lancet. 2019;20(393): 1577-79. DOI: https://doi.org/10.1016/S0140-6736

6. Escalona-González SO, González- Milán ZC. Inteligencia artificial en la predicción de mortalidad por enfermedad renal crónica [Internet]. Anales de la ACC. 2022;12(3):[aporx. 2 p.] Disponible en: http://scielo.sld.cu/scielo.php?pid=S2304-01062022000300004&script=sci_arttext

7. Ferguson T, Ravani P, Sood MM, Clarke A, Komenda P, Rigatto C, et al. Development and external validation of a machine learning model for progression of CKD [Internet]. Kidney Int Rep. 2022;7(8):1772-81. DOI: https://doi.org/10.1016/j.ekir.2022.05.004

8. Olczak J, Pavlopoulos J, Prijs J, Doornberg JN, Lundstrom C, Hedlund J, et al. Presenting artificial intelligence, deep learning, and machine learning studies to clinicians and healthcare stakeholders: an introductory reference with a guideline and a Clinical AI Research (CAIR) checklist proposal [Internet]. Acta Orthop. 2021; 92(5): 513–25.DOI: https://doi:10.1080/17453674.2021.1918389

9. Reddy S, Fox J, Purohit MP. Artificial intelligence-enabled healthcare delivery [Internet]. J R Soc Med. 2019; 112(1): 22–28. DOI: https://doi.org/10.1177/0141076818815510

10. Reddy S. Explainability and artificial intelligence in medicine [Internet]. Lancet Digit Health. 2022; 4(4):214–15. DOI: https//doi.org/10.1016/S2589-7500(22)00029-2

11. Ebbehoj A, Thunbo MO, Andersen OE, Glindtvad MV, Hulman A. Transfer learning for non-image data in clinical research: a scoping review [Internet]. Plos Digit Health. 2022; 1(2):1-22. DOI: https//doi.org/10.1371/journal.pdig.0000014

12. Chan L, Nadkarni GN, Fleming F, McCullough JR, Connolly P, Mosoyan G, et al. Derivation and validation of a machine learning risk score using biomarker and electronic patient data to predict progression of diabetic kidney disease [Internet]. Diabetología. 2021; 64(7):1504–1515. DOI: https//doi.org/101007/s00125-021-05444-0

13. Liu J, Wu J, Liu S, Li M, Hu K, Li K. Predicting Mortality of patient with acute kidney injury in the ICU using XGBoost model [Internet]. Plos One. 2021; 16(2)1-11: DOI: https//doi.org/10.1371/journal.pone.0246306

14. Tangri N, Kitsios GD, Inker LA, Griffith J, Naimark DM, Walker S, et al. Risk prediction models for patients with CKD [Internet]. Annals of Internal Medicine. 2013; 158(8):596- 603. DOI: https//doi.org/10.7326/0003-4819-158-8-201304160-00004

15. Tofallis C. A better measure of relative prediction accuracy for model selection and model estimation [Internet]. JORS. 2015; 66(8): 1352–62. DOI: https://doi.org/10.1057/jors.2014.103

16. Levey AS, Stevens LA, Schmid CH, Zhang Y, Castro AF, Feldman H, et al. A new equation to estimate glomerular filtration rate [Internet]. Ann Intern Med. 2011;155(6): 604-12. DOI: https://doi.org/10.7326/0003-4819-150-9-200905050-00006

17. Asociación Médica Mundial. Declaración de Helsinki de la AMM – Principios éticos para las investigaciones médicas con participantes humanos. WMA; 2024. [acceso: 09/06/2025]. Disponible en: https://www.wma.net/es/policies-post/declaracion-de-helsinki-de-la-amm-principios-eticos-para-las-investigaciones-medicas-en-seres-humanos/

18. Gallardo V, Rodríguez J, Burgos O. Utilidad de un modelo de predicción para la Enfermedad Renal Crónica en una unidad de primer nivel de atención [Internet]. Nefrología (Madr.). 2016 [acceso: 09/06/2025]; 36(2): 196-8. Disponible en https://scielo.isciii.es/scielo.php?pid=S0211-69952016000200196&script=sci_arttext&tlng=en

19. Bai Q, Su C, Tang W, Li Y. Machine learning to predict end stage kidney disease in chronic kidney disease [Internet]. Scientific Reports. 2022: 8377. DOI: https://doi.org/10.1038/s41598-022-1236-z

20. Australian Institute of Health and Welfare (AIHW). Chronic kidney disease: Australian facts [Internet]. Canberra: Australian Institute of Health and Welfare; 2024. [acceso: 09/06/2025]. Disponible en: https://www.aihw.gov.au/reports/chronic-kidney-disease

21. Miranda Machado PA. Progression of chronic kidney disease in over 65-year-old nephroprotection program patients in Colombia [Internet]. Rev Colomb Nefrol. 2023;10(2):1-10. DOI: https://doi.org/10.22265/acnef.10.2.659

22. Lim DKE, Boyd JH, Thomas E, Chakera A, Tippay S, Irish A, et al. Prediction models used in the progression of chronic kidney disease: A scoping review [Internet]. PLoS One. 2022; 17(7):1-24. DOI: https://doi.org/10.1371/journal.pone.0271619

23. Martínez-Castelao A, Górriz JL, Bóver J, Segura de la Morena JC, Escalada J, Esmatjes E, et al. Documento de consenso para la detección y manejo de la enfermedad renal crónica [Internet]. Nefrología (Madr.). 2014; 34(2): 243-62. DOI: https://doi.org/103265/Nefrología.pre2014.Feb.12455

24. Batista D, Estrada JC, Morell L. Enfermedad renal crónica y factores de progresión en pacientes con diabetes mellitus tipo 2 [Internet]. Revista Información Científica. 2024; 103:e4611. DOI. https://doi.org/10.5281/zenodo.10999895

25. Burlacu A, Namolovan CA, Covic A, Goldsmith DJ, Kanbay M. Neutrophil-to-Lymphocyte Ratio (NLR). Independent prognostic marker of renal function decline in chronic kidney disease: A systematic review and meta-analysis [Internet]. 2025;14(19):6822. DOI: https://doi.org/103390/jmc1496822

Downloads

Published

2026-01-05

How to Cite

1.
Castillo Deprés D, Castillo Deprés S, Delgado Ramos A, Vidal Ledo MJ. Development of a predictive model for chronic kidney disease. Rev. cuba. med. mil [Internet]. 2026 Jan. 5 [cited 2026 Jan. 13];55(1):e026076995. Available from: https://revmedmilitar.sld.cu/index.php/mil/article/view/76995

Issue

Vol. 55 No. 1 (2026): January - March (In progress)

Section

Research Article

License

Copyright (c) 2025 Dania Castillo Deprés, Saymara Castillo Deprés, Ariel Delgado Ramos, María Josefina Vidal Ledo

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

Authors who have publications with this Journal accept the following terms:

  • The authors will retain their copyright and guarantee the Journal the right of first publication of their work, which will simultaneously be subject to the Creative Commons Attribution License. The content presented here can be shared, copied and redistributed in any medium or format; Can be adapted, remixed, transformed or created from the material, using the following terms: Attribution (giving appropriate credit to the work, providing a link to the license, and indicating if changes have been made); non-commercial (you cannot use the material for commercial purposes) and share-alike (if you remix, transform or create new material from this work, you can distribute your contribution as long as you use the same license as the original work).
  • The authors may adopt other non-exclusive license agreements for the distribution of the published version of the work (for example: depositing it in an institutional electronic archive or publishing it in a monographic volume) as long as the initial publication in this Journal is indicated.
  • Authors are allowed and recommended to disseminate their work through the Internet (e.g., in institutional electronic archives or on their website) before and during the submission process, which can produce interesting exchanges and increase citations. of the published work.