Apparent validity, reliability and internal consistency of a predictive model of mortality in patients with end-stage renal disease

Authors

Keywords:

chronic kidney disease; internal consistency; predictive model; reliability; validation

Abstract

Introduction: Although several predictive models of mortality in chronic kidney disease exist, the evidence for validity, reliability and internal consistency metrics is limited and heterogeneous, affecting applicability and generalizability.

Objective: To evaluate apparent validity, reliability and internal consistency of a predictive model of mortality in chronic kidney disease.

Methods: A descriptive study was conducted to validate the criteria, reliability and internal consistency. A purposive sample of 10 experts was administered a questionnaire about a predictive model of mortality in patients with chronic kidney disease, using the expert consensus method described by Delphi. The overall Cronbach’s alpha coefficient was determined and it was calculated for each of the predictors of the predictive model. The Spearman-Brown split-half method was used for the internal consistency analysis.

Results: Experts demonstrated a K coefficient > 0.8 for predicting mortality in chronic kidney disease. Reliability was high (α = 0.824), indicating outstanding reproducibility of the estimates. If the predictors cardiovascular disease, albumin < 30 g/L and sepsis are removed from the predictive model, the overall alpha score decreases. The Spearman-Brown coefficient = 0.842 indicates adequate correlation and consistency among the predictors for measuring the construct.

Conclusions: The predictive model demonstrated strong face validity, high reliability and adequate internal consistency and can therefore be used as a clinical support tool.

Downloads

Download data is not yet available.

References

1. Bello A, Okpechi I, Osman M, Cho Y, Htay H, Jha V, et al. Epidemiology of haemodialysis

outcomes [Internet]. Nature Reviews Nephrology 2022;47(8):835–850. DOI: https://doi.org/10.1038/s41581-022-00542-7

2. Chadban S, Arici M, Power A, Wu MS, Mennini FS, Arango-Álvarez JJ, et al. Projecting the economic burden of chronic kidney disease at the patient level (Inside CKD): a microsimulation modelling study [Internet]. EClinicalMedicine 2024;72(1):102615. DOI: https://doi.org/10.1016/j.eclinm.2024.102615

3. Escalona-González SO, González-Milán ZC. Predicción de mortalidad en pacientes con enfermedad renal crónica en hemodiálisis: inteligencia artificial frente a los modelos predictivos tradicionales [Internet]. Revista Electrónica Dr. Zoilo E. Marinello Vidaurreta 2025 [acceso: 06/07/2025]; 50(1):e3914. Disponible en: https://revzoilomarinello.sld.cu/index.php/zmv/article/view/3914

4. Hippisley-Cox J, Coupland C, Bafadhel M, Russell R, Sheikh A, Brindle P, et al. Development and validation of a new algorithm for improved cardiovascular risk prediction [Internet]. Nature Medicine 2024;30(5):1440-7. DOI: https://doi.org/10.1038/s41591-024-02905-y

5. Wlliams K, Michalska S, Cohen E, Szomszor M, Grant J. Exploring the application of machine learning to expert evaluation of research impact [Internet]. Plos one 2023;18(8):e0288469. DOI: https://doi.org/10.1371/journal.pone.0288469

6. Rahrooh A, Garlid AO, Bartlett K, Coons W, Petousis P, Hsu W, et al. Towards a framework for interoperability and reproducibility of predictive models [Internet]. Journal of Biomedical Informatics 2024;149(1):104551. DOI: https://doi.org/10.1016/j.jbi.2023.104551

7. Luo W, Phung D, Tran T, Gupta S, Rana S, Karmakar C, et al. Guidelines for developing and reporting machine learning predictive models in biomedical research: a multidisciplinary view [Internet]. Journal of medical Internet research. 2016;18(12):e323. DOI: https://doi.org/10.2196/jmir.5870

8. Escalona-González SO, Caballero-Mota Y, Rodríguez-Alvarez Y, León-Acebo M, González-Milán ZC, Ricardo-Páez B, et al. Red neuronal artificial para la predicción de mortalidad de pacientes con enfermedad renal crónica [Internet]. Revista Cubana de Medicina Militar. 2024 [acceso: 06/07/2025]; 53(3):e024038408. Disponible en: https://revmedmilitar.sld.cu/index.php/mil/article/view/38408

9. Burguet Lago I, Rodríguez Rabelo A, Jorge Chacón D. Aplicación de tecnologías para la determinación de la competencia de los expertos [Internet]. Revista Cubana de Ciencias Informáticas 2019 [acceso: 06/07/2025];13(1):116-26. Disponible en: http://scielo.sld.cu/scielo.php?pid꞊S2227-18992019000100116&script꞊sci_arttext&tlng꞊en

10. Rivera-Cantos GL, Orellana-Romero JE, Barzola-Veliz VM. Validación de una estrategia educativa mediante el método de criterio de expertos o Delphi [Internet]. Revista Estudios del Desarrollo Social: Cuba y América Latina. 2023 [acceso: 06/07/2025];11(3):e40. Disponible en: http://scielo.sld.cu/scielo.php?pid=S2308-01322023000300040&script=sci_arttext

11. Majszak M, Jebeile J. Expert judgment in climate science: How it is used and how it can be justified [Internet]. Studies in history and philosophy of science. 2023;100(1):32-8. DOI: https://doi.org/10.1016/j.shpsa.2023.05.005

12. Belmar-Garrido HM. Expert validation of a Python test, reliability, difficulty and discrimination indices [Internet]. Journal of Education and Development. 2023;7(1):52. DOI: https://doi.org/10.20849/jed.v7i1.1320

13. Rodríguez-Rodríguez J, Reguant-Alvarez M. Calcular la fiabilidad de un cuestionario o escala mediante el SPSS: el coeficiente alfa de Cronbach [Internet]. Revista de innovación e investigación. 2020;13(2):8. DOI: https://doi.org/10.1344/reire2020.13.230048

14. Luo W, Phung D, Tran T, Gupta S, Rana S, Karmakar C, et al. Guidelines for developing and reporting machine learning predictive models in biomedical research: a multidisciplinary view [Internet]. Journal of medical Internet research. 2016;18(12):e323. DOI: https://doi.org/10.2196/jmir.5870

15. Díez-Sanmartín C, Sarasa Cabezuelo A, Belmonte AA. A new approach to predicting mortality in dialysis patients using sociodemographic features based on artificial intelligence [Internet]. Artificial Intelligence in Medicine. 2023;136(1):102478. DOI: https://doi.org/10.1016/j.artmed.2022.102478

16. Evangelidis N, Tong A, Manns B, Hemmelgarn B, Wheeler DC, Tugwell P, et al. Developing a set of score outcomes for trials inhemodialysis: an international Delphi survey [Internet]. American Journal of Kidney Diseases. 2017;70(4):464-475. DOI: https://doi.org/10.1053/j.ajkd.2016.11.029

17. Kalkbrenner MT. Alpha, omega, and H internal consistency reliability estimates: reviewing these options and when to use them [Internet]. Counseling Outcome Research and Evaluation. 2023;14(1):77-88. DOI: https://doi.org/10.1080/21501378.2021.1940118

18. Peterson RA, Kim Y. On the relationship between coefficient alpha and composite reliability [Internet]. Journal of applied psychology 2013;98(1):194-8. DOI: https://doi.org/10.1037/a0030767

19. Toro R, Peña-Sarmiento M, Avendaño-Prieto BL, Mejía-Vélez S, Bernal-Torres A. Análisis empírico del coeficiente Alfa de Cronbach en función de las opciones de respuesta a las preguntas, tamaño de la muestra y valores atípicos [Internet]. Revista Iberoamericana de Diagnóstico y Evaluación Psicológica. 2022 [acceso: 06/07/2025];63(1):1-18. Disponible en: https://www.redalyc.org/journal/4596/459671926003/html/

20. Fitriani A, Yetti K, Sukmarini L. Contributing factors to hemodialysis adherence in Aceh, Indonesia [Internet]. Enfermeria clínica. 2019;29(2):238-42. DOI: https://doi.org/10.1016/j.enfcli.2019.04.028

21. Petch J, Di S, Nelson W. Opening the black box: the promise and limitations of explainable machine learning in Cardiology [Internet]. Canadian Journal of Cardiology. 2022 [acceso: 06/07/2025]; 38(2):204-213. DOI: https://doi.org/10.1016/j.cjca.2021.09.004

22. Nazer L, Zatarah R, Waldrip S, Ke J, Moukheiber M, Khanna A, et al. Bias in artificial intelligence algorithms and recommendations for mitigation [Internet]. PLOS digital health 2023;2(6):e0000278. DOI: https://doi.org/10.1371/journal.pdig.0000278

23. Walsh I, Fishman D, Garcia-Gasulla D, Titma T, Pollastri G, Harrow J, et al. DOME: recommendations for supervised machine learning validation in biology [Internet]. Nature Methods 2021;18(1):1122-7. DOI: https://doi.org/10.1038/s41592-021-01205-4

Downloads

Published

2026-05-30

How to Cite

1.
Escalona González SO, González Milán ZC, Caballero Mota Y, Rodríguez Alvarez Y, Hernández Navarro D, Villar Bahamonde A, et al. Apparent validity, reliability and internal consistency of a predictive model of mortality in patients with end-stage renal disease. Rev. cuba. med. mil [Internet]. 2026 May 30 [cited 2026 Aug. 13];55(2):e026077345. Available from: https://revmedmilitar.sld.cu/index.php/mil/article/view/77345

Issue

Vol. 55 No. 2 (2026): April - June

Section

Research Article

License

Copyright (c) 2026 Sergio Orlando Escalona González, Zoraida Caridad González Milán, Yailé Caballero Mota, Yanela Rodríguez Alvarez, Diamela Hernández Navarro, Andrés Villar Bahamonde, Raymar Molina Vega

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.