Mortality estimation in chronic kidney disease based on artificial intelligence: a web-based support system
Keywords:
enfermedad renal crónica; mortalidad; inteligencia artificial; modelos predictivos; aplicación webAbstract
Introduction: Artificial intelligence-based predictive models for predicting mortality risk in patients with chronic kidney disease on hemodialysis are robust. The real impact would improve if they were translated into accessible, real-time tools.
Objective: To develop and implement an interactive, artificial intelligence-based web application for the individualized prediction of mortality risk in patients with chronic kidney disease on hemodialysis.
Methods: A clinical decision support system was developed based on a multilayer artificial neural network trained with clinical data from incident hemodialysis patients. TensorFlow and Keras were implemented in Python for its development. The network was trained with clinical data and exported to TensorFlow.js format for integration into the developed web application. Data preprocessing, variable standardization and cross-validation with 10 partitions were performed to evaluate model performance.
Results: The web application features an interactive from where the healthcare professional can enter relevant clinical data. The tool showed good calibration and discrimination. Cross-validation metrics provided a robust estimate of the model's overall performance. The applications allow for real-time predictions and features an intuitive and accessible interface.
Conclusions: The tool demonstrates a significant potential impact in the clinical setting for risk stratification of hemodialysis patients. It offers a list of personalized, data-driven recommendations for routine decision-making.
Downloads
References
1. GBD Chronic Kidney Disease Collaboration. Global, regional, and national burden of chronic kidney disease, 1990-2017: a systematic analysis for the Global Burden of Disease Study 2017. [Internet]. 2020 [consultado 10 nov 2025];395(10225)709-33. Disponible en: https://doi.org/10.1016/S0140-6736(20)30045-3
2. Jarrar F, Pasternak M, Harrison T, James M, Quinn R, Lam N, et al. Mortality Risk Prediction Models for People With Kidney Failure A Systematic Review. JAMA Network Open. [Internet]. 2025 [consultado 10 nov 2025];8(1):e2453190. Disponible en: https://doi.org/10.1001/jamanetworkopen.2024.53190
3. Liu P, Sawhney S, Jorgensen U, Quinn R, Jensen S, Mclean A, et al. Predicting the risks of kidney failure and deaths in adults with moderate to severe chronic kidney disease: multinational, longitudinal, population based, cohort study. BMJ. [Internet]. 2024 [consultado 10 nov 2025];385(1):e078063. Disponible en: https://dx.doi.org/10.1136/bmj-2023-078063
4. Gorke A. Dialysis Outcomes and Practice Patterns Study (DOPPS). Dialyse aktuell. [Internet]. 2016 [consultado 10 nov 2025];20(6):274-5. Disponible en: https://doi.org/10.1055/s-0042-110411
5. Pisoni R, Gillespie B, Dickinson D, Chen K, Kutner M, Wolfe R. The Dialysis Outcomes and Practice Patterns Study (DOPPS): design, data elements, and methodology. American Journal of Kidney Disease. [Internet]. 2004 [consultado 10 nov 2025];44(5):7-15. Disponible en: https://doi.org/10.1053/j.ajkd.2004.08.005
6. Ye Z, An S, Gao Y, Xie E, Zhao X, Guo Z, et al. The prediction of in-hospital mortality in chronic kidney disease patients with coronary artery disease using machine learning models. European Journal of Medical Research. [Internet]. 2023 [consultado 10 nov 2025];28(1):33. Disponible en: https://doi.org/10.1186/s40001-023-00995-x
7. Kumar Y, Koul A, Singla R, Ijaz M. Artificial intelligence in disease diagnosis: a systematic literature review, synthesizing framework and future research agenda. Journal of ambient intelligence and humanized computing. [Internet]. 2023 [consultado 10 nov 2025];14(7):8459-6. Disponible en: https://doi.org/10.1007/s12652-021-03612-z
8. Díez-Sanmartín C, Sarasa Cabezuelo A, Belmonte AA. A new approach to predicting mortality in dialysis patients using sociodemographic features based on artificial intelligence. Artificial Intelligence in Medicine. [Internet]. 2023 [consultado 10 nov 2025];136(1):102478. Disponible en: https://doi.org/10.1016/j.artmed.2022.102478
9. 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. Revista Cubana de Medicina Militar. [Internet]. 2024 [consultado 10 nov 2025];53(3):e024038408. Disponible en: https://revmedmilitar.sld.cu/index.php/mil/article/view/38408
10. He M. Performance and accuracy of Python distributed neural network training frameworks: Spark vs. TensorFlow in big data modeling and prediction. Applied and Computational Engineering. [Internet]. 2024 [consultado 10 nov 2025];92:52-8. Disponible en: https://doi.org/10.54254/2755-2721/92/20241729
11. Usman A, Abdul R, Uzair S, Majid H, Samraiz Z. A Privacy-Preserving System for Skin Disease Using a Lightweight CNN and TensorFlow.js for Client-Side Inference. Advance Social Science Archive Journal. [Internet]. 2025 [consultado 10 nov 2025];4(2):1785-97. Disponible en: https://doi.org/10.5281/zenodo.17656620
12. Meta Platforms, Inc. React: A JavaScript library for building user interfaces [Internet]. [consultado 10 nov 2025]. Disponible en: https://react.dev/
13. Vite.js. Vite: Next generation fronted tooling [Internet]. [consultado 10 nov 2025]. Disponible en: https://vitejs.dev/
14. Chollet. Keras. GitHub repository [Internet]. 2015-2025 [consultado 10 nov 2025]. Disponible en: https://github.com/keras-team/keras
15. Addepali L, Lokhande G, Sakinam S, Hussain S, Mookerjee J, Vamsi U, et al. Assessing the performance of Python data visualization libraries: a review. International Journal of Computer Engineering in Research Trends. [Internet]. 2023 [consultado 10 nov 2025]; 10(1):28-39. Disponible en: https://doi.org/10.22363/ijcert/2023/v10/i01/v10i0104
16. Bichri H, Chergui A, Hain M. Investigating the impact of train/test split ratio on the performance of pre-trained models with custom datasets. International Journal of Advanced Computer Science and Applications. [Internet]. 2024 [consultado 10 nov 2025]; 15(2):331-9. Disponible en: https://doi.org/10.14569/ijacsa.2024.0150235
17. Sclocchi A, Wyart M. On the different regimes of stochastic gradient descent. Computer Sciences. [Internet]. 2024 [consultado 10 nov 2025];121(9):e2316301121. Disponible en: https://doi.org/10.1073/pnas.2316301121
18. Brochet T, Lapuyade-Lahorque J, Huat A, Thureau S, Pasquier D, Gardin I, et al. A quantitative comparison between Shannon and Tsallis-Havrda-Charvat entropies applied to cancer outcome prediction. Entropy. [Internet]. 2022 [consultado 10 nov 2025];24:436. Disponible en: https://doi.org/10.3390/e24040436
19. Formik. Build forms in React, without the tears [Internet]. Formik; c2017-2025 [consultado 10 nov 2025]. Disponible en: https://formik.org/
20. Yup. Dead simple object schema validation [Internet]. Yup; c2016-2025 [consultado 10 nov 2025]. Disponible en: https://github.com/jquense/yup
21. Tailwind Labs, Inc. Tailwind CSS: A utility-first CSS framework [Internet]. San Francisco (CA): Tailwind Labs, Inc.; c2029-2025 [consultado 10 nov 2025]. Disponible en: https://tailwindcss.com/
22. Collins GS, Dhiman P, Andaur Navarro CL, Ma J, Hooft L, Reitsma JB, et al. Protocol for development of a reporting guideline (TRIPOD-AI) and risk of bias tool (PROBAST-AI) for diagnostic and prognostic prediction model studies based on artificial intelligence. BMJ Open. [internet]. 2021 [consultado 10 nov 2025];11:e048008. Disponible en: https://doi.org/10.1136/bmjopen-2020-048008
23. Kidney Disease: Improving Global Outcomes (KDIGO) CKD Work Group. KDIGO 2024 Clinical Practice Guideline for the Evaluation and Management of Chronic Kidney Disease. Kidney Int. [internet]. 2024 [consultado 10 nov 2025];105(4S): S117-S314. Disponible en: https://doi.org/10.1016/j.kint.2023.10.018
24. Almási AD, Wozniak S, Cristea V, Leblebici Y, Engbersen T. Review of advances in neural networks: Neural design technology stack. Neurocomputing. [Internet]. 2016 [consultado 10 nov 2025];174(1):31-41. Disponible en: https://doi.org/10.1016/j.neucom.2015.02.092
25. Escalona González SO, González Milán ZC. Inteligencia artificial en la predicción de mortalidad por enfermedad renal crónica. An Acad Cienc Cuba. [Internet]. 2022 [consultado 10 nov 2025];12(3):e1292. Disponible en: http://www.revistaccuba.cu/index.php/revacc/article/view/1292
26. Díaz-Canel Bermúdez M. Gestión de gobierno basada en ciencia e innovación: avances y desafíos. An Acad Cienc Cuba. [Internet]. 2022 [consultado 10 nov 2025];12(2):e1235. Disponible en: http://www.revistaccuba.cu/index.php/revacc/article/view/1235
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Sergio Orlando Escalona González, Ernesto Leonard Escariz, Yailé Caballero Mota, Yanela Rodríguez Alvarez, Zoraida Caridad González Milán
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
The journal Anales de la Academia de Ciencias de Cuba protects copyright, and operates with a Creative Commons License 4.0 (Creative Commons Attribution-NonCommercial License 4.0). By publishing in it, authors allow themselves to copy, reproduce, distribute, publicly communicate their work and generate derivative works, as long as the original author is cited and acknowledged. They do not allow, however, the use of the original work for commercial or lucrative purposes.
The authors authorize the publication of their writings, retaining the authorship rights, and assigning and transferring to the magazine all the rights protected by the intellectual property laws that govern in Cuba, which imply editing to disseminate the work.
Authors may establish additional agreements for the non-exclusive distribution of the version of the work published in the journal (for example, placing it in an institutional repository or publishing it in a book), with recognition of having been first published in this journal.
To learn more, see https://creativecommons.org
