An artificial neural network for the prediction of mortality in patients with chronic kidney disease
Keywords:
artificial intelligence, chronic kidney disease, computing neural networks, hemodialysis, machine learning, mortality.Abstract
Introduction: Early mortality in patients with chronic kidney disease represents a major health problem, which is why the design of novel prognostic models is a priority.Objective: Design an artificial neural network for the prediction of mortality in patients with chronic kidney disease on hemodialysis.
Methods: A prospective cohort analytical study was conducted in patients with chronic kidney disease on hemodialysis during the period from January 1, 2013 to December 31, 2017. A total of 36 attributes were analyzed in 392 patients. The multilayer perceptron was used to design an artificial neural network composed of 12 variables. Finally, the classification table, the discriminatory capacity of the algorithm and the normalized importance of the prognostic variables were evaluated.
Results: The artificial neural network presented overall correct classification percentages of a 96.3% in the training sample and a 96.7% in the validation sample. The discriminatory capacity was very good, area ROC of 0.989. The most important normalized predictors of mortality were cardiovascular disease, albumin, and sepsis.
Conclusions: The artificial neural network contributes to the stratification of mortality risk of patients with chronic kidney disease on hemodialysis. The model has good discriminatory capacity and indicators of statistical effectiveness. The prognostic variables identified are easy to determine and interpret, which is why it is considered a predictive tool with useful implementation in medical decision making in the clinical setting.
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; 18(6):378-95. DOI: 10.1038/s41581-022-00542-7
2. Anuario Estadístico de Salud, 2022. Ministerio de Salud Pública. Dirección de Registros médicos y Estadísticas de salud [Internet]. La Habana, 2023 [acceso: 15/11/2023]. Disponible en: http://bvscuba.sld.cu/anuario-estadistico-de-cuba/
3. Koteluk O, Wartecki A, Mazurek S, Kołodziejczak I, Mackiewicz A. How Do Machines Learn? Artificial Intelligence as a New Era in Medicine [Internet]. J Pers Med. 2021; 11(1):1-22. DOI: 10.3390/jpm11010032
4. Sarker IH. Machine learning: algorithms, real-world applications and research directions [Internet]. SN Computer Science. 2021; 2(3):1-21. DOI: 10.1007/s42979-021-00592-x
5. Park S, Park BS, Lee YJ, Kim H, Park JH, Ko J, et al. Artificial intelligence with kidney disease A scoping review with bibliometric analysis, PRISMA-ScR [Internet]. Medicine. 2021; 100(14):e25422. DOI: 10.1097/MD.0000000000025422
6. Khazaei S, Najafi Ghobadi S, Ramezani Doroh V. Construction data mining methods in the prediction of death in hemodialysis patients using support vector machine, neural network, logistic regression and decision tree [Internet]. J Prev Med Hyg. 2021; 62(1):E222-30. DOI: 10.15167/2421-4248/jpmh2021.62.1.1837
7. Gamboa Graus ME. Estadística aplicada a la investigación educativa [Internet]. Revista Dilemas Contemporáneos: Educación, política y valores. 2018 [acceso:15/11/2023]; 5(2):1-32. Disponible en: http://www.dilemascontemporaneoseducacionpoliticayvalores.com/i-ndex.php/dilemas/article/view/427/443
8. de Arriba G, Gutiérrez Ávila G, Torres Guinea M, Moreno Alia I, Herruzo JA, Rincón Ruiz B, et al. La mortalidad de los pacientes en hemodiálisis está asociada con su situación clínica al comienzo del tratamiento [Internet]. Nephrology. 2021; 41(4):461-6. DOI: 10.1016/j.nefro.2020.11.006
9. Ruperto M, Barril G. Nutritional status, body composition, and inflammation profile in older patients with advanced chronic kidney disease stage 4-5: A case control study [Internet]. Nutrients. 2022; 14(17):3650. DOI: 10.3390/nu14173650
10. Matsushita K, Ballew S, Wang A. Epidemiology and risk of cardiovascular disease in populations with chronic kidney disease [Internet]. Nature Reviews Nephrology. 2022; 18(11):696-707. DOI: 10.1038/s41581-022-00616-6
11. Lee S, Kang S, Joo Y. Smoking, smoking cessation, and progression of chronic kidney disease: results form KNOW-CKD study [Internet]. Nicotine & Tobacco Research. 2021; 23(1):92-8. DOI: 10. 1093/ntr/ntaa071
12. Liang X, Ye M, Tao M. The association between dyslipidemia and the incidence of chronic kidney disease in the general Zhejiang population: a retrospective study [Internet]. BMC Nephrol. 2020; 21(252):1-9. DOI: 10. 1186/s12882-020-01907-5
13. Feng-Ching S, Yi-Wen Ch, Mei-Chuan K. U-shaped association between waist-to-hip ratio and all-cause mortality in stage 3-5 chronic kidney disease patients with body mass index paradox [Internet]. J Pers Med. 2021; 11(12):1355. DOI: 10.3390/jpm11121355
14. Jan M, Deseo J. Balancing Nephrology Referrals With Nephrologist Capacity to Decrease Emergency Dialysis Starts [Internet]. Ki Reports. 2020; 6(1):7-10. DOI: 10.1016/j.ekir.2020.11.014
15. Hsu C, Parikh R, Pravoverov L. Implication of trends in timing of dialysis initiation for incidence of end-stage kidney disease [Internet]. JAMA Intern Med. 2020; 180(12):1647-54. DOI: 10.1001/jamainternmed.2020.5009
16. Bossola M, Pepe G, Antocicco M, Severino A, Di Stasio E. Interdialytic weight gain and educational/cognitive, counseling/behavioral and psychological/affective interventions in patients on chronic hemodialysis: a systematic review and meta-analysis [Internet]. Journal of Nephrology. 2022; 35(1):1973-83. DOI: 10.1007/s40620-022-01450-6
17. Romero J, León E. Algoritmos en el manejo de muestras y variables en bioestadística [Internet].16 de Abril. 2018 [acceso:15/11/2023]; 57(269):177-194. Disponible en: https://rev16deabril.sld.cu/index.php/16_04/article/view/770
18. Rossello X, González-Del-Hoyo M. Análisis de supervivencia en investigación cardiovascular (I): lo esencial [Internet]. Rev Esp Cardiol. 2022; 75(1):67-76. DOI: 10.1016/j.recesp.2021.05.017
19. Schlüter M, Nlte G, Murtovi A, Steffen B. Towards rigorous understanding of neural networks via semantics-preserving transformations [Internet]. International Journal on Software Tools for Technology Transfer. 2023; 25(3):301-27. DOI: 10.1007/s10009-023-00700-7
20. Celard P, Lorenzo Iglesias E, Sorribes-Fernández JM, Romero R, Seara Vieira A, Borrajo L. A survey on deep learning applied to medical images: from simple artificial networks to generative models. [Internet]. Neural Computing and Applications. 2023; 35(3):2291-323. DOI: 10.1007/s00521-022-07953-4
21. Bai Q, Su C, Tang W, Li Y. Machine learning to predict end stage kidney disease in chronic kidney disease [Internet]. Scientific Reports. 2022; 12(1):8377. DOI: 10.1038/s41598-022-12316-z
22. Elbasha A, Naga Y, Othman M, Moussa N, Elwakil H. A step towards the application of an artificial intelligence model in the prediction of intradialytic complications [Internet]. Alexandria Journal of Medicine. 2022; 58(1):18-30. DOI: 10.1080/20905068.2021.2024349
23. Singh V, Asari V, Rajasekaran R. A Deep Neural Network for Early Detection and Prediction of Chronic Kidney Disease [Internet]. Diagnostics. 2022; 12(1):1-22. DOI: 10.3390/diagnostics12010116
24. Liu H, Wang R. Associations between the serum magnesium and all-cause or cardiovascular mortality in chronic kidney disease and end-stage renal disease patients. A meta-analysis [Internet]. Medicine. 2021; 100(45):e27486. DOI: 10.1097/MD.0000000000027486
25. Zeng YQ, Qin ZA, Guo ZW. Non- linear relationship between basal serum albumin concentration and cardiac arrest in critically ill patients with end- stage renal disease: a cross-sectional study [Internet]. BMJ Open. 2022; 12(2):e051721. DOI: 10.1136/bmjopen-2021-051721
26. Hong YA, Ban TH, Chae Yeong K, Hwang SD, Choi SR, Lee H, et al. Trends in epidemiology characteristics of end-stage renal disease from 2019 Korean Renal Data System (KORDS) [Internet]. Kidney Res Clin Pract. 2021; 40(1):52-61. DOI: 10.23876/j.krcp.20.202
2. Anuario Estadístico de Salud, 2022. Ministerio de Salud Pública. Dirección de Registros médicos y Estadísticas de salud [Internet]. La Habana, 2023 [acceso: 15/11/2023]. Disponible en: http://bvscuba.sld.cu/anuario-estadistico-de-cuba/
3. Koteluk O, Wartecki A, Mazurek S, Kołodziejczak I, Mackiewicz A. How Do Machines Learn? Artificial Intelligence as a New Era in Medicine [Internet]. J Pers Med. 2021; 11(1):1-22. DOI: 10.3390/jpm11010032
4. Sarker IH. Machine learning: algorithms, real-world applications and research directions [Internet]. SN Computer Science. 2021; 2(3):1-21. DOI: 10.1007/s42979-021-00592-x
5. Park S, Park BS, Lee YJ, Kim H, Park JH, Ko J, et al. Artificial intelligence with kidney disease A scoping review with bibliometric analysis, PRISMA-ScR [Internet]. Medicine. 2021; 100(14):e25422. DOI: 10.1097/MD.0000000000025422
6. Khazaei S, Najafi Ghobadi S, Ramezani Doroh V. Construction data mining methods in the prediction of death in hemodialysis patients using support vector machine, neural network, logistic regression and decision tree [Internet]. J Prev Med Hyg. 2021; 62(1):E222-30. DOI: 10.15167/2421-4248/jpmh2021.62.1.1837
7. Gamboa Graus ME. Estadística aplicada a la investigación educativa [Internet]. Revista Dilemas Contemporáneos: Educación, política y valores. 2018 [acceso:15/11/2023]; 5(2):1-32. Disponible en: http://www.dilemascontemporaneoseducacionpoliticayvalores.com/i-ndex.php/dilemas/article/view/427/443
8. de Arriba G, Gutiérrez Ávila G, Torres Guinea M, Moreno Alia I, Herruzo JA, Rincón Ruiz B, et al. La mortalidad de los pacientes en hemodiálisis está asociada con su situación clínica al comienzo del tratamiento [Internet]. Nephrology. 2021; 41(4):461-6. DOI: 10.1016/j.nefro.2020.11.006
9. Ruperto M, Barril G. Nutritional status, body composition, and inflammation profile in older patients with advanced chronic kidney disease stage 4-5: A case control study [Internet]. Nutrients. 2022; 14(17):3650. DOI: 10.3390/nu14173650
10. Matsushita K, Ballew S, Wang A. Epidemiology and risk of cardiovascular disease in populations with chronic kidney disease [Internet]. Nature Reviews Nephrology. 2022; 18(11):696-707. DOI: 10.1038/s41581-022-00616-6
11. Lee S, Kang S, Joo Y. Smoking, smoking cessation, and progression of chronic kidney disease: results form KNOW-CKD study [Internet]. Nicotine & Tobacco Research. 2021; 23(1):92-8. DOI: 10. 1093/ntr/ntaa071
12. Liang X, Ye M, Tao M. The association between dyslipidemia and the incidence of chronic kidney disease in the general Zhejiang population: a retrospective study [Internet]. BMC Nephrol. 2020; 21(252):1-9. DOI: 10. 1186/s12882-020-01907-5
13. Feng-Ching S, Yi-Wen Ch, Mei-Chuan K. U-shaped association between waist-to-hip ratio and all-cause mortality in stage 3-5 chronic kidney disease patients with body mass index paradox [Internet]. J Pers Med. 2021; 11(12):1355. DOI: 10.3390/jpm11121355
14. Jan M, Deseo J. Balancing Nephrology Referrals With Nephrologist Capacity to Decrease Emergency Dialysis Starts [Internet]. Ki Reports. 2020; 6(1):7-10. DOI: 10.1016/j.ekir.2020.11.014
15. Hsu C, Parikh R, Pravoverov L. Implication of trends in timing of dialysis initiation for incidence of end-stage kidney disease [Internet]. JAMA Intern Med. 2020; 180(12):1647-54. DOI: 10.1001/jamainternmed.2020.5009
16. Bossola M, Pepe G, Antocicco M, Severino A, Di Stasio E. Interdialytic weight gain and educational/cognitive, counseling/behavioral and psychological/affective interventions in patients on chronic hemodialysis: a systematic review and meta-analysis [Internet]. Journal of Nephrology. 2022; 35(1):1973-83. DOI: 10.1007/s40620-022-01450-6
17. Romero J, León E. Algoritmos en el manejo de muestras y variables en bioestadística [Internet].16 de Abril. 2018 [acceso:15/11/2023]; 57(269):177-194. Disponible en: https://rev16deabril.sld.cu/index.php/16_04/article/view/770
18. Rossello X, González-Del-Hoyo M. Análisis de supervivencia en investigación cardiovascular (I): lo esencial [Internet]. Rev Esp Cardiol. 2022; 75(1):67-76. DOI: 10.1016/j.recesp.2021.05.017
19. Schlüter M, Nlte G, Murtovi A, Steffen B. Towards rigorous understanding of neural networks via semantics-preserving transformations [Internet]. International Journal on Software Tools for Technology Transfer. 2023; 25(3):301-27. DOI: 10.1007/s10009-023-00700-7
20. Celard P, Lorenzo Iglesias E, Sorribes-Fernández JM, Romero R, Seara Vieira A, Borrajo L. A survey on deep learning applied to medical images: from simple artificial networks to generative models. [Internet]. Neural Computing and Applications. 2023; 35(3):2291-323. DOI: 10.1007/s00521-022-07953-4
21. Bai Q, Su C, Tang W, Li Y. Machine learning to predict end stage kidney disease in chronic kidney disease [Internet]. Scientific Reports. 2022; 12(1):8377. DOI: 10.1038/s41598-022-12316-z
22. Elbasha A, Naga Y, Othman M, Moussa N, Elwakil H. A step towards the application of an artificial intelligence model in the prediction of intradialytic complications [Internet]. Alexandria Journal of Medicine. 2022; 58(1):18-30. DOI: 10.1080/20905068.2021.2024349
23. Singh V, Asari V, Rajasekaran R. A Deep Neural Network for Early Detection and Prediction of Chronic Kidney Disease [Internet]. Diagnostics. 2022; 12(1):1-22. DOI: 10.3390/diagnostics12010116
24. Liu H, Wang R. Associations between the serum magnesium and all-cause or cardiovascular mortality in chronic kidney disease and end-stage renal disease patients. A meta-analysis [Internet]. Medicine. 2021; 100(45):e27486. DOI: 10.1097/MD.0000000000027486
25. Zeng YQ, Qin ZA, Guo ZW. Non- linear relationship between basal serum albumin concentration and cardiac arrest in critically ill patients with end- stage renal disease: a cross-sectional study [Internet]. BMJ Open. 2022; 12(2):e051721. DOI: 10.1136/bmjopen-2021-051721
26. Hong YA, Ban TH, Chae Yeong K, Hwang SD, Choi SR, Lee H, et al. Trends in epidemiology characteristics of end-stage renal disease from 2019 Korean Renal Data System (KORDS) [Internet]. Kidney Res Clin Pract. 2021; 40(1):52-61. DOI: 10.23876/j.krcp.20.202
Published
2024-06-28
How to Cite
1.
Escalona González SO, Caballero Mota Y, Rodríguez Alvarez Y, León Acebo M, González Milán ZC, Ricardo Paez B, et al. An artificial neural network for the prediction of mortality in patients with chronic kidney disease. Rev Cubana Med Milit [Internet]. 2024 Jun. 28 [cited 2025 Apr. 3];53(3):e024038408. Available from: https://revmedmilitar.sld.cu/index.php/mil/article/view/38408
Issue
Section
Research Article
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.
