Predicting chronic kidney disease progression with artificial intelligence.
Artificial intelligence
Machine learning
Prediction
Renal insufficiency
Renal replacement therapy
Journal
BMC nephrology
ISSN: 1471-2369
Titre abrégé: BMC Nephrol
Pays: England
ID NLM: 100967793
Informations de publication
Date de publication:
26 Apr 2024
26 Apr 2024
Historique:
received:
26
01
2023
accepted:
14
03
2024
medline:
27
4
2024
pubmed:
27
4
2024
entrez:
26
4
2024
Statut:
epublish
Résumé
The use of tools that allow estimation of the probability of progression of chronic kidney disease (CKD) to advanced stages has not yet achieved significant practical importance in clinical setting. This study aimed to develop and validate a machine learning-based model for predicting the need for renal replacement therapy (RRT) and disease progression for patients with stage 3-5 CKD. This was a retrospective, closed cohort, observational study. Patients with CKD affiliated with a private insurer with five-year follow-up data were selected. Demographic, clinical, and laboratory variables were included, and the models were developed based on machine learning methods. The outcomes were CKD progression, a significant decrease in the estimated glomerular filtration rate (eGFR), and the need for RRT. Three prediction models were developed-Model 1 (risk at 4.5 years, n = 1446) with a F1 of 0.82, 0.53, and 0.55 for RRT, stage progression, and reduction in the eGFR, respectively,- Model 2 (time- to-event, n = 2143) with a C-index of 0.89, 0.67, and 0.67 for RRT, stage progression, reduction in the eGFR, respectively, and Model 3 (reduced Model 2) with C-index = 0.68, 0.68 and 0.88, for RRT, stage progression, reduction in the eGFR, respectively. The time-to-event model performed well in predicting the three outcomes of CKD progression at five years. This model can be useful for predicting the onset and time of occurrence of the outcomes of interest in the population with established CKD.
Sections du résumé
BACKGROUND
BACKGROUND
The use of tools that allow estimation of the probability of progression of chronic kidney disease (CKD) to advanced stages has not yet achieved significant practical importance in clinical setting. This study aimed to develop and validate a machine learning-based model for predicting the need for renal replacement therapy (RRT) and disease progression for patients with stage 3-5 CKD.
METHODS
METHODS
This was a retrospective, closed cohort, observational study. Patients with CKD affiliated with a private insurer with five-year follow-up data were selected. Demographic, clinical, and laboratory variables were included, and the models were developed based on machine learning methods. The outcomes were CKD progression, a significant decrease in the estimated glomerular filtration rate (eGFR), and the need for RRT.
RESULTS
RESULTS
Three prediction models were developed-Model 1 (risk at 4.5 years, n = 1446) with a F1 of 0.82, 0.53, and 0.55 for RRT, stage progression, and reduction in the eGFR, respectively,- Model 2 (time- to-event, n = 2143) with a C-index of 0.89, 0.67, and 0.67 for RRT, stage progression, reduction in the eGFR, respectively, and Model 3 (reduced Model 2) with C-index = 0.68, 0.68 and 0.88, for RRT, stage progression, reduction in the eGFR, respectively.
CONCLUSION
CONCLUSIONS
The time-to-event model performed well in predicting the three outcomes of CKD progression at five years. This model can be useful for predicting the onset and time of occurrence of the outcomes of interest in the population with established CKD.
Identifiants
pubmed: 38671349
doi: 10.1186/s12882-024-03545-7
pii: 10.1186/s12882-024-03545-7
doi:
Types de publication
Journal Article
Observational Study
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
148Informations de copyright
© 2024. The Author(s).
Références
Schiepatti A, Remuzzi G. Chronic renal diseases as a public health problem: Epidemiology, social, and economic implications. Kidney Int. 2005;68(suppl 98):7–10.
doi: 10.1111/j.1523-1755.2005.09801.x
Levey AS, Atkins R, Coresh J, et al. Chronic kidney disease as a global public health problem: approaches and initiatives– a position statement from kidney disease improving global outcomes. Kidney Int. 2007;72:247–59. https://doi.org/10.1038/sj.ki.5002343 .
doi: 10.1038/sj.ki.5002343
pubmed: 17568785
Lopera-Medina MM. Chronic kidney disease in Colombia: Health needs and response of the General System of Social Security for Health. Rev Gerenc Y Polit Salud. 2016;15:212–33. https://doi.org/10.11144/Javeriana.rgyps15-30.ercc .
doi: 10.11144/Javeriana.rgyps15-30.ercc
Cockwell P, Fisher LA. The global burden of chronic kidney disease. Lancet. 2020;395:662–4. https://doi.org/10.1016/S0140-6736(19)32977-0 .
doi: 10.1016/S0140-6736(19)32977-0
pubmed: 32061314
Colombian Fund for High Cost Diseases -. High Cost Account (CAC); Situation for chronic kidney disease, arterial hypertension, and diabetes mellitus in Colombia 2022; Bogota D.C 2022. Published online 2023.
Saran R, Li Y, Robinson B, Al E. Epidemiology of Kidney Disease in the United States. Am J Kidney Dis. 2016;67:s1–434. https://doi.org/10.1053/j.ajkd.2015.12.015 . US Renal Data System 2015 Annual Data Report.
Mendelssohn DC, Malmberg C, Hamandi B. An integrated review of unplanned dialysis initiation: reframing the terminology to suboptimal initiation. BMC Nephrol. 2009;10:1–8. https://doi.org/10.1186/1471-2369-10-22 .
doi: 10.1186/1471-2369-10-22
Cao J, Singh K. Integrating risk prediction models into chronic kidney disease care. Curr Opin Nephrol Hypertens. 2020;29:339–45. https://doi.org/10.1097/MNH.0000000000000603 .
doi: 10.1097/MNH.0000000000000603
pubmed: 32205582
Tangri N, Stevens LA, Griffith J, et al. A predictive model for progression of chronic kidney disease to kidney failure. JAMA. 2011;305:1553–9. https://doi.org/10.1001/jama.2011.451 .
doi: 10.1001/jama.2011.451
pubmed: 21482743
Halbesma N, Jansen DF, Heymans MW, et al. Development and validation of a general population renal risk score. Clin J Am Soc Nephrol. 2011;6:1731–8. https://doi.org/10.2215/CJN.08590910 .
doi: 10.2215/CJN.08590910
pubmed: 21734089
Schroeder EB, Yang X, Thorp ML, et al. Predicting 5-year risk of RRT in stage 3 or 4 CKD: development and external validation. Clin J Am Soc Nephrol. 2017;12:87–94. https://doi.org/10.2215/CJN.01290216 .
doi: 10.2215/CJN.01290216
pubmed: 28028051
Xiao J, Ding R, Xu X, et al. Comparison and development of machine learning tools in the prediction of chronic kidney disease progression. J Transl Med. 2019;17:1–13. https://doi.org/10.1186/s12967-019-1860-0 .
doi: 10.1186/s12967-019-1860-0
Levey AS, Stevens LA, Schmid CH, et al. A new equation to estimate glomerular filtration rate. Ann Intern Med. 2009;150:604–12. https://doi.org/10.7326/0003-4819-150-9-200905050-00006 .
doi: 10.7326/0003-4819-150-9-200905050-00006
pubmed: 19414839
pmcid: 2763564
Tangri N, Kitsios GD, Inker LA, et al. Risk prediction models for patients with chronic kidney disease. Ann Intern Med. 2014;158:596–603.
doi: 10.7326/0003-4819-158-8-201304160-00004
Echouffo-Tcheugui JB, Kengne AP. Risk models to predict chronic kidney disease and its progression: a systematic review. PLoS Med. 2012;9. https://doi.org/10.1371/journal.pmed.1001344 .
Ramspek CL, de Jong Y, Dekker, et al. Towards the best kidney failure prediction tool: a systematic review and selection aid. Nephrol Dial Transpl. 2020;35:1527–38. https://doi.org/10.1093/ndt/gfz018 .
doi: 10.1093/ndt/gfz018
Tangri N, Grams ME, Levey AS, et al. Multinational assessment of accuracy of equations for predicting risk of kidney failure ameta-analysis. JAMA. 2016;315:164–74. https://doi.org/10.1001/jama.2015.18202 .
doi: 10.1001/jama.2015.18202
pubmed: 26757465
pmcid: 4752167
(KDIGO) 2012 clinical practice Guideline for the evaluation and management of chronic kidney disease (CKD) chap. 5: referral to specialists and models of care. Kidney Int Suppl. 2013;3:112–9. https://doi.org/10.1038/kisup.2012.68 .
KDIGO. 2012 clinical practice Guideline for the evaluation and management of chronic kidney disease (CKD) chap. 2: definition, identification, and prediction of CKD progression. Kidney Int Suppl. 2013;3:63–72. https://doi.org/10.1038/kisup.2012.65 .
Anderson AH, Xie D, Wang X, et al. Novel risk factors for progression of diabetic and nondiabetic CKD: findings from the chronic renal insufficiency cohort (CRIC) study. Am J Kidney Dis. 2021;77:56–e731. https://doi.org/10.1053/j.ajkd.2020.07.011 .
doi: 10.1053/j.ajkd.2020.07.011
pubmed: 32866540
Zacharias HU, Altenbuchinger M, Schultheiss UT et al. A predictive model for progression of CKD to kidney failure based on routine laboratory tests. Am J Kidney Dis. 2021;(Drks 00003971). https://doi.org/10.1053/j.ajkd.2021.05.018 .
Dai D, Alvarez PJ, Woods SD. A predictive model for progression of chronic kidney disease to kidney failure using a large administrative claims database. Clin Outcomes Res. 2021;13:475–486. doi:10.2147/CEOR.S313857.