Predicting chronic kidney disease progression with artificial intelligence

• Published in: BMC nephrology Vol. 25; no. 1; p. 148
• Main Authors: Isaza-Ruget, Mario A, Yomayusa, Nancy, González, Camilo A, H, Catherine Alvarado, de Oro V, Fabio A, Cely, Andrés, Murcia, Jossie, Gonzalez-Velez, Abel, Robayo, Adriana, Colmenares-Mejía, Claudia C, Castillo, Andrea, Conde, María I
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 26.04.2024; BioMed Central; BMC
• Subjects: Adult; Aged; Algorithms; Artificial Intelligence; Cardiovascular disease; Care and treatment; Cholesterol; Chronic kidney failure; Cohort Studies; Creatinine; Development and progression; Diabetes; Disease Progression; Epidermal growth factor receptors; Female; Glomerular Filtration Rate; Health aspects; Hemodialysis; Hemoglobin; High density lipoprotein; Humans; Hypertension; Kidney diseases; Kidney transplants; Learning algorithms; Low density lipoprotein; Machine Learning; Male; Methods; Middle Aged; Neural networks; Prediction; Prediction models; Regression analysis; Renal insufficiency; Renal Insufficiency, Chronic - physiopathology; Renal Insufficiency, Chronic - therapy; Renal Replacement Therapy; Retrospective Studies; Tool use; Urine; Colombia; Renal insufficiency; Renal replacement therapy; Artificial intelligence; Machine learning; Prediction
• ISSN: 1471-2369; 1471-2369
• DOI: 10.1186/s12882-024-03545-7

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.