Accurate prediction of graft survival after kidney transplant is limited by the complexity and heterogeneity of risk factors influencing allograft survival. In this study, we applied machine learning methods, in combination with survival statistics, to build new prediction models of graft survival that included immunological factors, as well as known recipient and donor variables. Graft survival was estimated from a retrospective analysis of the data from a multicenter cohort of 3,117 kidney transplant recipients. We evaluated the predictive power of ensemble learning algorithms (survival decision tree, bagging, random forest, and ridge and lasso) and compared outcomes to those of conventional models (decision tree and Cox regression). Using a conventional decision tree model, the 3-month serum creatinine level post-transplant (cut-off, 1.65 mg/dl) predicted a graft failure rate of 77.8% (index of concordance, 0.71). Using a survival decision tree model increased the index of concordance to 0.80, with the episode of acute rejection during the first year post-transplant being associated with a 4.27-fold increase in the risk of graft failure. Our study revealed that early acute rejection in the first year is associated with a substantially increased risk of graft failure. Machine learning methods may provide versatile and feasible tools for forecasting graft survival.
Lim et al e405 FIGURE 1. Flow diagram of the study participants. SGLTi, sodium-glucose cotransporter 2 inhibitors.
BackgroundAbnormal serum potassium concentration has been suggested as a risk factor for mortality in patients undergoing dialysis patients. We investigated the impact of serum potassium levels on survival according to dialysis modality.MethodsA nationwide, prospective, observational cohort study for end stage renal disease patients has been ongoing in Korea since August 2008. Our analysis included patients whose records contained data regarding serum potassium levels. The relationship between serum potassium and mortality was analyzed using competing risk regression.ResultsA total of 3,230 patients undergoing hemodialysis (HD, 64.3%) or peritoneal dialysis (PD, 35.7%) were included. The serum potassium level was significantly lower (P < 0.001) in PD (median, 4.5 mmol/L; interquartile range, 4.0–4.9 mmol/L) than in HD patients (median, 4.9 mmol/L; interquartile range, 4.5–5.4 mmol/L). During 4.4 ± 1.7 years of follow-up, 751 patients (23.3%) died, mainly from cardiovascular events (n = 179) and infection (n = 120). In overall, lower serum potassium level less than 4.5 mmol/L was an independent risk factor for mortality after adjusting for age, comorbidities, and nutritional status (sub-distribution hazard ratio, 1.30; 95% confidence interval 1.10–1.53; P = 0.002). HD patients showed a U-shaped survival pattern, suggesting that both lower and higher potassium levels were deleterious, although insignificant. However, in PD patients, only lower serum potassium level (<4.5 mmol/L) was an independent predictor of mortality (sub-distribution hazard ratio, 1.35; 95% confidence interval 1.00–1.80; P = 0.048).ConclusionLower serum potassium levels (<4.5 mmol/L) occur more commonly in PD than in HD patients. It represents an independent predictor of survival in overall dialysis, especially in PD patients. Therefore, management of dialysis patients should focus especially on reducing the risk of hypokalemia, not only that of hyperkalemia.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.