Dynamic survival prediction of end-stage kidney disease using random survival forests for competing risk analysis

Abstract

Background and hypothesis: A static predictive model relying solely on baseline clinicopathological data cannot capture the heterogeneity in predictor trajectories observed in the progression of chronic kidney disease (CKD). To address this, we developed and validated a dynamic survival prediction model using longitudinal clinicopathological data to predict end-stage kidney disease (ESKD), with death as a competing risk.

Methods: We trained a sequence of random survival forests using a landmarking approach and optimized the model with a pre-specified prediction horizon of 5 years. The predicted cumulative incidence function (CIF) values were used to generate a personalized dynamic prediction plot.

Results: The model was developed using baseline demographics and 13 longitudinal clinicopathological variables from 4,950 patients. Variable importance analysis for ESKD and death informed the creation of a sequence of reduced models that utilized six key variables: age, serum albumin, bicarbonate, chloride, eGFR, and hemoglobin. The models demonstrated robust predictive performance, with a median concordance index of 84.84% for ESKD and 84.1% for death. The median integrated Brier scores were 0.03 for ESKD and 0.038 for death across all landmark times. External validation with 8,729 patients confirmed these results.

Conclusion: We successfully developed and validated a dynamic survival prediction model using common longitudinal clinicopathological data. This model predicts ESKD with death as a competing risk and aims to assist clinicians in dialysis planning for patients with CKD.

Keywords: competing risk; dynamic prediction model; end-stage kidney disease; landmarking; random survival forests.

Figure 1

Comparison of landmarking approach. (A) The Concordance index. (a) ESKD: The Kruskal–Wallis test comparing the ESKD concordance index of the models for each landmark time was non-significant. Each boxplot was created using the model’s performance on the five-fold cross-validation test dataset. (b) Death: The Kruskal–Wallis test comparing the death concordance index of the models for each landmark time was non-significant. Each boxplot was created using the model’s performance on the test dataset of the five-fold cross-validation. (B) Integrated Brier score. (a) ESKD: The Kruskal-Wallis test comparing the ESKD integrated Brier score of the models for each landmark time was non-significant. Each boxplot was created using the model’s performance on the test dataset of the five-fold cross-validation. (b) Death: The Kruskal–Wallis test comparing the death-integrated Brier score of the models for each landmark time was non-significant. Each boxplot was created using the model’s performance on the test dataset of the five-fold cross-validation.

Figure 2

Variable of importance. (A) ESKD and (B) Death. A bar plot value indicates median with an interquartile range.

Figure 3

Dynamic prediction plot. (A) Case 1: An 80-year-old patient died at 7.2 years. (B) Case 2: A 62-year-old patient with ESKD event at 5.08 years. (C) Case 3: A 67-year-old patient did not experience any event and was censored at 6.69 years. (A–C) On the left of the dynamic prediction plot, we plot all the observed longitudinal clinicpathological data (serum measurement of albumin, bicarbonate, chloride, eGFR, and hemoglobin) for the first 3 years. On the right, we drew the predicted CIF curve for ESKD and Death using the top 5 trained models on patients from the test dataset.