Early prediction of end-stage kidney disease using electronic health record data: a machine learning approach with a 2-year horizon

Abstract

Objectives: In the United States, end-stage kidney disease (ESKD) is responsible for high mortality and significant healthcare costs, with the number of cases sharply increasing in the past 2 decades. In this study, we aimed to reduce these impacts by developing an ESKD model for predicting its occurrence in a 2-year period. Materials and Methods: We developed a machine learning (ML) pipeline to test different models for the prediction of ESKD. The electronic health record was used to capture several kidney disease-related variables. Various imputation methods, feature selection, and sampling approaches were tested. We compared the performance of multiple ML models using area under the ROC curve (AUCROC), area under the Precision-Recall curve (PR-AUC), and Brier scores for discrimination, precision, and calibration, respectively. Explainability methods were applied to the final model. Results: Our best model was a gradient-boosting machine with feature selection and imputation methods as additional components. The model exhibited an AUCROC of 0.97, a PR-AUC of 0.33, and a Brier score of 0.002 on a holdout test set. A chart review analysis by expert physicians indicated clinical utility. Discussion and Conclusion: An ESKD prediction model can identify individuals at risk for ESKD and has been successfully deployed within our health system. Lay Summary End-stage kidney disease (ESKD) poses a substantial burden for mortality rate and healthcare costs in the United States. We developed and evaluated a machine learning (ML) model for predicting ESKD in 2 years using electronic health record (EHR) data. Various models were tested by leveraging EHR data and employing an ML pipeline. The developed model outperforms existing kidney failure models. Through a chart review, expert nephrologists affirmed the clinical utility of the model in predicting the outcome of complex cases. This model has been successfully integrated into our academic institution as part of a dashboard with visualizations and explainability for the model’s predictions. In conclusion, the developed ESKD prediction model demonstrates the ability to identify individuals at risk for ESKD. Any future reduction in mortality and healthcare costs would showcase the effectiveness of our model.