Shi X, Qu T, Van Pottelbergh G, van den Akker M, De Moor B. A Resampling Method to Improve the Prognostic Model of End-Stage Kidney Disease: A Better Strategy for Imbalanced Data.
Front Med (Lausanne) 2022;
9:730748. [PMID:
35321465 PMCID:
PMC8935060 DOI:
10.3389/fmed.2022.730748]
[Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/25/2021] [Accepted: 01/17/2022] [Indexed: 12/12/2022] Open
Abstract
Background
Prognostic models can help to identify patients at risk for end-stage kidney disease (ESKD) at an earlier stage to provide preventive medical interventions. Previous studies mostly applied the Cox proportional hazards model. The aim of this study is to present a resampling method, which can deal with imbalanced data structure for the prognostic model and help to improve predictive performance.
Methods
The electronic health records of patients with chronic kidney disease (CKD) older than 50 years during 2005–2015 collected from primary care in Belgium were used (n = 11,645). Both the Cox proportional hazards model and the logistic regression analysis were applied as reference model. Then, the resampling method, the Synthetic Minority Over-Sampling Technique-Edited Nearest Neighbor (SMOTE-ENN), was applied as a preprocessing procedure followed by the logistic regression analysis. The performance was evaluated by accuracy, the area under the curve (AUC), confusion matrix, and F3 score.
Results
The C statistics for the Cox proportional hazards model was 0.807, while the AUC for the logistic regression analysis was 0.700, both on a comparable level to previous studies. With the model trained on the resampled set, 86.3% of patients with ESKD were correctly identified, although it was at the cost of the high misclassification rate of negative cases. The F3 score was 0.245, much higher than 0.043 for the logistic regression analysis and 0.022 for the Cox proportional hazards model.
Conclusion
This study pointed out the imbalanced data structure and its effects on prediction accuracy, which were not thoroughly discussed in previous studies. We were able to identify patients with high risk for ESKD better from a clinical perspective by using the resampling method. But, it has the limitation of the high misclassification of negative cases. The technique can be widely used in other clinical topics when imbalanced data structure should be considered.
Collapse