Predicting chronic kidney disease progression using small pathology datasets and explainable machine learning models

Abstract

Background

Chronic kidney disease (CKD) poses a major global public health burden, with over 700 million affected. Early identification of those in whom the disease is likely to progress enables timely therapeutic interventions to delay advancement to kidney failure.

Methods

This study developed explainable machine learning models leveraging pathology data to accurately predict CKD trajectory, targeting improved prognostic capability even in early stages using limited datasets. Key variables used in this study include age, gender, most recent estimated glomerular filtration rate (eGFR), mean eGFR, and eGFR slope over time prior to the incidence of kidney failure. Supervised classification modelling techniques included decision tree and random forest algorithms selected for interpretability. Internal validation on an Australian tertiary centre cohort (n = 706; 353 with kidney failure and 353 without) achieved exceptional predictive accuracy. To address the inherent class imbalance, centroid-cluster-based under-sampling was applied to the Australian dataset. For external validation, the model was applied to a dataset (n = 597 adults) sourced from a Japanese CKD registry. Transfer learning was subsequently employed by fine-tuning machine learning models on 15 % of the external dataset (n = 89) before evaluating the remaining 508 patients.

Results

Internal validation achieved exceptional predictive accuracy, with the area under the receiver operating characteristic curve (ROC-AUC) reaching 0.94 and 0.98 on the binary task of predicting kidney failure for decision tree and random forest, respectively. External validation demonstrated performant results with an ROC-AUC of 0.88 for the decision tree and 0.93 for the random forest model. Decision tree model analysis revealed the most recent eGFR and eGFR slope as the most informative variables for prediction in the Japanese cohort.

Conclusion

The research highlights the utility of deploying explainable machine learning techniques to forecast CKD trajectory even in the early stages utilising limited real-world datasets.