Development and evaluation of an explainable prediction model for chronic kidney disease patients based on ensemble trees

Abstract

Chronic Kidney Disease (CKD), where delayed recognition implies premature mortality, is currently experiencing a globally increasing incidence and high cost to health systems. Data mining allows discovering subtle patterns in CKD indicators to contribute to an early diagnosis. This work presents the development and evaluation of an explainable prediction model that would support clinicians in the early diagnosis of CKD patients. The model development is based on a data management pipeline that detects the best combination of ensemble trees algorithms and features selected concerning classification performance. Furthermore, the main contribution of the paper involves an explainability-driven approach that allows selecting the best predictive model maintaining a balance between accuracy and explainability. Therefore, the most balanced explainable predictive model implements an extreme gradient boosting classifier over 3 features (packed cell value, specific gravity, and hypertension), achieving an accuracy of 99.2% and 97.5% with cross-validation technique and with new unseen data respectively. In addition, an analysis of the model´s explainability shows that the packed cell value is the most relevant feature that influences the prediction results of the model, followed by specific gravity and hypertension. This small number of feature selected results in a reduced cost of the early diagnosis of CKD implying a promising solution for developing countries.