Detection of the chronic kidney disease using XGBoost classifier and explaining the influence of the attributes on the model using SHAP

Abstract

Chronic kidney disease (CKD) is a condition distinguished by structural and functional changes to the kidney over time. Studies show that 10% of adults worldwide are affected by some kind of CKD, resulting in 1.2 million deaths. Recently, CKD has emerged as a leading cause of mortality worldwide, making it necessary to develop a Computer-Aided Diagnostic (CAD) system to diagnose CKD automatically. Machine Learning (ML) based CAD system can be used by a clinician to automatically diagnoses mass people. Since ML models are considered a black box, it is also necessary to expose influential causes behind a model's prediction of a particular output. So that, a doctor can make a more rational decision based on the model's output and analysis of the features influence on the model. In this paper, we have used the XGBoost as the ML classifier to predict whether a patient has CKD or not. Using the XGBoost classifier, we have obtained an accuracy, precision, recall, and F1 score of $$99.16{\%}, 100{\%}, 98.68{\%},$$ 99.16 % , 100 % , 98.68 % , and $$99.33{\%},$$ 99.33 % , respectively using all $$24$$ 24 features. Furthermore, we have used Biogeography Based Optimization (BBO) algorithm to find an effective subset of the features. The BBO algorithm selected almost half of the initial features. We have obtained an accuracy, precision, recall, and F1 score of $$98.33{\%}, 100{\%}, 97.36{\%},$$ 98.33 % , 100 % , 97.36 % , and $$98.67{\%},$$ 98.67 % , respectively using only 13 features selected by the BBO algorithm. Finally, we have explained the impact of the feature on the ML models using the SHapley Additive exPlanations (SHAP) analysis. Using SHAP analysis and BBO algorithm, we have found that hemoglobin and albumin mostly contribute to the detection of CKD.

Empowering Glioma Prognosis With Transparent Machine Learning and Interpretative Insights Using Explainable AI

“…The significance of every feature to machine learning model's prediction are considered by SHAP model in order to interpret model's output. [61]. By applying principles from game theory, it calculates an insight of each attribute to the model's output and offers comprehensible and straightforward explanations.…”

Multiple Explainable Approaches to Predict the Risk of Stroke Using Artificial Intelligence

“…The final stacking models of Mutual information, Pearson's correlation, Particle swarm optimization and Harris Hawks algorithm were employed for interpretation [46]. SHAP uses each feature's significance to the model's prediction to explain the machine learning model's output [47]. It computes an insight of each characteristic to the output of the model using game theory concepts and provides interpretable and clear explanations.…”

Classification of the Attempted Arm and Hand Movements of Patients with Spinal Cord Injury Using Deep Learning Approach

“…By analyzing the feature importance scores provided by XGBoost, data scientists can identify the most influential features in a dataset, gain insights into the relationships between features and the target variable, and potentially improve the model's performance by selecting or engineering more relevant features [Wang et al, 2020;Friedmann, 2001;Raihan et al, 2023;Machado et al, 2019]. The scores for each electrode obtained from the XGBoost analysis are represented in Fig.…”