Related Experiment Video
Updated: Jul 9, 2025
TBase - an Integrated Electronic Health Record and Research Database for Kidney Transplant Recipients
Published on: April 13, 2021
Risk Prediction Model for Chronic Kidney Disease in Thailand Using Artificial Intelligence and SHAP
Ming-Che Tsai1,2, Bannakij Lojanapiwat3, Chi-Chang Chang4,5
1Department of Emergency Medicine, School of Medicine, Chung Shan Medical University, Taichung 40201, Taiwan.
Insights
A new machine learning model accurately predicts chronic kidney disease (CKD) risk in Thailand, identifying key factors like serum albumin and blood urea nitrogen to aid personalized treatment strategies.
Area of Science:
- Nephrology
- Data Science
- Public Health
Background:
- Chronic kidney disease (CKD) is a significant health burden in Thailand, affecting 17.5% of the population.
- Advanced stages of CKD and the need for hemodialysis are substantial, highlighting the need for effective management and early detection.
Purpose of the Study:
- To develop and validate a robust risk prediction model for chronic kidney disease (CKD) specific to the Thai population.
- To identify critical independent variables contributing to CKD risk.
Main Methods:
- Utilized data from 17,100 patients to screen 14 independent risk factors.
- Employed machine learning algorithms including IBK, Random Tree, Decision Table, J48, and Random Forest, with synthetic minority oversampling technique (SMOTE) to address data imbalance.
- Applied SHapley Additive exPlanations (SHAP) for in-depth analysis of critical risk factors.
Main Results:
- The Random Forest model achieved a high accuracy rate of 92.1%.
- Key predictive factors identified include serum albumin, blood urea nitrogen, age, direct bilirubin, and glucose.
- SHAP analysis provided insights into the significance of individual and dual-attribute risk factors.
Conclusions:
- The developed machine learning model offers a reliable tool for CKD risk prediction in Thailand.
- The identified risk factors can inform the development of personalized treatment and prevention strategies for CKD.
- This approach enhances the understanding of multifactorial CKD etiology and management.
Abstract:
Chronic kidney disease (CKD) is a multifactorial, complex condition that requires proper management to slow its progression. In Thailand, 11.6 million people (17.5%) have CKD, with 5.7 million (8.6%) in the advanced stages and >100,000 requiring hemodialysis (2020 report). This study aimed to develop a risk prediction model for CKD in Thailand. Data from 17,100 patients were collected to screen for 14 independent variables selected as risk factors, using the IBK, Random Tree, Decision Table, J48, and Random Forest models to train the predictive models. In addition, we address the unbalanced category issue using the synthetic minority oversampling technique (SMOTE). The indicators of performance include classification accuracy, sensitivity, specificity, and precision. This study achieved an accuracy rate of 92.1% with the top-performing Random Forest model. Moreover, our empirical findings substantiate previous research through highlighting the significance of serum albumin, blood urea nitrogen, age, direct bilirubin, and glucose. Furthermore, this study used the SHapley Additive exPlanations approach to analyze the attributes of the top six critical factors and then extended the comparison to include dual-attribute factors. Finally, our proposed machine learning technique can be used to evaluate the effectiveness of these risk factors and assist in the development of future personalized treatment.
