Related Experiment Video
Updated: Sep 4, 2025
TBase - an Integrated Electronic Health Record and Research Database for Kidney Transplant Recipients
Published on: April 13, 2021
Establishment and Evaluation of Artificial Intelligence-Based Prediction Models for Chronic Kidney Disease under the
Xiaoqian Yan1, Ximin Li1, Ying Lu1
1Department of Nephropathy, Tongde Hospital of Zhejiang Province, Hangzhou, Zhejiang 310012, China.
Insights
This study developed advanced prediction models for chronic kidney disease (CKD) risk. The novel MD-BERT-LGBM model significantly improved prediction accuracy, aiding CKD management and prevention.
Area of Science:
- Medical Informatics
- Nephrology
- Machine Learning
Background:
- Chronic kidney disease (CKD) poses a significant global health challenge.
- Effective risk evaluation is crucial for CKD management and prevention.
Purpose of the Study:
- To develop and compare machine learning models for predicting CKD risk.
- To evaluate the impact of incorporating unstructured data using a novel transformer-based model.
Main Methods:
- Retrospective analysis of 1263 CKD and 1948 non-CKD patients.
- Comparison of XGBoost, random forest, Naive Bayes, SVM, and logistic regression models.
- Utilized a novel MD-BERT-LGBM model to process unstructured data and enhance prediction.
Main Results:
- XGBoost and random forest models showed high prediction accuracy.
- Neutrophil ratio and white blood cell count were significantly associated with CKD.
- The MD-BERT-LGBM model improved the area under the curve (AUC) for all prediction models.
Conclusions:
- The MD-BERT-LGBM model enhances prediction accuracy, sensitivity, and specificity for CKD.
- Clinical features like age, gender, and specific lab parameters are associated with CKD incidence.
- This approach aids in guiding CKD management and prevention strategies.
Objective:
To establish a prediction model for the risk evaluation of chronic kidney disease (CKD) to guide the management and prevention of CKD.
Methods:
A total of 1263 patients with CKD and 1948 patients without CKD admitted to the Tongde Hospital of the Zhejiang Province from January 1, 2008, to December 31, 2018, were retrospectively analyzed. Spearman's correlation was used to analyze the relationship between CKD and laboratory parameters. XGBoost, random forest, Naive Bayes, support vector machine, and multivariate logistic regression algorithms were employed to establish prediction models for the risk evaluation of CKD. The accuracy, precision, recall, F1 score, and area under the receiver operating curve (AUC) of each model were compared. The new bidirectional encoder representations from transformers with light gradient boosting machine (MD-BERT-LGBM) model was used to process the unstructured data and transform it into researchable unstructured vectors, and the AUC was compared before and after processing.
Results:
Differences in laboratory parameters between CKD and non-CKD patients were observed. The neutrophil ratio and white blood cell count were significantly associated with the occurrence of CKD. The XGBoost model demonstrated the best prediction effect (accuracy = 0.9088, precision = 0.9175, recall = 0.8244, F1 score = 0.8868, AUC = 0.8244), followed by the random forest model (accuracy = 0.9020, precision = 0.9318, recall = 0.7905, F1 score = 0.581, AUC = 0.9519). Comparatively, the predictions of the Naive Bayes and support vector machine models were inferior to those of the logistic regression model. The AUC of all models was improved to some extent after processing using the new MD-BERT-LGBM model.
Conclusion:
The new MD-BERT-LGBM model with the inclusion of unstructured data has contributed to the higher accuracy, sensitivity, and specificity of the prediction models. Clinical features such as age, gender, urinary white blood cells, urinary red blood cells, thrombin time, serum creatinine, and total cholesterol were associated with CKD incidence.
Related Concept Videos
01:25Chronic Kidney Disease I: Introduction
01:28Chronic Kidney Disease III: Interprofessional Care
01:30Acute Kidney Injury IV: Diagnostic Studies and Prevention
01:18Chronic Kidney Disease IV: Nursing Management
01:24Chronic Kidney Disease II: Clinical Manifestations
01:22Acute Kidney Injury I: Introduction