Related Experiment Video
Updated: Jun 8, 2025
5/6 Nephrectomy Using Sharp Bipolectomy Via Midline Laparotomy in Rats
Published on: April 4, 2025
Applying stacking ensemble method to predict chronic kidney disease progression in Chinese population based on
Jialin Du1, Jie Gao2,3,4,5, Jie Guan1
1Department of Clinical Laboratory, Peking University First Hospital, Beijing, China.
Insights
A new machine learning model accurately predicts chronic kidney disease (CKD) progression to kidney failure in Chinese patients using routine lab tests. This tool aids clinical decisions and improves patient outcomes for CKD management.
Area of Science:
- Nephrology
- Artificial Intelligence in Medicine
- Biostatistics
Background:
- Chronic kidney disease (CKD) poses a significant public health challenge globally.
- Accurate prediction of kidney failure progression is crucial for effective clinical management and patient care.
- Machine learning offers a promising approach to enhance predictive capabilities in CKD.
Purpose of the Study:
- To develop and externally validate a machine-learned model for predicting CKD progression.
- To utilize common laboratory variables, demographic data, and electronic health records for prediction.
- To identify high-risk patients for timely intervention and improved outcomes.
Main Methods:
- A predictive model was developed using longitudinal clinical data from 987 Chinese CKD patients.
- Fifty-three laboratory features were evaluated, with the final model incorporating six key variables.
- Model performance was assessed using metrics like AUC, accuracy, sensitivity, and specificity on internal and external datasets.
Main Results:
- The optimal model, based on stacked classifiers, included 24-h urine protein, potassium, glucose, urea, prealbumin, and total protein.
- The model demonstrated strong predictive power with AUC values of 0.896 (validation) and 0.771 (external dataset).
- The model accurately predicted renal function decline over various follow-up periods.
Conclusions:
- A prediction model using routinely collected laboratory features can effectively identify Chinese CKD patients at high risk of kidney failure.
- The developed model shows potential for seamless integration into clinical practice for patient management.
- An online version of the model can facilitate rapid clinical decision-making and treatment planning.
Background And Objective:
Chronic kidney disease (CKD) is a major public health issue, and accurate prediction of the progression of kidney failure is critical for clinical decision-making and helps improve patient outcomes. As such, we aimed to develop and externally validate a machine-learned model to predict the progression of CKD using common laboratory variables, demographic characteristics, and an electronic health records database.
Methods:
We developed a predictive model using longitudinal clinical data from a single center for Chinese CKD patients. The cohort included 987 patients who were followed up for more than 24 months. Fifty-three laboratory features were considered for inclusion in the model. The primary outcome in our study was an estimated glomerular filtration rate ≤15 mL/min/1.73 m2 or kidney failure. Machine learning algorithms were applied to the modeling dataset (n = 296), and an external dataset (n = 71) was used for model validation. We assessed model discrimination via area under the curve (AUC) values, accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F1 score.
Results:
Over a median follow-up period of 3.75 years, 148 patients experienced kidney failure. The optimal model was based on stacking different classifier algorithms with six laboratory features, including 24-h urine protein, potassium, glucose, urea, prealbumin and total protein. The model had considerable predictive power, with AUC values of 0.896 and 0.771 in the validation and external datasets, respectively. This model also accurately predicted the progression of renal function in patients over different follow-up periods after their initial assessment.
Conclusions:
A prediction model that leverages routinely collected laboratory features in the Chinese population can accurately identify patients with CKD at high risk of progressing to kidney failure. An online version of the model can be easily and quickly applied in clinical management and treatment.
