Related Experiment Video
Updated: Jul 18, 2026
Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
Published on: June 18, 2020
A Klotho-Based Machine Learning Model for Prediction of both Kidney and Cardiovascular Outcomes in Chronic Kidney
Yating Wang1, Yu Shi1, Tangli Xiao1
1Department of Nephrology, The Key Laboratory for the Prevention and Treatment of Chronic Kidney Disease of Chongqing, Kidney Center of PLA, Xinqiao Hospital, Army Medical University (Third Military Medical University), Chongqing, PR China.
Insights
Machine learning models using serum Klotho effectively predict end-stage kidney disease (ESKD) and cardiovascular disease (CVD) in chronic kidney disease (CKD) patients. These validated models offer significant clinical utility for risk assessment.
Area of Science:
- Nephrology
- Cardiology
- Biomarker Research
- Machine Learning in Healthcare
Background:
- Chronic kidney disease (CKD) is a progressive condition associated with high risks of end-stage kidney disease (ESKD) and cardiovascular disease (CVD).
- Serum Klotho is a potential biomarker for kidney function and cardiovascular health.
- Accurate prediction of ESKD and CVD is crucial for timely intervention in CKD patients.
Purpose of the Study:
- To develop and validate machine learning (ML) models for predicting ESKD and CVD risk in CKD patients.
- To assess the predictive performance of models incorporating serum Klotho levels.
- To identify key risk factors for ESKD and CVD in this cohort.
Main Methods:
- Utilized a cohort of 400 non-dialysis CKD patients.
- Developed five ML models using 47 clinical features, including serum Klotho, to predict ESKD and CVD at 3, 5, and 8 years.
- Internal validation was performed on 30% of the dataset; model performance was evaluated using C-index and Area Under the Curve (AUC).
Main Results:
- The least absolute shrinkage and selection operator (LASSO) regression model achieved the highest accuracy (C-index=0.71) for ESKD prediction, with serum Klotho being a key feature (AUC=0.930).
- The random survival forest model demonstrated the highest accuracy (C-index=0.66) for CVD prediction, with serum Klotho as a significant predictor (AUC=0.782).
- Key predictors for ESKD included eGFR, urinary microalbumin, serum albumin, phosphate, and parathyroid hormone, alongside serum Klotho.
Conclusions:
- Successfully developed and validated ML models incorporating serum Klotho for predicting ESKD and CVD in CKD patients.
- The models demonstrated good predictive performance, highlighting their potential clinical utility.
- Serum Klotho is a valuable biomarker for risk stratification in patients with chronic kidney disease.
Introduction:
This study aimed to develop and validate machine learning (ML) models based on serum Klotho for predicting end-stage kidney disease (ESKD) and cardiovascular disease (CVD) in patients with chronic kidney disease (CKD).
Methods:
Five different ML models were trained to predict the risk of ESKD and CVD at three different time points (3, 5, and 8 years) using a cohort of 400 non-dialysis CKD patients. The dataset was divided into a training set (70%) and an internal validation set (30%). These models were informed by data comprising 47 clinical features, including serum Klotho. The best-performing model was selected and used to identify risk factors for each outcome. Model performance was assessed using various metrics.
Results:
The findings showed that the least absolute shrinkage and selection operator regression model had the highest accuracy (C-index = 0.71) in predicting ESKD. The features mainly included in this model were estimated glomerular filtration rate, 24-h urinary microalbumin, serum albumin, phosphate, parathyroid hormone, and serum Klotho, which achieved the highest area under the curve (AUC) of 0.930 (95% CI: 0.897-0.962). In addition, for the CVD risk prediction, the random survival forest model with the highest accuracy (C-index = 0.66) was selected and achieved the highest AUC of 0.782 (95% CI: 0.633-0.930). The features mainly included in this model were age, history of primary hypertension, calcium, tumor necrosis factor-alpha, and serum Klotho.
Conclusion:
We successfully developed and validated Klotho-based ML risk prediction models for CVD and ESKD in CKD patients with good performance, indicating their high clinical utility.
Related Concept Videos
01:28Drug Dosing in Renal Diseases: Estimation of Glomerular Filtration Rate Based on Serum Creatinine Concentration
01:25Chronic Kidney Disease I: Introduction
01:24Chronic Kidney Disease II: Clinical Manifestations
01:28Chronic Kidney Disease III: Interprofessional Care
01:18Chronic Kidney Disease IV: Nursing Management