Related Experiment Video
Updated: Jun 7, 2025
Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
Published on: June 18, 2020
Development of a machine learning tool to predict the risk of incident chronic kidney disease using health
Yuki Yoshizaki1, Kiminori Kato2, Kazuya Fujihara3
1Department of Medical Informatics and Statistics, Niigata University Graduate School of Medical and Dental Sciences, Niigata, Japan.
Insights
Machine learning models effectively predict chronic kidney disease (CKD) risk within one year using health data, with estimated glomerular filtration rate (eGFR) being a key factor. Predicting proteinuria onset remains challenging with current data.
Area of Science:
- Nephrology
- Medical Informatics
- Machine Learning
Background:
- Chronic kidney disease (CKD) is a significant global health issue requiring early detection.
- Early identification of CKD is crucial for effective management and preventing severe outcomes.
- This study addresses the need for predictive tools for CKD development.
Purpose of the Study:
- To develop and evaluate machine learning models for predicting CKD risk.
- To forecast the likelihood of developing CKD within 1 and 5-year timeframes.
- To assess the impact of various health metrics on CKD prediction.
Main Methods:
- Utilized health examination data from 30,273 participants (2017-2022).
- Developed prediction models using logistic regression, conditional logistic regression, neural networks, and recurrent neural networks.
- Examined outcomes including incident estimated glomerular filtration rate (eGFR) <60 mL/min/1.73 m² and proteinuria development.
Main Results:
- Models demonstrated high predictive values, sensitivities, and specificities (>0.8) for 1-year CKD onset (eGFR <60).
- Area Under the Receiver Operating Characteristic Curve (AUROC) exceeded 0.9 for 1-year eGFR prediction.
- 5-year prediction AUROCs ranged from 0.889 to 0.890; prediction accuracy decreased significantly without eGFR as a variable.
Conclusions:
- Machine learning models show promise in predicting CKD risk, particularly when eGFR is included.
- Predicting proteinuria onset solely from health examination data presents challenges.
- Further research is needed to improve prediction models for eGFR decline and increased urine protein.
Background:
Chronic kidney disease (CKD) is characterized by a decreased glomerular filtration rate or renal injury (especially proteinuria) for at least 3 months. The early detection and treatment of CKD, a major global public health concern, before the onset of symptoms is important. This study aimed to develop machine learning models to predict the risk of developing CKD within 1 and 5 years using health examination data.
Methods:
Data were collected from patients who underwent annual health examinations between 2017 and 2022. Among the 30,273 participants included in the study, 1,372 had CKD. Demographic characteristics, body mass index, blood pressure, blood and urine test results, and questionnaire responses were used to predict the risk of CKD development at 1 and 5 years. This study examined three outcomes: incident estimated glomerular filtration rate (eGFR) <60 mL/min/1.73 m2, the development of proteinuria, and incident eGFR <60 mL/min/1.73 m2 or the development of proteinuria. Logistic regression (LR), conditional logistic regression, neural network, and recurrent neural network were used to develop the prediction models.
Results:
All models had predictive values, sensitivities, and specificities >0.8 for predicting the onset of CKD in 1 year when the outcome was eGFR <60 mL/min/1.73 m2. The area under the receiver operating characteristic curve (AUROC) was >0.9. With LR and a neural network, the specificities were 0.749 and 0.739 and AUROCs were 0.889 and 0.890, respectively, for predicting onset within 5 years. The AUROCs of most models were approximately 0.65 when the outcome was eGFR <60 mL/min/1.73 m2 or proteinuria. The predictive performance of all models exhibited a significant decrease when eGFR was not included as an explanatory variable (AUROCs: 0.498-0.732).
Conclusion:
Machine learning models can predict the risk of CKD, and eGFR plays a crucial role in predicting the onset of CKD. However, it is difficult to predict the onset of proteinuria based solely on health examination data. Further studies must be conducted to predict the decline in eGFR and increase in urine protein levels.
Related Concept Videos
01:12Internal Anatomy of the Kidney
Anatomical Position and Dimensions
The kidneys are retroperitoneal organs positioned against the posterior abdominal wall on either side of the spine, roughly between the twelfth thoracic and third lumbar vertebrae. Each kidney is typically 10-12 cm long, 5-6 cm wide, and 3-4 cm thick, weighing about 150 grams.
Renal Cortex
The outermost region of the kidney is the...
01:17Factors Affecting Renal Clearance: Renal Impairment
One condition associated with renal failure is uremia. Uremia is characterized by impaired glomerular filtration and fluid accumulation in the body. This condition hinders the renal clearance of drugs, resulting in drug accumulation and potential...