Can a Predictive Model Determine Kidney Failure in Stage 3 or 4 Kidney Disease?

  • 1st Revision: Isobel Lester
  • 2nd Revision: Tamsin Rose
  • 3rd Revision: Emma Soopramanien

Based on a research article titled “A Predictive Model for Progression of Chronic Kidney Disease to Kidney Failure Using a Large Administrative Claims Database”

Originally written by Dai et al. 2021

By Murielle Nsiela

Chronic kidney disease is the progressive deterioration of kidney function, whereby the kidneys are unable to filter blood, resulting in a dangerous accumulation of waste products. It is a public health concern affecting 15% of the total adult population in the USA alone.1 Chronic kidney disease is linked to morbidity and mortality. The disease creates a global burden on healthcare expenses due to frequent hospitalisation, progression to other life-threatening diseases, progression to kidney failure, and ultimately death. 2, 3, 4 This article discusses the stages of kidney disease and risk prediction models, and evaluates whether these models provide efficiency in a clinical setting.

There are several stages (1 to 5) involved in chronic kidney disease, where stage 3 is the most common. Stage 3 chronic kidney disease is characterised by a 50% reduction in kidney function. Therefore, it is essential to have an early diagnosis and effective evidence-based management of the disease to prevent further progression and complications. A model was developed and validated to identify patients with stage 3 or 4 kidney disease who were at increased risk of progressing to later stages of kidney disease, and kidney failure.5 This study is helpful as it predicts when to intervene with therapeutics to avoid further loss of kidney filtration rate, and it has the potential to be used to create a chronic kidney disease management program.6

Other risk prediction models of chronic kidney disease are not used for the management of the disease. However, the model developed by this study used demographics, the presence of other diseases, and drug utilisation data that is regularly obtained from patients with chronic kidney disease. This data can be easily included in a clinical decision-making system. Furthermore, the model was able to determine that gender, age, diabetes, individuals with advanced chronic kidney disease, high blood pressure, circulatory disorder, heart failure, kidney filtration risk score, and iron deficiency predict significant risks of chronic kidney disease advancing to kidney failure. Furthermore, with the model, they were able to find two new predictors leading to kidney failure: elevated potassium levels, and poor adherence to a specific class of drugs, known as RAASi, used to treat heart failure. 

This model could be used in several settings, including clinical practice and management. For example, the risk score system used in this study can provide good quality care, and offer personalised treatments to patients with chronic kidney disease. Also, as the model helps to determine those at higher risk of progression to kidney failure, it can aid healthcare providers and insurers in focusing on those individuals. Furthermore, the risk score system used within the model can provide a way for clinicians to decide an order of treatment for patients requiring dialysis or kidney transplantation. Finally, the model could help determine which patients can be enrolled in clinical trial studies depending on various risk thresholds.5

Overall, the model provides a level of accuracy that is acceptable in determining the risk of patients with stage 3 or 4 kidney disease in developing kidney failure. The model included 12 predictors, of which two were new. The findings of the study, therefore, reinforce the use of predictive based models to provide timely treatment. 


  1. Gaitonde Y., Cook L. and Rivera M., 2017. Chronic kidney disease: detection and evaluation. American Family Physician, 96(12), pp.776–783. 
  2. Honeycutt, A., Segel, J., Zhuo, X., Hoerger, T., Imai, K. and Williams, D., 2013. Medical Costs of CKD in the Medicare Population. Journal of the American Society of Nephrology, 24(9), pp.1478-1483.
  3. Golestaneh L., Alvarez J., Reaven L., et al., 2017. All-cause costs increase exponentially with increased chronic kidney disease stage. The American Journal of Managed Care, 23(10), pp.163–172.
  4. Yang, C., Wang, H., Zhao, X., Matsushita, K., Coresh, J., Zhang, L. and Zhao, M., 2020. CKD in China: Evolving Spectrum and Public Health Implications. American Journal of Kidney Diseases, 76(2), pp.258-264.
  5. Dai, D., Alvarez, P. and Woods, S., 2021. A Predictive Model for Progression of Chronic Kidney Disease to Kidney Failure Using a Large Administrative Claims Database. ClinicoEconomics and Outcomes Research, Volume 13, pp.475-486.
  6. Leon, S. and Tangri, N., 2019. The Use of Renin-Angiotensin System Inhibitors in Patients With Chronic Kidney Disease. Canadian Journal of Cardiology, 35(9), pp.1220-1227.
This content is purely informational and isn’t medical guidance. It shouldn’t replace professional medical counsel. Always consult your physician regarding treatment risks and benefits. See our editorial standards for more details.

Get our health newsletter

Get daily health and wellness advice from our medical team.
Your privacy is important to us. Any information you provide to this website may be placed by us on our servers. If you do not agree do not provide the information.

Murielle Nsiela

MSc Graduate in Medical Engineering - Bachelor's degree, Pharmaceutical Science, Keele University, Staffordshire UK

MSc in Medical Engineering Design, Keele University Modules included: Advanced engineering applications, Engineering for medical applications report, Bioreactors and Growth environment, Creative engineering design, Experimental research methodology and research projects

BSc (Hons) Pharmaceutical Science, Technology and Business, Keele University Modules included: Core topics in pharmaceutical science, Laboratory studies - tabletting and liposomes report, applied Pharmaceutical Science 2, Pharmaceutical research project

Leave a Reply

Your email address will not be published. Required fields are marked * presents all health information in line with our terms and conditions. It is essential to understand that the medical information available on our platform is not intended to substitute the relationship between a patient and their physician or doctor, as well as any medical guidance they offer. Always consult with a healthcare professional before making any decisions based on the information found on our website.
Klarity is a citizen-centric health data management platform that enables citizens to securely access, control and share their own health data. Klarity Health Library aims to provide clear and evidence-based health and wellness related informative articles. 
Klarity / Managed Self Ltd
Alum House
5 Alum Chine Road
Westbourne Bournemouth BH4 8DT
VAT Number: 362 5758 74
Company Number: 10696687

Phone Number:

 +44 20 3239 9818