AUTHOR=Fu Zhiyan , Wang Zhiyu , Clemente Karen , Jaisinghani Mohit , Poon Ken Mei Ting , Yeo Anthony Wee Teo , Ang Gia Lee , Liew Adrian , Lim Chee Kong , Foo Marjorie Wai Yin , Chow Wai Leng , Ta Wee An 

TITLE=Development and deployment of a nationwide predictive model for chronic kidney disease progression in diabetic patients

JOURNAL=Frontiers in Nephrology

VOLUME=Volume 3 - 2023

YEAR=2024

URL=https://www.frontiersin.org/journals/nephrology/articles/10.3389/fneph.2023.1237804

DOI=10.3389/fneph.2023.1237804

ISSN=2813-0626

ABSTRACT=Chronic Kidney Disease (CKD) is a major complication of diabetes and a significant disease burden on the healthcare system. The aim of this work is to apply predictive model to identify high-risk patients at early stages of CKD to provide early intervention in order to avert or delay kidney function deterioration.Using the data of the National Diabetes Database in Singapore, we applied a machine learning algorithm to develop a predictive model on CKD progression for diabetic patients and deploy the model in nationwide.Our model was rigorously validated and outperformed existing models and clinician predictions. The area under the ROC curve (AUC) of our model is 0.88, with the 95% confidence interval being 0.87-0.89. In recognition of its higher and consistent accuracy, and clinical usefulness, our CKD model became the first clinical model deployed nationwide in Singapore and has been incorporated into national program to engage patients in long-term care plans in battling chronic diseases. The risk score generated by the model stratifies patients into three risk levels, which are embedded into Diabetes Patient Dashboard for clinicians and care managers to allocate healthcare resource accordingly.This project provided a successful example to demonstrate how an AI model can be adopted to support clinical decision making nationwide.