Kidney Age Index (KAI): A novel age-related biomarker to estimate kidney function in patients with diabetic kidney disease using machine learning. (November 2021)

• Record Type: Journal Article
• Authors: Belur Nagaraj, Sunil; Kieneker, Lyanne M; Pena, Michelle J
• Is Part Of: Computer methods and programs in biomedicine. Volume 211(2021)
• Publication Date: 2021-11
• Subjects: Machine learning -- Diabetes -- Chronic kidney disease -- Healthy aging -- Medical informatics; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2021.106434
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Several methods have been developed to estimate renal risk, however with a high margin of error and difficult to interpret. The kidneys of patients with diabetic kidney disease age faster compared to their chronological age. The Kidney Age Index may be an easily understandable tool to discuss renal risk with patients. Abstract: Background and objective: With aging, patients with diabetic kidney disease (DKD) show progressive decrease in kidney function. We investigated whether the deviation of biological age (BA) from the chronological age (CA) due to DKD can be used (denoted as Kidney Age Index; KAI) to quantify kidney function using machine learning algorithms. Methods: Three large datasets were used in this study to develop KAI. The machine learning algorithms were trained on PREVEND dataset with healthy subjects ( N = 7963) using 13 clinical markers to predict the CA. The trained model was then used to predict the BA of patients with DKD using RENAAL ( N = 1451) and IDNT ( N = 1706). The performance of four traditional machine learning algorithms were evaluated and the KAI = BA-CA was estimated for each patient. Results: The neural network model achieved the best performance and predicted the CA of healthy subjects in PREVEND dataset with a mean absolute deviation (MAD) = 6.5 ± 3.5 years and pearson correlation = 0.62. Patients with DKD showed a significant higher KAI of 15.4 ± 11.8 years and 13.6 ± 12.3 years in RENAAL and IDNT datasets, respectively. Conclusions: Our findings suggest that for a given CA, patients with DKD shows excess BA when compared to their healthy counterparts due to disease severity. With further improvement, the proposed KAI can be used as a complementary easy-to-interpret tool to give a more inclusive idea into disease state.