Title: A clustering method to study the loss of kidney function following kidney transplantation

Authors: Ashish Joshi, Aryya Gangopadhyay, Madhushri Banerjee, George Baffoe-Bonnie, Viresh Mohanlal, Ravinder K. Wali

Addresses: Department of Information Systems, University of Maryland Baltimore County (UMBC), Baltimore, MD 21250, USA. ' Department of Information Systems, University of Maryland Baltimore County (UMBC), Baltimore, MD 21250, USA. ' Department of Information Systems, University of Maryland Baltimore County (UMBC), Baltimore, MD 21250, USA. ' School of Medicine, Department of Medicine, University of Maryland Baltimore, Baltimore, MD 21201, USA. ' Harbor hospital Center, Baltimore, MD Brooklyn, MD 21225, USA. ' School of Medicine, Department of Medicine, University of Maryland Baltimore, Baltimore, MD 21201, USA

Abstract: We describe a method for studying the loss of kidney functions after renal transplantation. We monitor the changes in the estimated glomerular filtration rate (eGFR) for each patient on a monthly basis for 24 months following the transplantation. Principal components analysis is performed on the time series of eGFRs. The data is then clustered into two groups, which are then statistically analysed. We developed kernel density functions for each month on the two clusters to further validate our findings that exhibit different characteristics in their renal functions in the post-transplant periods. This can have significant monitoring and treatment implications.

Keywords: eGFR; estimated glomerular filtration rate; kidney transplants; renal transplantation; CKD; chronic kidney disease; K-means clustering; principal components analysis; PCA; kernel density functions; kidney function loss; renal functions.

DOI: 10.1504/IJBET.2010.029652

International Journal of Biomedical Engineering and Technology, 2010 Vol.3 No.1/2, pp.64 - 82

Published online: 30 Nov 2009 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article