Evolving connectionist system versus algebraic formulas for prediction of renal function from serum creatinine

Date
2005-05
Authors
Marshall, MR
Song, Q
Ma, TM
MacDonell, SG
Kasabov, NK
Supervisor
Item type
Journal Article
Degree name
Journal Title
Journal ISSN
Volume Title
Publisher
Nature Publishing Group
Abstract

Background In clinical trials, equation 7 from the Modification of Diet in Renal Disease (MDRD) Study is the most accurate formula for the prediction of glomerular filtration rate (GFR) from serum creatinine. An alternative approach has been developed using evolving connectionist systems (ECOS), which are novel computing structures that can be trained to generate accurate output from a given set of input variables. This study aims to compare the prediction errors associated with each method, using data that reproduce routine clinical practice as opposed to the artificial setting of clinical trials. Methods The methods were compared using 441 radioisotope measurements of GFR in 178 chronic kidney disease patients from 12 centers in Australia and New Zealand. All clinical and laboratory measurements were obtained from the patients' center rather than central laboratories, as would be the case in routine clinical practice. Both the MDRD formula and ECOS used the same predictive variables, and both were optimized to the study cohort by stepwise regression and training, respectively. Results Mean measured GFR in the cohort was 22.6 mL/min/1.73 m2. The bias and precision of the MDRD formula were -3.5 mL/min/1.73 m2 and 34.5%, respectively, improving to -1.2 mL/min/1.73 m2 and 31.1% after maximal optimization of the formula to study data. The bias and precision of the ECOS were 0.7 mL/min/1.73 m2 and 32.6%, respectively, improving to -0.1 mL/min/1.73 m2 and 16.6% after maximal optimization of the system to study data. The prediction of GFR using ECOS was improved by accounting for the center from where clinical and laboratory measurements originated within the connectionist model. Conclusion Algebraic formulas will be associated with greater prediction error in routine clinical practice than in the original trials, and machine intelligence is more likely to predict GFR accurately in this setting.

Description
Keywords
Adult , Aged , Creatinine , Edetic Acid , Female , Glomerular filtration rate , Humans , Kidney function Tests , Male , Mathematics , Middle Aged , Neural Networks (Computer) , Prospective Studies , Creatinine clearance , Artificial intelligence, Connectionist systems
Source
Kidney International, vol. 67(5), pp. 1944–1954
Rights statement
Copyright © 2005 Nature Publishing Group (www.nature.com). All Rights Reserved. Authors retain the right to place his/her pre-publication version of the work on a personal website or institutional repository for non commercial purposes. The definitive version was published in (see Citation). The original publication is available at (see Publisher’s Version).