Genetic algorithms for parameter estimation in mathematical modeling of glucose metabolism

Authors:
Umberto Morbiducci; Andrea Tura;Mauro Grigioni
Affiliations:
Laboratory of Biomedical Engineering, Istituto Superiore di Sanití, Viale Regina Elena 299, 00161 Rome, Italy;Institute of Biomedical Engineering, National Research Council, Padua, Italy;Laboratory of Biomedical Engineering, Istituto Superiore di Sanití, Viale Regina Elena 299, 00161 Rome, Italy
Venue:
Computers in Biology and Medicine
Year:
2005

Citing 6
Cited 4

Adaptation in natural and artificial systems

Adaptation in natural and artificial systems
Genetic algorithms + data structures = evolution programs (3rd ed.)

Genetic algorithms + data structures = evolution programs (3rd ed.)
Automatic correlation and calibration of noisy sensor readings using elite genetic algorithms

Artificial Intelligence
Outline for a Logical Theory of Adaptive Systems

Journal of the ACM (JACM)
Genetic Algorithms in Search, Optimization and Machine Learning

Genetic Algorithms in Search, Optimization and Machine Learning
Hybrid simplex genetic algorithm for blind equalization using RBF networks

Mathematics and Computers in Simulation

Mathematical modeling and application of genetic algorithm to parameter estimation in signal transduction: Trafficking and promiscuous coupling of G-protein coupled receptors

Computers in Biology and Medicine
Genetic algorithm based NARX model identification for evaluation of insulin sensitivity

Applied Soft Computing
Identification of a model of non-esterified fatty acids dynamics through genetic algorithms: The case of women with a history of gestational diabetes

Computers in Biology and Medicine
An evolutionary approach for searching metabolic pathways

Computers in Biology and Medicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

Direct measurement of hormones secretion and kinetics in glucose metabolism is not feasible in the clinical practice, being highly invasive. As their knowledge is important in the diagnosis of metabolic disorders, thanks to mathematical models based on non-invasive tests, estimation of hormones behaviour is obtained. Unfortunately, traditional model estimation can suffer for convergence problems, and it can be strongly dependent on the parameters initial value. To overcome these limitations, Genetic algorithms (GAs) were tested on a group of 49 subjects. The stochastic nature of GAs allowed overcoming the initialization problem. Moreover, GAs significantly improved the accuracy of fit.