## Abstract

Artificial neural networks (ANN) are used for a wide variety of data-processing applications such as predicting medical outcomes and classifying clinical data and patients. We investigated the applicability of an ANN for estimating the intracellular water compartment for a population of 104 healthy Italians ranging in age from 19 to 68 years. Anthropometric variables, bioelectric impedance analysis (BIA) variables, and reference values for intracellular water, measured using whole-body ^{40}K counting (ICW _{K40}), were measured for all study participants. The anthropometric variables and the impedance index (height^{2}/resistance) were fed to the ANN input layer, which produced as output the estimated values for intracellular water (ICW_{ANN}). We also estimated intracellular water using a BIA formula for the same population (ICW_{DeLorenzo}) and another for Caucasians (ICW_{Gudivaka}). Errors in the estimations generated by ANN and the BIA equations were calculated as the root mean square error (RMSE). The mean (±SD) reference value (ICW_{K40}) was 25.01±4.50 1, whereas the mean estimated value was 15.20±1.79 1 (RMSE=11.06 1) when calculated using ICW_{DeLorenzo}, 18.07±1.14 1 (RMSE=8.72 1) when using ICW_{Gudivaka}, and 25.01±2.74 1 (RMSE=3.22 1) when using ICW_{ANN}. Based on these results, we deduce that the ANN algorithm is a more accurate predictor for reference ICW _{K40} than BIA equations.

Original language | English |
---|---|

Journal | Acta Diabetologica |

Volume | 40 |

Issue number | SUPPL. 1 |

ISSN | 0940-5429 |

DOIs | |

Publication status | Published - 01.10.2003 |