Predicting the intracellular water compartment using artificial neural network analysis

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 ⁴⁰K counting (ICW_K40), were measured for all study participants. The anthropometric variables and the impedance index (height²/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 (ICWK40) was 25.01±4.50 l, whereas the mean estimated value was 15.20±1.79 l (RMSE=11.06 l) when calculated using ICW_DeLorenzo, 18.07±1.14 l (RMSE=8.72 l) when using ICW_Gudivaka, and 25.01±2.74 l (RMSE=3.22 l) 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.