Artificial neural network model effectively estimates muscle and fat mass using simple demographic and anthropometric measures

Prediction of body fat percentage: Development and validation of new anthropometric equations

INTRODUCTION

The aim of this study was to test the validity of existing equations, retrieved from the literature, in the Algerian adult population. To develop, and validate, new predictive equations for body fat percentage (%BF) using simple and easy-to-measure anthropometric parameters.

METHODS

This is a cross-sectional study including 877 Algerian adults who underwent a body composition assessment by the direct segmental multi-frequency bioelectrical impedance technique (Inbody-770). Participants were randomly divided into two groups: the development group (n = 577) and the validation group (n = 300). To develop the equations, multiple linear regression models were analyzed. The predictive performance of the developed equations was compared with the direct technique. The following validation tests were used: Student's t-test for paired samples, correlation, and Bland-Altman diagram. Diagnostic accuracy has also been assessed.

RESULTS

Four existing equations were tested, and all showed statically significant bias. Four new equations were developed; all had satisfactory predictive performance, with a correlation coefficient ranging from 0.72 to 0.94 in men and 0.87 to 0.93 in women. The best-fitting equation was based on body mass index, waist-to-hip ratio, and chest circumference. The diagnostic accuracy of this equation was 96.7% in men and 95.3% in women.

CONCLUSION

The newly developed equations based on anthropometric parameters can serve as a simple tool for the accurate prediction of BF% in adult subjects, at both individual and epidemiological levels.

Artificial Neural Network Models for Accurate Predictions of Fat-Free and Fat Masses, Using Easy-to-Measure Anthropometric Parameters

Abdominal fat and fat-free masses report a close association with cardiometabolic risks, therefore this specific body compartment presents more interest than whole-body masses. This research aimed to develop accurate algorithms that predict body masses and specifically trunk fat and fat-free masses from easy to measure parameters in any setting. The study included 104 apparently healthy subjects, but with a higher-than-normal percent of adiposity or waist circumference. Multiple linear regression (MLR) and artificial neural network (ANN) models were built for predicting abdominal fat and fat-free masses in patients with relatively low cardiometabolic risks. The data were divided into training, validation and test sets, and this process was repeated 20 times per each model to reduce the bias of data division on model accuracy. The best performance models used a maximum number of five anthropometric inputs, with higher R² values for ANN models than for MLR models (R² = 0.96-0.98 vs. R² = 0.80-0.94, p = 0.006). The root mean square error (RMSE) for all predicted parameters was significantly lower for ANN models than for MLR models, suggesting a higher accuracy for ANN models. From all body masses predicted, trunk fat mass and fat-free mass registered the best performance with ANN, allowing a possible error of 1.84 kg for predicting the correct trunk fat mass and 1.48 kg for predicting the correct trunk fat-free mass. The developed algorithms represent cost-effective prediction tools for the most relevant adipose and lean tissues involved in the physiopathology of cardiometabolic risks.