Diagnostic performance of an artificial neural network to predict excess body fat in children

BACKGROUND: Waist circumference (WC) and z scores of body mass index (BMI) are commonly used to predict childhood obesity, although BMI and WC have a limited sensitivity. OBJECTIVES: To generate an artificial neural network (ANN), using the input parameters age, height, weight, and WC, to predict excess body fat in children. METHODS: As part of the National Health and Nutrition Examination Survey (NHANES) study, in the years 1999 to 2004, the body fat percentage of randomly selected Americans from 8 to 19 years were measured using whole-body dual energy X-ray absorptiometry (DXA) scans. Excess body fat was defined as a body fat percentage ≥ 85th centile. RESULTS: The data of 1999 children (856 female) were eligible. In females, the sensitivity of the BMI, WC, and ANN approaches to predict excess body fat were 0.751 (95% CI, 0.730-0.771), 0.523 (0.487-0.559), and 0.782 (0.754-0.810), respectively. In males, the sensitivity of the BMI, WC, and ANN approaches to predict excess body fat were 0.721 (95% CI, 0.699-0.743), 0.572 (0.549-0.594), and 0.795 (0.768-0.821). CONCLUSIONS: Only in boys, the diagnostic performance in identifying excess body fat was better by using an ANN than by applying BMI and WC z scores. In girls, the ANN and BMI z scores performed comparable and significantly better than WC z scores.