The Role of Body Adiposity Index in Determining Body Fat Percentage in Colombian Adults with Overweight or Obesity

Abstract

The aim of this study is to investigate the accuracy of body adiposity index (BAI) as a convenient tool for assessing body fat percentage (BF%) in a sample of adults with overweight/obesity using bioelectrical impedance analysis (BIA). The study population was composed of 96 volunteers (60% female, mean age 40.6 ± 7.5 years old). Anthropometric characteristics (body mass index, height, waist-to-height ratio, hip and waist circumference), socioeconomic status, and diet were assessed, and BF% was measured by BIA-BF% and by BAI-BF%. Pearson's correlation coefficient was used to evaluate the correlation between BAI-BF% and BF% assessed by BIA-BF%, while controlling for potential confounders. The concordance between the BF% measured by both methods was obtained with a paired sample t-test, Lin's concordance correlation coefficient, and Bland-Altman plot analysis. Overall, the correlation between BF% obtained by BIA-BF% and estimated by BAI-BF% was r = 0.885, p < 0.001, after adjusting for potential confounders (age, socioeconomic status, and diet). Lin's concordance correlation coefficient was moderate in both sexes. In the men, the paired t-test showed a significant mean difference in BF% between the methods (-5.6 (95%CI -6.4 to -4.8); p < 0.001). In the women, these differences were (-3.6 (95%CI -4.7 to -2.5); p < 0.001). Overall, the bias of the BAI-BF% was -4.8 ± 3.2 BF%; p < 0.001), indicating that the BAI-BF% method significantly underestimated the BF% in comparison with the reference method. In adults with overweight/obesity, the BAI presents low agreement with BF% measured by BIA-BF%; therefore, we conclude that BIA-BF% is not accurate in either sex when body fat percentage levels are low or high. Further studies are necessary to confirm our findings in different ethnic groups.

Trial registration: ClinicalTrials.gov NCT02715063.

Keywords: adults; body composition; obesity; prediction; validity.

Figure 1

Bland-Altman plots with mean bias (central line) and 95% limits of agreement for comparing BAI-BF% and BIA-BF% among women (A), and men (C). Panels (B,D) represent residual values for Bland-Altman linear regression. The central line represents the systematic bias between BAI-BF% and BIA-BF%; the outer lines represent 95% limits. Solid lines represent the regression line and dashed lines indicate ± 1.96 SD. SD: standard deviation.