Background/Objectives Body mass index (BMI) is a proxy for obesity that is commonly used in spite of its limitation in estimating body fatness. Trained observers with repeated exposure to different body types can estimate body fat (BF) of individuals compared to criterion methods with reasonable accuracy. The purpose of this study was to develop and validate a computer algorithm to provide a valid estimate %BF using digital photographs. Subjects/Methods Our sample included 97 children and 226 adults (age in years: 11.3±3.3; 38.1±11.6, respectively). Measured height and weight were used (BMI in kg/m 2 : 20.4±4.4; 28.7±6.6 for children and adults, respectively). Dual x-ray absorptiometry (DXA) was the criterion method. Body volume (BV PHOTO ) and body shape (BS PHOTO ) were derived from two digital images. Final support vector regression (SVR) models were trained using age, sex, race, BMI for % BF NOPHOTO , plus BV PHOTO and BS PHOTO for %BF PHOTO. Separate validation models were used to evaluate the learning algorithm in children and adults. The differences in correlations between %BF DXA , %BF NOPHOTO and %BF PHOTO were tested using the Fisher’s Z-score transformation. Results Mean BF DXA and BF PHOTO were 27.0%±9.2 vs. 26.7%± 7.4 in children and 32.9± 10.4% vs. 32.8%±9.3 in adults. SVR models produced %BF PHOTO values strongly correlated with % BF DXA . Our final model produced correlations of r DP = 0.80 and r DP = 0.87 in children and adults, respectively for %BF PHOTO vs. %BF DXA . The correlation between %BF NOPHOTO and %BF DXA was moderate, yet statistically significant in both children r DB = 0.70; p <0.0001 and adults r DB = 0.86; p<0.0001. However, the correlations for r DP were statistically higher than r DB (%BF DXA vs. %BF NOPHOTO ) in both children and adults (children: Z = 5.95, p<0.001; adults: Z = 3.27, p<0.0001). Conclusions Our photographic method produced valid estimates of BF in both children and adults. Further research is needed to create norms for subgroups by sex, race/ethnicity, and mobility status.
Mendeley helps you to discover research relevant for your work.
CITATION STYLE
Affuso, O., Pradhan, L., Zhang, C., Gao, S., Wiener, H. W., Gower, B., … Allison, D. B. (2018). A method for measuring human body composition using digital images. PLoS ONE, 13(11). https://doi.org/10.1371/journal.pone.0206430