Abstract
Currently available anthropometric body composition prediction equations were often developed on small participant samples, included only several measured predictor variables, or were prepared using conventional statistical regression methods. Machine learning approaches are increasingly publicly available and have key advantages over statistical modeling methods when developing prediction algorithms on large datasets with multiple complex covariates. This study aimed to test the feasibility of predicting DXA-measured appendicular lean mass (ALM) with a neural network (NN) algorithm developed on a sample of 576 participants using 10 demographic (sex, age, 7 ethnic groupings) and 43 anthropometric dimensions generated with a 3D optical scanner. NN-predicted and measured ALM were highly correlated (n = 116; R2, 0.95, p < 0.001, non-significant bias) with small mean, absolute, and root-mean square errors (X ± SD, −0.17 ± 1.64 kg and 1.28 ± 1.04 kg; 1.64). These observations demonstrate the application of NN body composition prediction algorithms to rapidly emerging large and complex digital anthropometric datasets. Clinical Trial Registration: NCT03637855, NCT05217524, NCT03771417, and NCT03706612.
This is a preview of subscription content, log in via an institution to check access.
Data availability
Data and computer code will made available to investigators following request and review by the authors.
References
Bennett JP, Liu YE, Quon BK, Kelly NN, Wong MC, Kennedy SF, et al. Assessment of clinical measures of total and regional body composition from a commercial 3-dimensional optical body scanner. Clin Nutr. 2022;41:211–8.
Majmudar MD, Chandra S, Yakkala K, Kennedy S, Agrawal A, Sippel M, et al. Smartphone camera based assessment of adiposity: a validation study. NPJ Digit Med. 2022;5:79.
Pilgrim LJ. History of photogrammetry in medicine. Australas Phys Eng Sci Med. 1992;15:1–8.
McCarthy C, Tinsley GM, Yang S, Irving BA, Wong MC, Bennett JP, et al. Smartphone prediction of skeletal muscle mass: model development and validation in adults. Am J Clin Nutr. 2023;117:794–801.
Alzubaidi L, Zhang J, Humaidi AJ, Al-Dujaili A, Duan Y, Al-Shamma O, et al. Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. J Big Data. 2021;8:53.
DeGregory KW, Kuiper P, DeSilvio T, Pleuss JD, Miller R, Roginski JW, et al. A review of machine learning in obesity. Obes Rev. 2018;19:668–85.
Marin-Jimenez N, Cruz-Leon C, Sanchez-Oliva D, Jimenez-Iglesias J, Caraballo I, Padilla-Moledo C, et al. Criterion-related validity of field-based methods and equations for body composition estimation in adults: a systematic review. Curr Obes Rep. 2022;11:336–49.
McCarthy C, Tinsley GM, Bosy-Westphal A, Muller MJ, Shepherd J, Gallagher D, et al. Total and regional appendicular skeletal muscle mass prediction from dual-energy X-ray absorptiometry body composition models. Sci Rep. 2023;13:2590.
Zheng Y, Long Z, Zhang X, Hahn JK. 3D Body shape for regional and appendicular body composition estimation. Proc SPIE Int Soc. 2023;12464:124642C.
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, et al. Scikit-learn: machine learning in python. J Mach Learn Res. 2011;12:2825–30.
Thomas DM, Kleinberg S, Brown AW, Crow M, Bastian ND, Reisweber N, et al. Machine learning modeling practices to support the principles of AI and ethics in nutrition research. Nutr Diabetes. 2022;12:48.
Funding
This work was partially supported by National Institutes of Health NORC Center Grants P30DK072476, Pennington Biomedical Research Center and P30DK040561, Harvard Medical School and by the National Institute of Diabetes and Digestive and Kidney Diseases (NIH R01DK111698 & R01DK109008).
Author information
Authors and Affiliations
Contributions
CM, JAS, and SBH designed the study; FM, CM, RHF, HN, TN, JAS, GMT, and SBH conducted the analyses; SBH and JAS acquired essential materials; FM, CM, RHF, HN, TN, JAS, GMT, and SBH prepared the manuscript; and FM, CM, RHF, HN, TN, JAS, GMT, and SBH reviewed and approved the final manuscript.
Corresponding author
Ethics declarations
Competing interests
SBH reports his role on the Medical Advisory Boards of Tanita Corporation, Amgen, and Medifast. GMT has received support for his research laboratory, in the form of research grants or equipment loan or donation, from manufacturers of body composition assessment devices, including Size Stream LLC; Naked Labs Inc.; Prism Labs Inc.; RJL Systems; MuscleSound; and Biospace, Inc. The other authors and their close relatives and their professional associates have no financial interests in the study outcome, nor do they serve as an officer, director, member, owner, trustee, or employee of an organization with a financial interest in the outcome or as an expert witness, advisor, consultant, or public advocate on behalf of an organization with a financial interest in the study outcome.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary information
Rights and permissions
About this article
Cite this article
Marazzato, F., McCarthy, C., Field, R.H. et al. Advances in digital anthropometric body composition assessment: neural network algorithm prediction of appendicular lean mass. Eur J Clin Nutr 78, 452–454 (2024). https://doi.org/10.1038/s41430-023-01396-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1038/s41430-023-01396-3
- Springer Nature Limited