Assessing body composition via a smartphone computer vision application: High repeatability but method-dependent agreement compared with BODPOD and Inbody
4 affiliations
- 1Sports Medicine Assessment Research & Testing (SMART) Laboratory, George Mason University, Virginia, United States of America
- 2State Key Laboratory of Mechanical System and Vibration, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China
- 3Department of Bioengineering, George Mason University, Virginia, United States of America
- 4Center for the Advancement of Well-Being, George Mason University, Fairfax, Virginia, United States of America
Abstract
Accurate assessment of body composition is essential for monitoring health status, fitness progress, and disease risk. Traditional methods such as air displacement plethysmography (BODPOD) and bioelectrical impedance analysis (BIA) are widely used to estimate body fat percentage (BF%), fat mass (FM), and fat-free mass (FFM), but can be costly or inaccessible. Smartphone applications utilizing computer vision (CV) offer a promising alternative. This study evaluated the relative agreement and same session repeatability under standardized conditions of a smartphone-based CV application (CVapp) compared to BODPOD and the InBody BIA device. Forty-nine adults (ages 18–70; 29 females, 27 racial and ethnic minority participants) completed two consecutive measurements using BODPOD, InBody, and CVapp in a single session. Differences in BF%, FM, and FFM estimates were analyzed using repeated-measures ANOVA. Agreement metrics included mean absolute error (MAE), root mean square error (RMSE), concordance correlation coefficients (CCC), and Bland-Altman analysis. Subgroup analyses examined differences by sex and minority status. The CVapp yielded higher BF% (mean=+2.2%, P = 0.004) and FM (+1.5 kg, p = 0.015) compared to BODPOD, and lower FFM than InBody (mean=−1.84 kg, p = 0.043). The CVapp agreement with BODPOD (MAE = 4.0, RMSE = 5.0, CCC = 0.86) was weaker than with the InBody (MAE = 3.3, RMSE = 4.3, CCC = 0.89), with wider limits of agreement. All methods showed excellent within session repeatability under standardized conditions (ICC > 0.99). A significant Sex×Method interaction was observed for BF% (p < 0.001), FM (p < 0.001), and FFM (p = 0.013), with females showing greater overestimation of BF% (mean=+3.9%) and FM (mean=+2.7 kg, p < 0.001), and underestimation of FFM (mean=−2.5 kg, p < 0.001) by the CVapp. Among Minority participants, BF% and FM estimates from the CVapp were significantly higher than BODPOD (mean=+2.7%, p = 0.009; mean=+1.8 kg, p = 0.031), and FFM was lower (mean=−1.8 kg, p = 0.035), with significant Method×Minority Group interactions for FM and FFM (p < 0.03). These findings support cautious use of CVapp-derived values for within-person monitoring under similar conditions but suggest they should not be treated as interchangeable with established comparator methods or used as standalone diagnostic estimates of body composition. Future efforts should address the need for more accurate, transparent, and equitable algorithms that are validated across diverse populations and testing contexts. Author summary: Body composition measurements are widely used to monitor health, fitness, and the effects of nutrition and exercise programs. Traditional assessment methods often require specialized equipment, trained personnel, and access to laboratories, making them impractical for many people. Smartphone applications that estimate body composition from photographs could make these assessments far more accessible, but they must first be shown to produce trustworthy results. In this study, we compared a commercially available smartphone computer vision application with two commonly used body composition methods under carefully standardized laboratory conditions. We found that the smartphone application produced highly consistent results when measurements were repeated during the same session, demonstrating excellent repeatability. However, its estimates were not interchangeable with the comparison methods and differed systematically for some groups of participants, particularly females and participants from racial and ethnic minority groups. These findings highlight an important distinction between consistency and agreement: a tool can provide repeatable measurements while still producing systematically different estimates. Our results suggest that smartphone-based body composition applications may be useful for monitoring changes within an individual over time, but they should be interpreted cautiously for estimating absolute body composition.
Related
- Inter‐Session Repeatability of a Smartphone‐Based Markerless System to Measure Segment Length and Lower‐Limb Kinematics in Patients With End‐Stage Knee Osteoarthritis
- The relationship between smartphone addiction, Mediterranean diet adherence, body composition, and quality of life among university students: a cross-sectional study
- Testing the Feasibility of a Smartphone Application for Collecting Data on Occupational Violence Exposure Among Nurses and Midwives
- Immunonutrition vs. Standard Oral Nutritional Supplements in Prehabilitation for Colorectal Cancer Surgery: A Randomized Clinical Trial Assessing Morbidity and Body Composition by Computed Tomography
- Assessing the Competing Risks of Loss to Follow-up and Mortality Among Adults Receiving Antiretroviral Therapy in Northern Ghana: Application of the Fine-Gray Subdistribution Hazard Model
BibTeX
@article{sisohor2026assessing,
title = {{Assessing body composition via a smartphone computer vision application: High repeatability but method-dependent agreement compared with BODPOD and Inbody}},
author = {Jahliya Sisohor and Jatin P. Ambegaonkar and Bryndan Lindsey and Qi Wei and Yosef Shaul and Joel Martin},
journal = {PLOS Digital Health},
year = {2026},
month = sep,
doi = {10.1371/journal.pdig.0000983},
url = {https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0000983},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Assessing body composition via a smartphone computer vision application: High repeatability but method-dependent agreement compared with BODPOD and Inbody
AU - Jahliya Sisohor
AU - Jatin P. Ambegaonkar
AU - Bryndan Lindsey
AU - Qi Wei
AU - Yosef Shaul
AU - Joel Martin
PY - 2026
DA - 2026/09/02
JO - PLOS Digital Health
DO - 10.1371/journal.pdig.0000983
UR - https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0000983
AB - Accurate assessment of body composition is essential for monitoring health status, fitness progress, and disease risk. Traditional methods such as air displacement plethysmography (BODPOD) and bioelectrical impedance analysis (BIA) are widely used to estimate body fat percentage (BF%), fat mass (FM), and fat-free mass (FFM), but can be costly or inaccessible. Smartphone applications utilizing computer vision (CV) offer a promising alternative. This study evaluated the relative agreement and same session repeatability under standardized conditions of a smartphone-based CV application (CVapp) compared to BODPOD and the InBody BIA device. Forty-nine adults (ages 18–70; 29 females, 27 racial and ethnic minority participants) completed two consecutive measurements using BODPOD, InBody, and CVapp in a single session. Differences in BF%, FM, and FFM estimates were analyzed using repeated-measures ANOVA. Agreement metrics included mean absolute error (MAE), root mean square error (RMSE), concordance correlation coefficients (CCC), and Bland-Altman analysis. Subgroup analyses examined differences by sex and minority status. The CVapp yielded higher BF% (mean=+2.2%, P = 0.004) and FM (+1.5 kg, p = 0.015) compared to BODPOD, and lower FFM than InBody (mean=−1.84 kg, p = 0.043). The CVapp agreement with BODPOD (MAE = 4.0, RMSE = 5.0, CCC = 0.86) was weaker than with the InBody (MAE = 3.3, RMSE = 4.3, CCC = 0.89), with wider limits of agreement. All methods showed excellent within session repeatability under standardized conditions (ICC > 0.99). A significant Sex×Method interaction was observed for BF% (p < 0.001), FM (p < 0.001), and FFM (p = 0.013), with females showing greater overestimation of BF% (mean=+3.9%) and FM (mean=+2.7 kg, p < 0.001), and underestimation of FFM (mean=−2.5 kg, p < 0.001) by the CVapp. Among Minority participants, BF% and FM estimates from the CVapp were significantly higher than BODPOD (mean=+2.7%, p = 0.009; mean=+1.8 kg, p = 0.031), and FFM was lower (mean=−1.8 kg, p = 0.035), with significant Method×Minority Group interactions for FM and FFM (p < 0.03). These findings support cautious use of CVapp-derived values for within-person monitoring under similar conditions but suggest they should not be treated as interchangeable with established comparator methods or used as standalone diagnostic estimates of body composition. Future efforts should address the need for more accurate, transparent, and equitable algorithms that are validated across diverse populations and testing contexts. Author summary: Body composition measurements are widely used to monitor health, fitness, and the effects of nutrition and exercise programs. Traditional assessment methods often require specialized equipment, trained personnel, and access to laboratories, making them impractical for many people. Smartphone applications that estimate body composition from photographs could make these assessments far more accessible, but they must first be shown to produce trustworthy results. In this study, we compared a commercially available smartphone computer vision application with two commonly used body composition methods under carefully standardized laboratory conditions. We found that the smartphone application produced highly consistent results when measurements were repeated during the same session, demonstrating excellent repeatability. However, its estimates were not interchangeable with the comparison methods and differed systematically for some groups of participants, particularly females and participants from racial and ethnic minority groups. These findings highlight an important distinction between consistency and agreement: a tool can provide repeatable measurements while still producing systematically different estimates. Our results suggest that smartphone-based body composition applications may be useful for monitoring changes within an individual over time, but they should be interpreted cautiously for estimating absolute body composition.
SN - 2767-3170
ER -