Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.27017 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911571088769024 |
|---|---|
| author | Zhou, Menglian Charton, Arno Blanchard, Emily Cai, Lawrence Giest, Tracy Watkins, Herschel Bouterfa, Mohamed Wasson, Jackie Natarajan, Keerthana Deshpande, Aniket Zhan, Jiening Yuen, Shelten Prieto, Xavi Shreibati, Jacqueline Malhotra, Mark Patel, Shwetak Sunden, Lindsey Speed, Cathy Kokoszka, Alicia Natarajan, Aravind Pantelopoulos, Alexandros Metwally, Ahmed |
| author_facet | Zhou, Menglian Charton, Arno Blanchard, Emily Cai, Lawrence Giest, Tracy Watkins, Herschel Bouterfa, Mohamed Wasson, Jackie Natarajan, Keerthana Deshpande, Aniket Zhan, Jiening Yuen, Shelten Prieto, Xavi Shreibati, Jacqueline Malhotra, Mark Patel, Shwetak Sunden, Lindsey Speed, Cathy Kokoszka, Alicia Natarajan, Aravind Pantelopoulos, Alexandros Metwally, Ahmed |
| contents | Body Mass Index (BMI) is a widely accessible but imprecise proxy of cardiometabolic health. While assessing true body composition is superior, gold-standard methods like Dual-Energy X-ray Absorptiometry (DXA) are not scalable. We address this gap by developing and validating "PhotoScan," a method to estimate body composition from smartphone imagery. We pretrained a deep learning model on UK Biobank participants (N=35,323) and fine-tuned on a newly recruited clinical cohort (PhotoBIA cohort, N=677) with diverse ethnicity, age, and body fat distribution, achieving high accuracy against DXA for total body fat percentage (BF%, MAE = 2.15%), Android-to-Gynoid fat ratio (A/G, MAE = 0.11), and visceral-to-subcutaneous fat area ratio (V/S, MAE = 0.09). Generalizability of the model was demonstrated on an independent metabolic health study cohort (MetabolicMosaic cohort, N=132 participants), achieving MAEs of 2.13% for BF%, 0.09 for A/G, and 0.09 for V/S. We then evaluated the clinical utility of these metrics in the MetabolicMosaic cohort by predicting insulin resistance (IR). Adding PhotoScan-derived body composition metrics to baseline demographics model (Age, Sex, BMI) significantly improved insulin resistance classification (Area Under the Receiver Operating Characteristic Curve "AUROC" 76.0% vs 69.2%, DeLong test p=0.002, Net Reclassification Index "NRI" 0.593). Crucially, this accessible smartphone method achieved performance nearly equivalent to adding clinical-grade DXA data to baseline demographics model (AUROC 77.3% vs 69.2%, DeLong test p=0.004, NRI 0.748). These findings demonstrate that smartphone-based phenotyping captures clinically meaningful risk signals missed by BMI and anthropometrics, offering a scalable alternative to DXA for cardiometabolic risk stratification. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_27017 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Beyond BMI: Smartphone Body Composition Phenotyping for Cardiometabolic Risk Assessment Zhou, Menglian Charton, Arno Blanchard, Emily Cai, Lawrence Giest, Tracy Watkins, Herschel Bouterfa, Mohamed Wasson, Jackie Natarajan, Keerthana Deshpande, Aniket Zhan, Jiening Yuen, Shelten Prieto, Xavi Shreibati, Jacqueline Malhotra, Mark Patel, Shwetak Sunden, Lindsey Speed, Cathy Kokoszka, Alicia Natarajan, Aravind Pantelopoulos, Alexandros Metwally, Ahmed Quantitative Methods Body Mass Index (BMI) is a widely accessible but imprecise proxy of cardiometabolic health. While assessing true body composition is superior, gold-standard methods like Dual-Energy X-ray Absorptiometry (DXA) are not scalable. We address this gap by developing and validating "PhotoScan," a method to estimate body composition from smartphone imagery. We pretrained a deep learning model on UK Biobank participants (N=35,323) and fine-tuned on a newly recruited clinical cohort (PhotoBIA cohort, N=677) with diverse ethnicity, age, and body fat distribution, achieving high accuracy against DXA for total body fat percentage (BF%, MAE = 2.15%), Android-to-Gynoid fat ratio (A/G, MAE = 0.11), and visceral-to-subcutaneous fat area ratio (V/S, MAE = 0.09). Generalizability of the model was demonstrated on an independent metabolic health study cohort (MetabolicMosaic cohort, N=132 participants), achieving MAEs of 2.13% for BF%, 0.09 for A/G, and 0.09 for V/S. We then evaluated the clinical utility of these metrics in the MetabolicMosaic cohort by predicting insulin resistance (IR). Adding PhotoScan-derived body composition metrics to baseline demographics model (Age, Sex, BMI) significantly improved insulin resistance classification (Area Under the Receiver Operating Characteristic Curve "AUROC" 76.0% vs 69.2%, DeLong test p=0.002, Net Reclassification Index "NRI" 0.593). Crucially, this accessible smartphone method achieved performance nearly equivalent to adding clinical-grade DXA data to baseline demographics model (AUROC 77.3% vs 69.2%, DeLong test p=0.004, NRI 0.748). These findings demonstrate that smartphone-based phenotyping captures clinically meaningful risk signals missed by BMI and anthropometrics, offering a scalable alternative to DXA for cardiometabolic risk stratification. |
| title | Beyond BMI: Smartphone Body Composition Phenotyping for Cardiometabolic Risk Assessment |
| topic | Quantitative Methods |
| url | https://arxiv.org/abs/2603.27017 |