Association of machine learning-derived measures of body fat distribution with cardiometabolic diseases in >40,000 individuals
Authors:
- Saaket AgrawalSASaaket Agrawal
- Takara L. StanleyTSTakara L. Stanley
- Patrick T. EllinorPEPatrick T. Ellinor
- Melina ClaussnitzerMCMelina Claussnitzer
- Steven K. GrinspoonSGSteven K. Grinspoon
- Amit V. KheraAKAmit V. Khera
Preprint
Abstract
Background: The clinical implications of BMI-independent variation in fat distribution are not fully understood. Methods: We studied MRI imaging data of 40,032 UK Biobank participants. Using previously quantified visceral (VAT), abdominal subcutaneous (ASAT), and gluteofemoral (GFAT) adipose tissue volume in up to 9,041 to train convolutional neural networks (CNNs), we quantified these depots in the remainder of the participants. We derived new metrics for each adipose depot – fully independent of BMI – by quantifying deviation from values predicted by BMI (e.g. VAT adjusted for BMI, VATadjBMI) and determined associations with cardiometabolic diseases. Results: CNNs based on two-dimensional projection images enabled near-perfect estimation of VAT, ASAT, and GFAT, with r 2 in a holdout testing dataset (r 2 = 0.978-0.991). Using the newly derived measures of local adiposity – residualized based on BMI – we note marked heterogeneity in associations with cardiometabolic diseases. Taking presence of type 2 diabetes as an example, VATadjBMI was associated with significantly increased risk (odds ratio per standard deviation increase (OR/SD) 1.49; 95%CI: 1.43-1.55), while ASATadjBMI was largely neutral (OR/SD 1.08; 95%CI: 1.03-1.14) and GFATadjBMI conferred protection (OR/SD 0.75; 95%CI: 0.71-0.79). Similar patterns were observed for coronary artery disease. Conclusions: Deep learning models trained on a simplified MRI input enable near perfect quantification of VAT, ASAT, and GFAT. For any given BMI, measures of local adiposity have variable and divergent associations with cardiometabolic diseases.Keywords
All Related Versions
- Published version: Nature Communications, 14 (1), 1.
This publication has 48 references indexed in Scilit:
- Absolute value of visceral fat area measured on computed tomography scans and obesity-related cardiovascular risk factors in large-scale Japanese general population (the VACATION-J study)Annals of Medicine, 2010
- Gluteofemoral body fat as a determinant of metabolic healthInternational Journal of Obesity, 2010
- Patterns of Abdominal Fat DistributionDiabetes Care, 2009
- Identification and Characterization of Metabolically Benign Obesity in HumansArchives of internal medicine (1960), 2008
- Abdominal obesity and metabolic syndromeNature, 2006
- Evidence for a role of developmental genes in the origin of obesity and body fat distributionProceedings of the National Academy of Sciences, 2006
- Overweight, Obesity, and Mortality from Cancer in a Prospectively Studied Cohort of U.S. AdultsNew England Journal of Medicine, 2003
- Body Fat Distribution and Insulin Resistance in Healthy Asian Indians and CaucasiansThe Journal of Clinical Endocrinology & Metabolism, 2001
- LMNA, encoding lamin A/C, is mutated in partial lipodystrophyNature Genetics, 2000
- Obesity: new insight into the anthropometric classification of fat distribution shown by computed tomography.BMJ, 1985