Abstract 12760: Association of Machine Learning-Derived Measures of Body Fat Distribution in >40,000 Individuals With Cardiometabolic Diseases

Abstract

Background: Obesity is defined based on body-mass index (BMI), a proxy for overall adiposity. However, for any given BMI, individuals vary substantially in fat distribution. The clinical implications of this variability 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, 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: Machine learning models based on two-dimensional projection images enabled near-perfect estimation of VAT, ASAT, and GFAT, with r 2 in a holdout testing dataset >0.97 for each. 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: For any given BMI, measures of local adiposity have variable and divergent associations with cardiometabolic diseases.