Article Impact Level: HIGH Data Quality: STRONG Summary of Annals of Internal Medicine, https://doi.org/10.7326/ANNALS-24-01863 Dr. Matthias Jung et al.
Points
- AI-derived body composition from MRI is strongly associated with cardiometabolic risk.
- High visceral adipose tissue proportion is an independent predictor for diabetes and MACE in both sexes.
- Elevated skeletal muscle fat fraction is also an independent predictor for diabetes and MACE in both sexes.
- In males only, a low skeletal muscle proportion significantly increases the risk for diabetes and MACE.
- These detailed body composition measures add prognostic value beyond traditional BMI and waist circumference.
Summary
This prospective cohort study investigated the association between artificial intelligence (AI)-derived body composition (BC) compartments from magnetic resonance imaging (MRI) and cardiometabolic outcomes. Conducted within the UK Biobank, the study included 33,432 participants (mean age 65.0 years [SD, 7.8]; mean BMI 25.8 kg/m2 [SD, 4.2]; 52.8% female) with no history of diabetes, myocardial infarction, or ischemic stroke. An AI tool was utilized to derive three-dimensional BC measures, including subcutaneous adipose tissue (SAT), visceral adipose tissue (VAT), skeletal muscle (SM), and SM fat fraction (SMFF), allowing for the calculation of their relative distribution.
Initially, after adjusting for age, smoking, and hypertension, greater adiposity and lower SM proportion were associated with higher incidence of diabetes mellitus (DM) and major adverse cardiovascular events (MACE) over a median follow-up of 4.2 years. However, upon further adjustment for BMI and waist circumference (WC), the prognostic value narrowed significantly. Only elevated VAT proportions (top fifth percentile) and high SMFF (top fifth percentile) retained significant associations with increased risk for DM (females: aHR 2.16 [95% CI, 1.59 to 2.94] for VAT, 1.27 [CI, 0.89 to 1.80] for SMFF; males: aHR 1.84 [CI, 1.48 to 2.27] for VAT, 1.84 [CI, 1.43 to 2.37] for SMFF) and MACE (females: aHR 1.37 [CI, 1.00 to 1.88] for VAT, 1.72 [CI, 1.23 to 2.41] for SMFF; males: aHR 1.22 [CI, 0.99 to 1.50] for VAT, 1.25 [CI, 0.98 to 1.60] for SMFF).
Additionally, in males exclusively, those in the bottom fifth percentile of SM proportion exhibited an increased risk for DM (aHR 1.96 [CI, 1.45 to 2.65]) and MACE (aHR 1.55 [CI, 1.15 to 2.09]). The study concludes that while AI-derived BC proportions are strongly linked to cardiometabolic risk, after accounting for conventional measures like BMI and WC, VAT proportion and SMFF (in both sexes) and SM proportion (in males only) provide independent prognostic information. The generalizability of these findings may be limited to White populations within the UK.
Link to the article: https://www.acpjournals.org/doi/10.7326/ANNALS-24-01863
References
Jung, M., Reisert, M., Rieder, H., Rospleszcz, S., Lu, M. T., Bamberg, F., Raghu, V. K., & Weiss, J. (2025). Association between body composition and cardiometabolic outcomes: A prospective cohort study. Annals of Internal Medicine, ANNALS-24-01863. https://doi.org/10.7326/ANNALS-24-01863
