Truace
Subscribe

Artificial intelligence-enabled clinical phenotyping of human brown fat

Adipose tissue has a central role in systemic energy balance and the pathogenesis of obesity and its sequelae 1,2 . In contrast to white adipose tissue, brown adipose tissue (BAT) uses energy to produce heat 3 . Detectable BAT in humans is associated with decreased prevalence of cardiometabolic diseases 4 . However, the complete spectrum of health conditions associated with BAT remains unknown, and high-throughput methods to quantify BAT activity in humans are lacking 5,6 . Here we leveraged big data and artific…

By the Truvace desk2 min read1 sourcePeer-reviewedTRV-2026-2130· cite & verify
Artificial intelligence-enabled clinical phenotyping of human brown fat
Quantitative-assessment-of-brown-adipose-tissue-metabolic-activity-and-volume-using-18F-FDG-PETCT-2191-219X-1-30-S1 by Mirbolooki M, Constantinescu C, Pan M, Mukherjee J. CC BY 2.0 · https://creativecommons.org/licenses/by/2.0

In brief

Researchers used big data and artificial intelligence to study brown adipose tissue, a fat type that burns energy to make heat, across a cohort of 101,243 patients from a large cancer centre. Across all diagnoses, cardiovascular and psychiatric diseases were less prevalent in people with detectable brown fat.

A machine learning method then scored brown fat activity in roughly 8,700 patients. This matters because high-throughput ways to measure the tissue in humans were lacking, and the work suggests an existing drug class could be repurposed to activate it. What remains open is how far these associations hold beyond this patient group and whether they translate into clinical benefit.

Main points

  1. The cohort included 101,243 patients from a large cancer centre, and brown fat detection was analysed across all diagnoses.
  2. Higher brown fat activity, especially in the axillary depot, was associated with lower odds of cardiometabolic diseases and healthier white fat distribution.
  3. People with brown fat showed more favourable glycaemic parameters, lipid profiles, inflammatory markers and echocardiographic indices.
  4. Angiotensin receptor blocker use was positively associated with brown fat presence in the medication analysis.
  5. As proof of concept, losartan increased brown adipocyte activity and whole-body energy expenditure.

The gain

Machine learning let researchers semi-automatically measure brown fat activity in about 8,700 patients, linking higher activity to lower odds of cardiometabolic disease and pointing to losartan as a candidate for activating the tissue.

The rundown

The study begins from a gap: detectable brown fat in humans has been tied to fewer cardiometabolic diseases, but the full range of associated health conditions was unknown and scalable ways to quantify its activity were missing.

An unbiased analysis of the large cohort found that cardiovascular and psychiatric diseases were less prevalent in people with brown fat. The machine learning step then gave activity measures for about 8,700 patients, allowing comparison of fat distribution, blood markers and heart imaging indices.

The medication analysis flagged angiotensin receptor blockers as associated with brown fat presence. A proof-of-concept test showed losartan raised brown adipocyte activity and whole-body energy expenditure, which the authors present as a platform for drug repurposing.

Sources

  1. Peer-reviewedNature2026-10-14

The debate