// NATURE NEWS — SPAZIO & SCIENZA
Artificial intelligence-enabled clinical phenotyping of human brown fat
Nature
(2026) Cite this article
Adipose tissue has a central role in systemic energy balance and the pathogenesis of obesity and its sequelae1,2. In contrast to white adipose tissue, brown adipose tissue (BAT) uses energy to produce heat3. Detectable BAT in humans is associated with decreased prevalence of cardiometabolic diseases4. However, the complete spectrum of health conditions associated with BAT remains unknown, and high-throughput methods to quantify BAT activity in humans are lacking5,6. Here we leveraged big data and artificial intelligence to systematically define the clinical impact of BAT in a cohort of 101,243 patients from a large cancer centre. Our unbiased analyses revealed that, across all diagnoses, cardiovascular and psychiatric diseases were less prevalent in people with BAT. Using a machine learning approach, we semi-automatically quantified BAT activity in approximately 8,700 patients and demonstrated that higher BAT activity, especially in the axillary depot, is associated with lower odds of cardiometabolic diseases and healthier white fat distribution. People with BAT also exhibited more favourable glycaemic parameters, lipid profiles, inflammatory markers and echocardiographic indices. Analysis of medication usage demonstrated that angiotensin receptor blocker use was positively associated with BAT presence. As proof of concept, we showed that the angiotensin receptor blocker losartan increased brown adipocyte activity and whole-body energy expenditure. Altogether, our studies harnessing artificial intelligence and big data identify new clinical phenotypes linked to BAT and serve as a platform for drug repurposing to activate this tissue in humans.
Obesity is a major risk factor for type 2 diabetes (T2D), hypertension and cardiovascular disease2,7. Adipose tissue dysfunction is a hallmark of obesity and contributes to the pathophysiology of cardiometabolic diseases1. White adipose tissue (WAT) stores energy as triglyceride1 in subcutaneous and visceral depots, and visceral adiposity is a key feature of metabolically unhealthy obesity8. By contrast, brown adipose tissue (BAT) dissipates energy as heat (thermogenesis) and its activation in animal models protects against obesity and metabolic diseases3. However, the relevance of BAT to adult human physiology and whether it can be targeted therapeutically remain unclear5,6.
Since the landmark reports that adult humans have inducible BAT9,10,11,12, several clinical studies have aimed to recruit BAT through cold exposure or β-adrenergic agonists13,14,15,16,17. Although these interventions activate BAT and improve glucose homeostasis, their side effects and the small number of participants studied have limited their clinical impact5. More recently, our group described the largest reported cohort of people with BAT and demonstrated that the presence of BAT in 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET)–computed tomography (CT) (18F-FDG-PET–CT) scans obtained for clinical purposes and without previous stimulation was associated with reduced prevalence of cardiometabolic disease4. A caveat from this work is that patients were characterized based on BAT presence or absence, rather than by quantitative BAT metabolic activity. Like WAT, human BAT is localized in distinct anatomic depots18, but whether these depots uniquely affect health remains unknown. Moreover, most human BAT studies have focused on cardiometabolic outcomes, but how this tissue influences other organ systems and disease types remains largely unexplored. These limitations have hindered the identification of pharmacologic agents that promote BAT activity, and there are no approved, widely used medications to leverage the cardiometabolic benefits linked to this tissue.
In this study we expanded our cohort to more than 100,000 patients and performed an unbiased, comprehensive analysis across all diagnostic codes to identify new clinical pheno