Adiposity, the accumulation of excess fat in the body, is a well-documented driver of cardiometabolic diseases such as heart disease, stroke, type 2 diabetes, and kidney disease. Yet, obtaining a comprehensive understanding of an individual’s risk has proven challenging. Traditional metrics like body mass index (BMI) often conflate fat and muscle mass, failing to account for fat distribution within the body. In a groundbreaking study, researchers from Mass General Brigham and their colleagues have demonstrated that an artificial intelligence (AI) tool can accurately assess body composition in just three minutes using a body scan. Their findings, published in the Annals of Internal Medicine, reveal that not all fat is equally harmful and underscore the potential of AI to repurpose data from routine medical scans.
“We are hoping that these findings could be used to develop an ‘opportunistic screening’ tool to repurpose existing MRI and CT scans taken at the hospital to find patients with high-risk body composition who may be flying under the radar and could benefit from targeted diabetes and cardiovascular disease prevention,” stated co-senior author Vineet K. Raghu, PhD, a computational scientist with the Mass General Brigham Heart and Vascular Institute.
AI’s Role in Advancing Medical Diagnostics
The study conducted by Raghu and his team utilized data from the U.K. Biobank, analyzing whole-body MRIs of over 33,000 adults with no prior history of diabetes or cardiovascular events, tracked over a median of 4.2 years. The AI tool was able to identify visceral adipose tissue volume—fat surrounding the abdominal organs—and fat deposits in muscle, which were strongly associated with diabetes and cardiovascular disease risk beyond standard obesity measures like BMI and waist circumference. Intriguingly, the study also found that in men, lower skeletal muscle volume was significantly associated with increased risk.
“The team found that in both men and women, AI-derived visceral adipose tissue volume and fat deposits in muscle were strongly associated with diabetes and cardiovascular disease risk beyond standard measures of obesity like BMI and waist circumference.”
Implications for Future Healthcare Practices
The implications of these findings are substantial. By leveraging AI to analyze routine imaging, healthcare providers could potentially identify patients at high risk for cardiometabolic diseases earlier and more accurately. This approach could lead to more personalized and effective prevention strategies, ultimately reducing the incidence of these conditions.
The authors of the study emphasize the need for further research to determine if their findings can be generalized across different populations and if AI can consistently measure these body composition metrics from routine scans. With additional validation, AI-driven diagnostics could become a cornerstone of preventative healthcare, offering a more nuanced understanding of body composition and its impact on health.
Looking Ahead: The Future of AI in Medicine
As AI continues to evolve, its applications in medicine are expanding rapidly. The ability to extract detailed insights from routine medical scans could transform how diseases are predicted and prevented. This study, authored by Matthias Jung, Michael T. Lu, Vineet K. Raghu, and colleagues, represents a significant step forward in this journey.
Funding for this research was provided by the Deutsche Forschungsgemeinschaft (German Research Foundation), the Norn Group Longevity Impetus Grant, NHLBI K01HL168231, and the AHA Career Development Award. The study, titled “Association Between Body Composition and Cardiometabolic Outcomes,” is available in the Annals of Internal Medicine.
As healthcare systems worldwide grapple with the rising burden of cardiometabolic diseases, the integration of AI into routine diagnostics offers a promising avenue for early intervention and improved patient outcomes. The ongoing research and development in this field hold the potential to redefine how we understand and manage health risks associated with body composition.
