Metabolic syndrome is a major global health concern, affecting a quarter of the global population and leading to severe health issues like heart attacks, strokes, diabetes, cognitive diseases, and liver diseases. This syndrome creates significant challenges for patients, not only due to its severe health implications but also due to the difficulty in diagnosing and managing it effectively. People with metabolic syndrome often exhibit an apple-shaped body, characterized by significant abdominal weight. Currently, diagnosis is based on a combination of laboratory tests, blood pressure measurements, and body shape evaluations. However, the absence of universally accepted screening methods, due to variability in measurements, complicates the effective screening for this syndrome. Clinically, metabolic syndrome is confirmed when an individual exhibits at least three of the following conditions: abdominal obesity, elevated blood pressure, high triglyceride levels, reduced HDL cholesterol, and high fasting blood glucose levels. Given the limitations of current diagnostic methods like body mass index (BMI) and bioimpedance scales, which often provide inaccurate results, there is a pressing need for more reliable and consistent methods to assess the risk and severity of metabolic syndrome.

Researchers at Mayo Clinic (Rochester, MN, USA) are now integrating artificial intelligence (AI) with an advanced 3D body-volume scanner to help doctors predict metabolic syndrome risk and severity. The combination of tools offers a more accurate alternative to other measures of disease risk like BMI and waist-to-hip ratio, according to the study published in the European Heart Journal - Digital Health. The research team developed and validated this AI model using data from 1,280 volunteer subjects who underwent comprehensive health evaluations including 3D body-volume scans, clinical questionnaires, blood tests, and traditional body measurements. Additionally, to further refine the tool’s capabilities, 133 volunteers were assessed using front- and side-view images captured via a mobile app to determine the presence and severity of their metabolic syndrome.

The findings indicated that using 3D imaging to digitally measure a patient’s body volume index offers a highly accurate assessment of body shapes and volumes, particularly in areas prone to unhealthy visceral fat accumulation like the abdomen and chest. These scans also measure volumes in the hips, buttocks, and legs, which are indicative of muscle mass and healthier fat deposits. Whether using a large, stationary 3D scanner or a mobile app, the technology successfully identified the presence and severity of metabolic syndrome through non-invasive imaging, bypassing the need for more invasive tests. Future research will aim to expand the diversity of the study’s participant pool to enhance the generalizability of the findings.

"Our research shows that this AI model may also be a tool to guide clinicians and patients to take action and seek outcomes that are a better fit for their metabolic health," said Betsy Medina Inojosa, M.D., a research fellow at Mayo Clinic and first author of the study. 

http://www.gzjiayumed.com/en/index.asp .