Developing an AI-based algorithm to determine visceral fat

Visceral fat, the harmful belly fat that surrounds the body's organs, is a contributor to serious health problems like heart disease, diabetes and cancer.

Researchers in Australia are developing an Artificial Intelligence (AI) algorithm that can estimate the amount of dangerous “hidden fat” (also known as visceral fat) from bone density scans – which are used to detect spinal fractures.

In a statement, Australia's Edith Cowan University (ECU) said on September 4 that visceral fat, the harmful belly fat that surrounds the body's organs, is a factor causing serious health problems such as heart disease, diabetes and cancer.

The ECU research team is training a machine learning algorithm to analyze lateral spine dual-energy X-ray absorptiometry (DXA) scans, used to assess bone density, to accurately predict visceral fat from these images, providing valuable new health insights without the need for additional testing.

Current methods for estimating visceral fat, such as body mass index (BMI), waist circumference, and waist-to-hip ratio, have limitations because they cannot distinguish between different types of body fat, leading to inconsistent assessments of obesity, according to the researchers.

Imaging techniques such as magnetic resonance imaging (MRI) and computed tomography (CT) can accurately measure visceral fat but are expensive and, in the case of CT, can expose patients to higher levels of radiation.

Mr. Syed Zulqarnain Gilani, senior lecturer and leading AI scientist at ECU, said the machine learning model has been trained on thousands of images, the next step is to incorporate more data sets from around the world to be as effective as possible./.

(TTXVN/Vietnam+)

Source: https://www.vietnamplus.vn/phat-trien-thuat-toan-su-dung-ai-de-xac-dinh-luong-mo-trong-noi-tang-post1059916.vnp