The tool automatically measures fat around the heart from MRI scan images.

An AI tool developed by researchers from Queen Mary University of London has established that larger amounts of fat surrounding a person’s heart indicate the higher probability of diabetes regardless of the person’s age, sex, and body mass index. The AI tool could automatically estimate the amount of fat around the heart from MRI scan images. (News Medical)

The difficulties of measuring fat around the heart

It is well accepted that fat accumulated around the heart could be a reliable predictor of various diseases, particularly those related to the heart such as atrial fibrillation and coronary artery disease. It is also a good indicator of the likelihood of diabetes.

However, because measuring the amount of fat around the heart manually is laborious and challenging, this correlation between fat around the heart and other diseases has not been investigated thoroughly such as in studies of large groups of people.

“To address this problem, we’ve invented an AI tool that can be applied to standard heart MRI scans to obtain a measure of the fat around the heart automatically and quickly, in under three seconds,” said Dr Zahra Raisi-Estabragh, Lead Researcher, Queen Mary University of London. “This tool can be used by future researchers to discover more about the links between the fat around the heart and disease risk, but also potentially in the future, as part of a patient’s standard care in hospital.”

Accuracy of diabetes predictions

When tested on MRI scan images of the heart of more than 45,000 people, the AI algorithm could accurately determine the amount of fat around the heart in those images.

It could also calculate the probability of the patient getting diabetes.

“This novel tool has high utility for future research and, if clinical utility is demonstrated, may be applied in clinical practice to improve patient care,” said Professor Steffen Petersen from Queen Mary University of London, who supervised the project. “This work highlights the value of cross-disciplinary collaborations in medical research, particularly within cardiovascular imaging.”

Related Story:   An AI Algo Can Predict Your Diabetes Risk