Artificial Intelligence pinpoints diabetes risk through assessment of fat near the heart
In a groundbreaking development, researchers from Queen Mary University of London have created an artificial intelligence (AI) tool that can automatically measure the amount of fat around the heart from MRI scan images. This tool, published in the esteemed journal Frontiers in Cardiovascular Medicine, has the potential to revolutionise the way we understand and approach heart health.
The research paper, titled 'Automated quality-controlled cardiovascular magnetic resonance pericardial fat quantification using a convolutional neural network in the UK Biobank', was authored by a team of experts including Andrew Bard, Zahra Raisi-Estabragh, Maddalena Ardissino, Aaron Lee, Francesca Pugliese, Damini Dey, Sandip Sarkar, Patricia B. Munroe, Stefan Neubauer, Nicholas C. Harvey, and Steffen E. Petersen.
Interestingly, this research paper was published in the same journal where the original AI tool for measuring heart fat was previously published. The new tool, however, offers an additional advantage - it can calculate a patient's risk of diabetes.
Funding for the research came from the CAP-AI programme, led by Barts Life Sciences. It's important to note that the CAP-AI programme is separate from the funding source for the research on the AI tool for measuring heart fat. The CAP-AI programme, led by Capital Enterprise in partnership with Barts Health NHS Trust, Digital Catapult, and The Alan Turing Institute, focuses on a variety of AI-related projects, not just the development of AI tools for medical imaging.
The AI tool was tested on over 45,000 people's heart MRI scan images, including participants in the UK Biobank. The results showed that a larger amount of fat around the heart is associated with significantly greater odds of diabetes, independent of a person's age, sex, and body mass index. This finding underscores the potential of the AI tool as a predictor of heart disease, a condition that has been linked to a range of conditions, including atrial fibrillation, diabetes, and coronary artery disease.
One notable feature of the AI tool is its in-built method for calculating the uncertainty of its own results. This feature ensures that the results are reliable and can be trusted by healthcare professionals and researchers alike.
The new tool could be a valuable resource for future researchers seeking to discover more about the links between the fat around the heart and disease risk. The research paper, which is available at this link: https://www.frontiersin.org/articles/10.3389/fcvm.2021.677574, provides a comprehensive overview of the development and testing of the AI tool.
The distribution of fat in the body can influence a person's risk of developing various diseases. By accurately measuring the amount of fat around the heart, this AI tool could play a crucial role in preventing and managing heart disease.
