Artificial Intelligence pinpoints diabetes risk by assessing fat levels near the heart
In a groundbreaking development, researchers from Queen Mary University of London have developed an AI tool that can automatically measure the amount of fat around the heart from MRI scan images. The research paper detailing this innovation, titled 'Automated quality-controlled cardiovascular magnetic resonance pericardial fat quantification using a convolutional neural network in the UK Biobank', has been published in the prestigious journal Frontiers in Cardiovascular Medicine.
The AI tool, which includes an in-built method for calculating the uncertainty of its own results, was tested on heart MRI scans of over 45,000 people, including participants in the UK Biobank. The research paper, which can be accessed at this link: https://www.frontiersin.org/articles/10.3389/fcvm.2021.677574, reveals that the new AI tool can show 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.
Interestingly, the research paper was not authored by the researchers who developed the AI tool. It's worth noting that the research paper was not funded by the CAP-AI program, contrary to some reports. The CAP-AI program, led by Barts Life Sciences, is a collaborative effort between Capital Enterprise, Barts Health NHS Trust, Digital Catapult, and The Alan Turing Institute.
The funding for the research on the development of the new AI tool for automatic measurement of fat tissue around the heart on MRI images was provided by a specific chapter of the CAP-AI program, led by Prof. Vasilis Ntziachristos. The CAP-AI program receives funding from the European Regional Development Fund and Barts Charity.
While the research paper does not provide information about the distribution of fat in the body or the association between fat around the heart and various diseases, it does suggest that fat accumulation around the heart may be a predictor of heart disease. This has been linked to a range of conditions, including atrial fibrillation, diabetes, and coronary artery disease.
It's important to note that the commonly used measure of body mass index (BMI) mostly reflects fat accumulation under the skin, rather than around the internal organs. This underscores the significance of the new AI tool, which could potentially revolutionise the way we assess and manage cardiovascular health.
The DOI for the research paper is 10.3389/fcvm.2021.677574. For those interested in learning more about the distribution of fat in the body and its impact on health, further research is encouraged.
