AI technique helps detect people at risk of heart failure

Share:
AI technique helps detect people at risk of heart failure

The main function of the heart is to pump blood throughout the body non-stop. It’s an involuntary muscle that is vital for survival. If the heart has difficulty pumping blood effectively, it may lead to a multitude of heart conditions, including heart failure.

Heart failure is a potentially fatal illness that stems from the inability of the heart to pump enough blood to meet the body’s needs. Usually, it develops gradually, which means it worsens over time. The condition can either affect the right side or both sides of the heart.

A team of researchers has now used an artificial intelligence (AI) technique that can identify people who are at risk of developing heart failure, which can help in developing novel treatments and therapies for the condition.

The researchers at the Queen Mary University of London utilized an artificial intelligence technique to study and examine magnetic resonance imaging (MRI) scans of about 17,000 healthy UK Biobank participants. After analysis, they found that certain genetic factors account for about 22% to 39% of the variation in size and function of the heart’s left ventricle.

The function of the left ventricle

The heart’s left ventricle is a strong muscle that is responsible for pumping oxygenated blood into the aorta and throughout the body. When the left ventricle becomes enlarged and weak, it can eventually lead to heart failure. Hence, the researchers point out that some people are at higher risk of heart failure depending on the size and function of the left ventricle.

The left ventricle is the strongest muscle in the heart and if it becomes impaired, oxygen won’t reach the different cells in the body as needed. As a result, when these cells do not have oxygen, they will die.

In the study published in the journal Circulation, the team conducted AI analysis of images in a fraction of the time. The experts have developed AI algorithms to help study other aspects of cardiac structure and physiology. With these analyses, they can help doctors and health experts to improve the efficiency of patient care for heart failure.

“We report fourteen genetic loci and indicate several candidate genes which not only enhance our understanding of the genetic architecture of prognostically important LV phenotypes but also shed light on potential novel therapeutic targets for LV remodeling,” the researchers concluded in the study.

Study implications for medical treatments


It is exciting that the state-of-the-art AI techniques now allow rapid and accurate measurement of the tens of thousands of heart MRI images required for genetic studies. The findings open up the possibility of earlier identification of those at risk of heart failure and of new targeted treatments. The genetic risk scores established from this study could be tested in future studies to create an integrated and personalized risk assessment tool for heart failure.
Dr Nay Aung, Queen Mary University of London and lead author of study
Past studies have shown that the differences in the function, size, and structural characteristics of the heart can be influenced by genetics. However, this is the first study on how genes that affect heart structure and subsequently, increase the risk of having heart failure. Knowledge and understanding of the genetic basis of heart structure and function can ultimately lead to new therapies and treatment options.

Aside from that, the study could lead to further investigation for genetic research using heart MRI images and gene analysis.

For the researchers, using MRI images and genetics can validate how hereditary factors can impact heart function. Gene analysis has once again provided new knowledge and discovery that may provide a blueprint for future studies, and eventually, the formulation of new drugs to target these genes and reduce the risk of heart failure.

Journal reference:
Aung, N., Vargas, J., Yang, C., Cabrera, C., Warren, H., Fung, K., Tzanis, E., Barnes, M., Rotter, J., Taylor, K., Manichaikul, A., Lima, J., Bluemke, D., Piechnik, S., Neubauer, S., Munroe, P., and Petersen, S. (2019). Genome-Wide Analysis of Left Ventricular Image-Derived Phenotypes Identifies Fourteen Loci Associated with Cardiac Morphogenesis and Heart Failure Development. Circulation. https://www.ahajournals.org/doi/10.1161/CIRCULATIONAHA.119.041161

No comments