A groundbreaking study partially funded by the company used AI to understand the genes that determine the aspect of the heart’s left ventricle using three-dimensional images of the organ.

An international team led by the University of Manchester used state-of-the-art unsupervised deep learning to analyze more than 50,000 three-dimensional magnetic resonance images (MRIs) of the heart provided by the UK Biobank.

This study was published in a leading journal nature machine intelligence, focused on uncovering the complex genetic causes behind cardiovascular traits. It revealed 49 new gene locations associated with traits such as left ventricular structure, and 25 additional locations that may have an impact as well.

This discovery has significant implications for cardiology and precision medicine. By further elucidating the genetic basis of cardiovascular traits, this study paves the way for the development of targeted therapies and interventions for people at risk for heart disease.

“The power of big data”

Professor Brian Williams, our chief scientific and medical officer, said: “This new study shows the enormous power of big data to link genes and heart structure. Machine learning can process, analyze, and derive insights from big data to address the biggest questions in cardiovascular research. We’ve made this possible by transforming the way we get

“This pioneering new method will uncover even more genes that influence heart structure and function, providing new insights into why abnormal structure and function causes heart disease. ”

“Heart and circulatory diseases still claim millions of lives every year in the UK. AI has the potential to reveal more information about the genes that contribute to the structure of the heart. In the future This could lead to real improvements for patients, including the development of tailored, precision treatments for people with heart disease.”

“It will be a light for future research.”

Professor Bernard Keaveney, BHF Professor of Cardiovascular Medicine at the University of Manchester, who was involved in the study, said: “By using cutting-edge deep learning to integrate genetic and imaging data, we uncovered the genetic basis of heart structure. ” he said. This approach guides future organ research and understanding of genetic influences on organ anatomy. ”

The research also received funding from the Royal Academy of Engineering (RAEng), the Royal Society, and Argentina’s National Council for Scientific and Technical Research (CONICET). This was a collaboration with the University of Manchester, the University of Leeds, Argentina’s National Council for Scientific and Technical Research, and IBM Research.

Learn more about our research