Researchers from the MRC Laboratory of Medical Sciences have introduced a new approach to studying heart disease by integrating imaging data into knowledge graphs. The team, led by Dr Khaled Rjoob and Professor Declan O'Regan from the Computational Cardiac Imaging Group, developed a model called CardioKG. This is the first time imaging data has been added to a knowledge graph, which traditionally connects information about genes, diseases, treatments, molecular pathways, and symptoms.
CardioKG uses heart-imaging data collected from 4,280 UK Biobank participants with atrial fibrillation, heart failure or heart attack and 5,304 healthy individuals. The researchers generated over 200,000 image-based traits to train their model. They combined this with information from 18 biological databases and used artificial intelligence to predict associations between genes and diseases as well as potential opportunities for drug repurposing.
The study identified several new genes linked to heart disease. It also predicted that methotrexate—commonly used for rheumatoid arthritis—could help treat heart failure. Additionally, gliptins—a class of drugs for diabetes—may benefit patients with atrial fibrillation. The research also found that caffeine might have a protective effect in patients with atrial fibrillation who experience irregular and fast pulse rates.
Professor Declan O'Regan commented on these findings: "What's exciting is there are other recent studies in the field which support our preliminary findings," says Declan, "this highlights the huge potential of knowledge graphs in uncovering existing drugs that might be repurposed as new treatments."
The researchers suggest that CardioKG is a proof-of-concept technology with potential applications beyond cardiology. Similar approaches could be applied to imaging data from other organs such as the brain or body fat to investigate new therapeutic options for conditions like dementia or obesity.
Dr Khaled Rjoob said: "Building on this work, we will extend the knowledge graph into a dynamic, patient-centred framework that captures real disease trajectories," says Khaled, "This will open new possibilities for personalised treatment and predicting when diseases are likely to develop."
The project received funding from organizations including the Medical Research Council, British Heart Foundation, Bayer AG and the National Institute for Health and Care Research (NIHR) Imperial College Biomedical Research Centre.
Professor O'Regan also serves as British Heart Foundation Professor of Cardiovascular AI and Clinical Theme Lead at Imperial's National Heart and Lung Institute.
