A new artificial intelligence tool could speed up the search for treatments for heart disease, according to a new study.
Cardiovascular diseases (CVDs) are the leading cause of death and disability across the European Union, accounting for about 1.7 million deaths annually and affecting 62 million people, according to the Organisation for Economic Co-operation and Development (OECD).
Scientists at Imperial College London have developed an artificial intelligence (AI) tool to identify which genes are linked to disease and to help find heart disease drugs faster by combining detailed heart scans with large medical databases.
The tool, named CardioKG, was built using heart imaging data from thousands of people in the UK Biobank. This included patients with conditions such as atrial fibrillation, heart failure and heart attacks, as well as healthy volunteers.
By doing this, researchers say they can make more accurate predictions about which medicines might help people with specific heart conditions.
“One of the advantages of knowledge graphs is that they integrate information about genes, drugs and diseases,” said Declan O’Regan, the group leader of the Computational Cardiac Imaging Group at the MRC Laboratory of Medical Sciences, Imperial College London.
Researchers say the approach could eventually lead to more personalised care, where treatments are better matched to how an individual’s heart is functioning.
The same technology could also be adapted to study other conditions using medical imaging, including brain disorders and obesity.
“This means you have more power to make discoveries about new therapies. We found that including heart imaging in the graph transformed how well new genes and drugs could be identified,” said O’Regan.
Among the drugs highlighted were methotrexate, which is widely used to treat rheumatoid arthritis, and a group of diabetes medicines known as gliptins.
The AI model suggested methotrexate could help people with heart failure, while gliptins might benefit those with atrial fibrillation.
The analysis also pointed to a possible protective effect of caffeine in some patients with atrial fibrillation, although researchers stressed this does not mean people should change their caffeine intake.
“Building on this work, we will extend the knowledge graph into a dynamic, patient-centred framework that captures real disease trajectories,” said Khaled Rjoob, the first author of the study and a data science researcher at Imperial College London.
“This will open new possibilities for personalised treatment and predicting when diseases are likely to develop”.
Curated by Fatima Al-Hassan
