New AI tool could help find heart disease drugs faster

Credit: Unsplash+

A team of scientists in the UK has taken a big step forward in understanding heart disease by combining medical images with a powerful computer tool called a knowledge graph.

This new system, named CardioKG, could help doctors discover which genes are linked to heart problems and even find new uses for existing medicines.

Knowledge graphs are like smart maps. They connect pieces of information such as genes, symptoms, diseases, and treatments, showing how everything is linked.

These graphs have been used in medicine before, but one thing was missing—actual images of how organs look and work in the body. That’s what makes CardioKG special. For the first time, researchers added real heart scan data into a knowledge graph.

The work was led by Dr. Khaled Rjoob and Professor Declan O’Regan at the MRC Laboratory of Medical Sciences. They used heart imaging data from over 9,000 people in the UK Biobank, including patients with heart conditions like atrial fibrillation, heart failure, and heart attacks, as well as healthy individuals.

These scans showed more than 200,000 different traits about how the heart looks and functions. The team used this massive amount of data to train an artificial intelligence model that could learn how these traits relate to genes and diseases.

What they found was exciting. With the help of CardioKG, the computer model was able to predict which genes might be involved in heart disease and which existing drugs might help treat them. For example, the drug methotrexate—normally used for arthritis—could be useful for heart failure.

Another group of drugs called gliptins, used to treat diabetes, might help patients with atrial fibrillation. Perhaps most surprising, the model suggested that caffeine might actually help some people with atrial fibrillation by calming their heart rhythms. This goes against the common belief that caffeine is always bad for the heart.

Professor O’Regan explained that adding imaging data to the graph made a big difference. It gave the computer much more power to detect patterns and connections between genes, diseases, and drugs. He also said that other studies are beginning to support their results, especially the one about caffeine.

The CardioKG system is still new, but the researchers believe this kind of tool could be used for other parts of the body too. The same approach could be applied to brain scans, fat distribution in the body, or any other organ where imaging data is available. This could lead to better understanding and treatment of conditions like dementia or obesity.

By making it easier to spot the most important genes and how they relate to diseases, knowledge graphs could also help drug companies work faster and more accurately when developing new treatments. Instead of starting from scratch, they could use graphs like CardioKG to see which drugs might already be helpful for other illnesses.

Dr. Rjoob said the next step is to make the system more personal. They hope to build a version that tracks how diseases develop over time in individual patients. This could lead to more personalised treatments and help doctors predict who might get sick before symptoms even appear.

The study was supported by several major organisations, including the Medical Research Council, the British Heart Foundation, and Bayer. Professor O’Regan is also a leader in heart disease research at Imperial College London and the British Heart Foundation.

In conclusion, CardioKG is a powerful new tool that combines heart images with genetic and medical data to discover new ways to treat heart disease. It can spot links between genes and heart conditions and may help repurpose existing drugs.

The research shows that technology like this could lead to faster and more effective treatments—not just for the heart, but for other diseases too. This is an exciting step forward in the future of personalised medicine.

If you care about heart disease, please read studies that herbal supplements could harm your heart rhythm, and how eating eggs can help reduce heart disease risk.

For more health information, please see recent studies that apple juice could benefit your heart health, and results showing yogurt may help lower the death risks in heart disease.

The study is published in Nature.

Copyright © 2025 Knowridge Science Report. All rights reserved.