Key Takeaways
- A new artificial intelligence tool, CardioKG, has been developed to speed up the search for treatments for heart disease
- The tool uses heart imaging data and large medical databases to identify genes linked to disease and potential heart disease drugs
- The approach could lead to more personalized care, with treatments better matched to individual heart function
- The technology could also be adapted to study other conditions, including brain disorders and obesity
- Potential treatments highlighted by the AI model include methotrexate for heart failure and gliptins for atrial fibrillation
Introduction to Cardiovascular Diseases
Cardiovascular diseases (CVDs) are a major health concern, accounting for approximately 1.7 million deaths annually and affecting 62 million people across the European Union, according to the Organisation for Economic Co-operation and Development (OECD). In an effort to combat this, 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. As Declan O’Regan, the group leader of the Computational Cardiac Imaging Group at the MRC Laboratory of Medical Sciences, Imperial College London, noted, "One of the advantages of knowledge graphs is that they integrate information about genes, drugs and diseases."
The Development of CardioKG
The AI tool, named CardioKG, was built using heart imaging data from thousands of people in the UK Biobank, including patients with conditions such as atrial fibrillation, heart failure, and heart attacks, as well as healthy volunteers. By combining this data with large medical databases, researchers can make more accurate predictions about which medicines might help people with specific heart conditions. As O’Regan explained, "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." The tool’s ability to integrate information about genes, drugs, and diseases makes it a powerful resource for identifying potential treatments.
Potential Treatments and Future Directions
The AI model has already highlighted several potential treatments, including methotrexate, which is widely used to treat rheumatoid arthritis, and a group of diabetes medicines known as gliptins. According to the model, methotrexate could help people with heart failure, while gliptins might benefit those with atrial fibrillation. Additionally, the analysis suggested a possible protective effect of caffeine in some patients with atrial fibrillation, although researchers stressed that this does not mean people should change their caffeine intake. As Khaled Rjoob, the first author of the study and a data science researcher at Imperial College London, noted, "Building on this work, we will extend the knowledge graph into a dynamic, patient-centred framework that captures real disease trajectories. This will open new possibilities for personalised treatment and predicting when diseases are likely to develop."
Personalized Care and Future Applications
The development of CardioKG has the potential to lead to more personalized care, with treatments better matched to individual heart function. As O’Regan explained, the approach could eventually lead to more targeted and effective treatments, improving patient outcomes. The technology could also be adapted to study other conditions, including brain disorders and obesity, using medical imaging. This could lead to a greater understanding of the underlying causes of these conditions and the development of more effective treatments. As Rjoob noted, the potential applications of this technology are vast, and further research is needed to fully explore its possibilities.
Conclusion and Future Research
In conclusion, the development of CardioKG is a significant step forward in the search for treatments for heart disease. The tool’s ability to integrate information about genes, drugs, and diseases makes it a powerful resource for identifying potential treatments. As researchers continue to develop and refine the technology, it is likely that we will see significant advances in the treatment of heart disease and other conditions. As O’Regan noted, "One of the advantages of knowledge graphs is that they integrate information about genes, drugs and diseases." This integration of information has the potential to revolutionize the field of medicine, leading to more personalized and effective treatments for a range of conditions.
https://www.euronews.com/health/2026/01/03/new-study-shows-how-ai-could-transform-drug-prescriptions-for-heart-diseases