Cardiovascular disease remains the world's leading cause of death, despite decades of advances in treatment. One of the biggest challenges is that many people show few, if any, warning signs until the condition has already progressed.
Researchers at the University of Hong Kong believe artificial intelligence could help change that. In a study published in Nature Communications, they describe a blood test that estimates a person's future risk of several major cardiovascular diseases by analysing thousands of biological markers rather than relying mainly on inherited genetics, reports Science Daily.
A broader picture
The research suggests the approach can detect patterns linked to coronary artery disease, stroke, heart failure, atrial fibrillation, peripheral artery disease and venous thromboembolism. Among people who later developed cardiovascular disease, the model identified elevated risk as much as 15 years before clinical diagnosis.
The system, called CardiOmicScore, was trained using data from the UK Biobank. Instead of focusing only on DNA, it examines proteins and metabolites circulating in the blood, which can change over time in response to factors such as ageing, lifestyle, diet and overall health.
Also read: New drug shows promise for millions with kidney disease
According to the researchers, this creates a more dynamic assessment of cardiovascular risk than genetic scores alone, which remain largely unchanged throughout a person's life.
From prediction to prevention
Current cardiovascular risk assessments are typically based on factors including age, blood pressure, smoking history and cholesterol levels. While these remain valuable, the researchers argue they may not always capture the earliest biological changes associated with future disease.
The study found that combining the AI-generated score with routine clinical information improved the model's ability to predict long-term cardiovascular risk.
Although the findings are promising, the technology is still at the research stage and is not yet available as part of routine medical care. Further studies will be needed to confirm its performance across different populations before it can be introduced into clinical practice.
Also read: New study identifies the painkillers linked to the highest overdose risk
Also read: High temperatures during pregnancy may affect children's brain development, study finds
This article is made and published by Mie Hermansen, who may have used AI in the preparation.