A single blood test can predict heart disease 15 years in advance

The study was published in the journal Nature Communications.

The development was presented by a team of researchers from the University of Hong Kong. They created a tool called CardiOmicScore, which uses artificial intelligence techniques to analyse complex biological data.

Details

The system is based on analysing thousands of molecular markers in the blood, including:

• proteins
• metabolites
• genetic data.

To train the model, scientists used data from the UK Biobank, one of the largest medical projects in the world.

The algorithm is able to estimate the risk of developing six common cardiovascular diseases at once, including:

• coronary heart disease
• stroke
• heart failure
• atrial fibrillation
• peripheral arterial disease
• venous thromboembolism.

According to the researchers, the system can detect signs of future disease about 15 years before it occurs.

Benefits

Today, doctors assess the risk of heart disease mainly based on factors such as:

• age
• blood pressure
• smoking
• cholesterol level.

However, such indicators do not always reflect early changes in the body.

The new approach analyses real biological processes in the body and can help to detect the risk of disease much earlier. This gives more time for prevention - such as making lifestyle changes or starting treatment.

Background

Cardiovascular disease remains the leading cause of death worldwide. According to international studies, they are responsible for nearly 20 million deaths in 2022.

Scientists believe that new methods of early diagnosis could help prevent many of these cases.

Source

Yan Luo et al, AI-based multiomics profiling reveals complementary omics contributions to personalised prediction of cardiovascular disease, Nature Communications (2026), DOI: 10.1038/s41467-026-68956-6