Researchers at The University of Hong Kong have developed an artificial intelligence-powered blood test capable of predicting major cardiovascular diseases up to 15 years before symptoms become clinically visible.

The system, called CardiOmicScore, uses a single blood sample to estimate future risks for six serious cardiovascular conditions, including coronary artery disease, stroke, heart failure, atrial fibrillation, peripheral artery disease and venous thromboembolism.

The findings were published in the scientific journal Nature Communications.

Scientists say the tool could help doctors identify high-risk patients much earlier and shift healthcare toward preventive treatment instead of reactive care.

Cardiovascular disease remains the world’s leading cause of death.

According to global health estimates cited in the study, cardiovascular conditions caused around 19.8 million deaths worldwide in 2022.

Doctors currently estimate heart disease risks using traditional indicators such as age, blood pressure, smoking habits and family history.

However, researchers say these methods often fail to detect subtle biological changes that emerge years before disease develops.

AI system studies proteins, metabolism and real-time body changes

The HKUMed research team used deep learning technology to combine genomics, proteomics and metabolomics into one integrated prediction model.

Researchers analysed 2,920 circulating proteins and 168 blood metabolites using population data from the UK Biobank.

Scientists described these molecular signals as “real-time recorders” of the body because they capture ongoing changes linked to metabolism, immunity and vascular health.

Qingpeng Zhang, Associate Professor in the Department of Pharmacology and Pharmacy at HKUMed, said the technology offers a more dynamic picture of human health than traditional genetic screening alone.

“Genes determine where we start. They define our baseline health risk,” Zhang explained.

“However, proteins and metabolites reflect our current physical health.”

“Our AI tool is designed to decode these complex molecular signals, enabling doctors and patients to identify risks much earlier, which can potentially change the trajectory of disease through timely lifestyle modifications and early prevention,” he added.

Researchers said the system significantly outperformed conventional polygenic risk scores when combined with clinical information such as age and gender.

Scientists say precision medicine is entering a new era

The study also highlights a broader shift in precision medicine away from purely gene-based risk assessments.

Unlike genetic risk, which largely remains fixed throughout life, molecular signals captured through blood testing can change in response to lifestyle, diet, stress and environmental conditions.

Scientists believe this makes multiomics-based systems more effective for monitoring real-time health changes.

Researchers said future health screenings could eventually use small blood samples to generate broad cardiovascular risk profiles covering multiple diseases simultaneously.

Professor Zhang said the team hopes the technology will support earlier medical intervention and better public health outcomes.

“We aim to leverage technology to identify and prevent diseases before they develop,” he said.

“By shifting health management from reactive treatment to proactive prediction and intervention, we aim to create a lasting impact for both public health and individual patient care.”

The research received support from the Research Grants Council of Hong Kong, the University of Hong Kong and China’s National Natural Science Foundation.