Researchers at the University of Hong Kong’s LKS Faculty of Medicine have developed an AI-powered tool that can estimate future cardiovascular disease risk through a single blood test. The tool, called CardiOmicScore, can predict the risk of six major cardiovascular diseases: coronary artery disease, stroke, heart failure, atrial fibrillation, peripheral artery disease, and venous thromboembolism. The findings were published in Nature Communications.

Researchers at the University of Hong Kong’s LKS Faculty of Medicine have developed an AI-powered tool that can estimate future cardiovascular disease risk through a single blood test.

The tool, called CardiOmicScore, can predict the risk of six major cardiovascular diseases: coronary artery disease, stroke, heart failure, atrial fibrillation, peripheral artery disease, and venous thromboembolism. The findings were published in Nature Communications.

According to HKUMed, CardiOmicScore can provide warning signals up to 15 years before the clinical onset of disease.

The system is designed to detect molecular changes in the body before symptoms appear. This could help doctors and patients identify risk earlier and take preventive steps before the disease develops.

The research team used deep learning to combine multiomics data, including genomics, metabolomics, and proteomics.

The study used large-scale population data from the UK Biobank and analyzed 2,920 circulating proteins and 168 metabolites measured from blood samples. These molecular signals can reflect changes in the immune system, metabolism, and vascular health.

Professor Zhang Qingpeng, Associate Professor in the Department of Pharmacology and Pharmacy at HKUMed, said genes define a person’s baseline health risk, while proteins and metabolites show current physical health.

He said the AI tool is designed to decode these molecular signals so doctors and patients can identify risks earlier and support timely lifestyle changes and prevention.

Standard health checks usually estimate cardiovascular risk through factors such as age, blood pressure, smoking, and other clinical indicators.

However, these checks may miss early biological changes before the disease becomes visible. Polygenic risk scores can also help, but genetic risk is mostly fixed from birth and does not show the impact of changing lifestyle or environmental factors.

The researchers said CardiOmicScore performed better than conventional polygenic risk scores. When combined with clinical details such as age and gender, the model improved prediction accuracy for all six cardiovascular diseases.

The study points to a shift in precision medicine from fixed genetic risk models to more dynamic tools that reflect a person’s current biological condition.

In the future, a small blood sample could help create a broad cardiovascular risk profile for multiple diseases.

Professor Zhang said the goal is to use technology to identify and prevent diseases before they develop, moving healthcare from reactive treatment to proactive prediction and intervention.

📢 For the latest Tech & Telecom news, videos and analysis join ProPakistani's WhatsApp Group now!

Follow ProPakistani on Google News & scroll through your favourite content faster!