New AI Blood Test Can Predict Heart Disease Risk 15 Years Early

(WS News) – Researchers at the University of Hong Kong have developed an AI-powered blood test that can flag a person’s risk of major cardiovascular disease up to 15 years before symptoms appear, according to findings published in the journal Nature Communications.

The tool, called CardiOmicScore, uses a single blood sample and deep learning to analyze thousands of proteins and metabolites, estimating a person’s risk of six major cardiovascular conditions including coronary artery disease, stroke, heart failure and atrial fibrillation. Unlike genetic risk scores, which stay fixed over a lifetime, the system captures real-time biological changes tied to a person’s current health, lifestyle and environment.

The research team, led by Professor Zhang Qingpeng of the university’s pharmacology and pharmacy department, built the model using large-scale population data from the UK Biobank, analyzing 2,920 circulating proteins and 168 metabolites from participants’ blood samples. “Genes determine where we start — they define our baseline health risk,” Zhang said. “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.”

Cardiovascular disease remains the leading cause of death worldwide, responsible for roughly 19.8 million deaths in 2022 alone. Outside experts have welcomed the research, with one cardiologist telling reporters the tool “may eventually help physicians recognize biological warning signs years before a patient develops symptoms.” The researchers say the approach performed substantially better than conventional polygenic risk scores when combined with basic clinical details such as age and gender, though the tool has not yet been deployed in routine clinical practice.

This is a sensitive health topic; readers with specific medical concerns should consult a qualified healthcare provider.