Researchers at the University of Hong Kong have developed the CardiOmicScore tool, which allows early detection of cardiovascular diseases through a blood test. This test can identify the risk of six major cardiovascular conditions.

The study, published in Nature Communications, notes that the tool can reveal conditions such as coronary artery disease, stroke, heart failure, atrial fibrillation, peripheral artery disease and venous thromboembolism.

Professor Zhang Qingpeng highlights that the tool can detect warning signs up to 15 years before symptoms appear. Its incorporation into medical practice could transform current approaches towards prevention.

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

Comparison with genetic tests

Unlike genetic testing, which provides a static assessment of DNA-based risk, CardiOmicScore measures current physical status, reflecting how changes in diet and lifestyle may influence cardiovascular risk.

"This research offers an exciting glimpse into the future of cardiovascular prevention," Rick Snyder, board-certified advanced interventional cardiologist and president of HeartPlace Cardiology, told Newsweek. “By using AI to interpret thousands of proteins and metabolites circulating in the blood, CardiOmicScore could help doctors recognize biological warning signs years before a patient develops symptoms,” he added.

Despite its promise, the tool has not been independently validated and should be considered a complement, not a substitute, to traditional risk assessments. Experts stress the need for rigorous development and clinical testing before widespread implementation.

Comparison with other tests

CardiOmicScore is a multi-task deep learning model developed by researchers at the University of Hong Kong (HKUMed) that integrates genomics, proteomics and metabolomics data from a single blood test.

Comparison with other available tests:

Polygenic risk scores (PRS)

Polygenic risk scores combine multiple genetic variants to estimate hereditary risk, but have important limitations:

Framingham Score and other clinical models

The Framingham score and similar tools are based on conventional clinical risk factors (age, blood pressure, cholesterol, smoking, etc.):

Traditional individual biomarkers

Tests such as troponin, B-type natriuretic peptide (BNP), or C-reactive protein (CRP) measure specific markers: