AI Blood Test Predicts Heart Disease Up to 15 Years Before Symptoms
HKU researchers built CardiOmicScore, an AI tool that uses a single blood test to flag six cardiovascular diseases up to 15 years before onset.
In Brief
- CardiOmicScore uses a single blood test to predict six cardiovascular diseases
- It can flag elevated risk up to 15 years before symptoms appear
- The tool was developed by researchers at the University of Hong Kong
Researchers at the University of Hong Kong have built an AI tool that can predict a person’s risk of six major cardiovascular diseases from a single routine blood test — and flag it up to 15 years before any symptoms appear.
The system, called CardiOmicScore, was reported by ScienceDaily, which explains that “the system, known as CardiOmicScore, uses information from a single blood test to estimate a person’s future risk” of coronary artery disease, stroke, heart failure, atrial fibrillation, peripheral artery disease, and venous thromboembolism.
The underlying research comes from HKUMed. In its press release, the university says it “develops a cardiovascular risk prediction tool that can accurately predict the future risk of six major cardiovascular diseases with a single blood test” and “can provide early warning signals up to 15 years before clinical onset.”
Independent coverage confirms the finding. MedicalXpress reports “a single blood test can predict heart diseases up to 15 years before onset,” noting that when combined with age and gender the model significantly improves risk prediction across the six conditions.
How CardiOmicScore works
CardiOmicScore analyzes molecular signals already present in standard blood work rather than requiring new, expensive scans. By learning patterns across many biomarkers, the model estimates the trajectory of cardiovascular risk decades ahead of a clinical event. Kimi China Open-Weight
The six diseases it covers are among the leading causes of death worldwide. Catching them early matters because interventions — diet, medication, monitoring — are far more effective before damage accumulates, and a 15-year lead time is unusual for a non-invasive screening tool. Qualcomm Bets Wearables
HKUMed frames the tool as a population-scale early-warning system. Because it relies on a blood test many people already get, it could be deployed widely through existing primary-care pathways rather than specialist cardiology clinics.
What early prediction means for patients
For individuals, an earlier risk signal translates into more time to act. A person flagged in their forties could begin targeted prevention well before a heart attack or stroke would otherwise appear.
For health systems, the appeal is cost and triage: scarce cardiology resources can be aimed at those the model identifies as highest risk, while lower-risk patients avoid unnecessary testing. The trade-off is the familiar one of any predictive screen — false alarms and anxiety must be managed carefully.
The research also points to a broader trend in AI diagnostics: models that turn cheap, routine data into long-horizon forecasts. If validated at scale, CardiOmicScore could become a template for predicting other chronic diseases from tests patients already take.
FAQ
What is CardiOmicScore?
CardiOmicScore is an AI tool from the University of Hong Kong that uses a single blood test to estimate future risk of six major cardiovascular diseases.
How early can it predict heart disease?
HKUMed says the tool can provide early warning signals up to 15 years before clinical onset of disease.
Which diseases does it cover?
It covers coronary artery disease, stroke, heart failure, atrial fibrillation, peripheral artery disease, and venous thromboembolism.
