Researchers at the University of Hong Kong’s LKS School of Medicine (HKUMed) have developed an artificial intelligence tool that could help predict serious cardiovascular problems years before symptoms appear.
The system, known as CardiOmicScore, uses information from a single blood test to estimate a person’s future risk for six major cardiovascular diseases (CVD): coronary artery disease, stroke, heart failure, atrial fibrillation, peripheral artery disease, and venous thromboembolism. The model was able to detect warning signals 15 years before clinical symptoms develop in high-risk people.
The survey results are nature communications.
Blood test to understand your current health condition
Cardiovascular disease remains the leading cause of death worldwide, accounting for approximately 19.8 million deaths in 2022 alone.
Doctors usually assess cardiovascular risk by testing factors such as age, blood pressure, smoking history, and other standard clinical measurements. Although these indicators are useful, they may not reveal the earliest biological changes occurring in the body before disease becomes apparent.
As a result, some people may not be identified as being at high risk until the best opportunities for prevention have already begun to narrow.
Genetic risk testing provides another way to estimate a person’s likelihood of developing a disease. For example, polygenic risk scores combine the effects of many genetic variations into a single measure of genetic risk. However, a person’s genetic makeup is largely fixed at birth.
This means that genetic scores cannot fully reflect more direct changes caused by diet, exercise, aging, disease, environmental exposures, or other effects on health.
CardiOmicScore is designed to give you a more up-to-date picture of what’s happening inside your body.
AI combines thousands of biosignals
To build this tool, the HKUMed team used deep learning to combine several layers of biological information. This approach is known as multi-omics because it integrates data from different fields of biology, such as genomics, metabolomics, and proteomics.
Genomics examines genetic information. Proteomics focuses on proteins that perform many important functions in the body. Metabolomics studies small molecules called metabolites that are produced when the body processes food, produces energy, and responds to disease.
Researchers analyzed large-scale population data from the UK Biobank. Their model examined 2,920 circulating proteins and 168 metabolites measured in blood samples.
Together, these molecules can provide a detailed snapshot of a person’s current biological state. These may reflect subtle changes in immune activity, metabolism, and vascular health before significant symptoms develop.
Zhang, an associate professor in the Department of Pharmacology and Pharmacy at HKUMed. Professor Qingpeng said: “Genes determine where we start and define our baseline health risks. But proteins and metabolites are designed to reflect our current physical health. Our AI tools… “It is designed to decipher these complex molecular signals, allowing doctors and patients to identify risks earlier, potentially changing the trajectory of the disease through timely lifestyle modifications and early prevention.”
Predict 6 cardiovascular diseases
Results showed that CardiOmicScore can turn complex molecular measurements into personalized estimates of cardiovascular risk.
This system performed significantly better than traditional polygenic risk scores. When researchers added clinical information such as age and gender, the accuracy improved even more.
This model was designed to assess the risk of coronary artery disease, stroke, heart failure, atrial fibrillation, peripheral artery disease, and venous thromboembolism.
Atrial fibrillation is an irregular heartbeat that can increase your risk of stroke and other complications. Peripheral artery disease occurs when blood vessels narrow, reducing circulation to the extremities. Venous thromboembolism refers to a dangerous blood clot that forms in a vein and can travel to the lungs.
In high-risk individuals, CardiOmicScore can warn of increased cardiovascular risk up to 15 years before symptoms appear.
From treatment to early prevention
This research reflects broader changes in precision medicine.
Traditional genetic approaches yield relatively fixed estimates of genetic risk. Multi-omics tools have the potential to provide more dynamic assessments by tracking biological signals that change over time.
In the future, it may be possible to use small blood samples to create detailed risk profiles covering multiple cardiovascular diseases at once. This information gives patients and doctors more time to make adjustments such as lifestyle changes, close monitoring, and other preventive measures.
Professor Chan added: “We aim to leverage technology to identify and prevent diseases before they occur. By moving health management from reactive treatment to proactive prediction and intervention, we aim to create a lasting impact on both public health and individual patient care.”
About the research team
The research was led by Professor Zhang Qingpeng, Associate Professor in the School of Pharmacology and Pharmaceutical Sciences at the University of Hong Kong, and the Hong Kong Musketeers Foundation Institute for Data Science (IDS).
The first author is Luo Yan from HKU IDS.
