Skip to Content Facebook Feature Image

HKUMed develops innovative AI tool: a single blood test can predict heart diseases up to 15 years before onset

HK

HKUMed develops innovative AI tool: a single blood test can predict heart diseases up to 15 years before onset
HK

HK

HKUMed develops innovative AI tool: a single blood test can predict heart diseases up to 15 years before onset

2026-03-12 12:15 Last Updated At:12:34

A research team from the Department of Pharmacology and Pharmacy at the LKS Faculty of Medicine of the University of Hong Kong (HKUMed) has developed an innovative AI-based cardiovascular risk prediction tool, called CardiOmicScore. With a single blood test, the system can accurately forecast the future risk of six major cardiovascular diseases (CVDs): coronary artery disease, stroke, heart failure, atrial fibrillation, peripheral artery disease and venous thromboembolism. It can also provide early warning signals up to 15 years before clinical onset. The findings were published in Nature Communications [link to the publication].

HKUMed develops a cardiovascular risk prediction tool that can accurately predict the future risk of six major cardiovascular diseases with a single blood test. The system can provide early warning signals up to 15 years before clinical onset. The research is led by Professor Zhang Qingpeng (left).

HKUMed develops a cardiovascular risk prediction tool that can accurately predict the future risk of six major cardiovascular diseases with a single blood test. The system can provide early warning signals up to 15 years before clinical onset. The research is led by Professor Zhang Qingpeng (left).

AI-based multiomics integration reflects the body’s real-time health status

CVDs remain the leading cause of death worldwide, accounting approximately 19.8 million fatalities in 2022 alone. In routine health assessments, physicians typically evaluate cardiovascular risk based on age, blood pressure, smoking and other conventional clinical indicators. However, these measures often fail to capture subtle and early biological changes before the disease becomes clinically apparent, leading to many patients missing the optimal window for preventive intervention. Although polygenic risk scores have become popular in recent years, genetic predisposition is largely fixed at birth and does not change over time. Consequently, polygenic risk scores cannot reflect the immediate impact on health conditions resulting from lifestyle or environmental changes. This creates an urgent need for tools that can capture a person’s current biological state and provide accurate, early warnings for CVDs.

To address this problem, the HKUMed research team applied deep learning techniques to integrate multiomics data, including genomics, metabolomics and proteomics, to develop the CardiOmicScore tool. The study was based on large-scale population data from the UK Biobank, analysing 2,920 circulating proteins and 168 metabolites measured from blood samples. These molecular signals act as ‘real-time recorders’ of the body, sensitively reflecting subtle changes in the immune system, metabolism, and vascular health.

Professor Zhang Qingpeng, Associate Professor in the Department of Pharmacology and Pharmacy at HKUMed, explained, ‘Genes determine where we start—they define our baseline health risk. 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, which can potentially change the trajectory of disease through timely lifestyle modifications and early prevention.’

Accurate prediction of six major cardiovascular diseases with 15-year advance warning in high-risk groups

The results showed that CardiOmicScore transforms complex multiomics measurements into personalised risk scores with substantially improved predictive performance compared with conventional polygenic risk scores. When combined with clinical information such as age and gender, the model significantly enhanced the risk prediction accuracy of six common CVDs and can even flag elevated risk up to 15 years before symptoms appear.

This study marks a shift in precision medicine from a static, gene-centric paradigm towards a more dynamic, multiomics-based approach. In the future, a small-volume blood sample may be sufficient to generate a comprehensive cardiovascular risk profile for multiple diseases.

Professor Zhang added, ‘We aim to leverage technology to identify and prevent diseases before they develop. By shifting health management from reactive treatment to proactive prediction and intervention, we aim to create a lasting impact for both public health and individual patient care.’

About the research team

The study was led by Professor Zhang Qingpeng, Associate Professor in the Department of Pharmacology and Pharmacy, HKUMed, and the HKU Musketeers Foundation Institute of Data Science (IDS). The first author is Luo Yan from the HKU IDS.

Lung cancer is one of the most common cancers in Hong Kong and carries the highest mortality rate, not only locally but also globally. Professor Rina Hui, Director of the Centre for Cancer Medicine at the University of Hong Kong (HKU), said that cancer treatment is advancing at an unprecedented pace, with new breakthroughs emerging almost every fortnight. These include antibody-drug conjugates (ADCs) that are often referred to as "smart chemotherapy", T-cell engagers, and bispecific antibodies, which combine two different antibodies.

With such rapid progress, the curriculum at HKU’s Li Ka Shing Faculty of Medicine (HKUMed) needs to keep pace. About a year and a half ago, the faculty launched an eight-month integrated cancer medicine course to equip medical students with the latest clinical cancer technologies.

Professor Rina Hui, Director of the Centre for Cancer Medicine at the University of Hong Kong (HKU), Photo by Bastille Post

Professor Rina Hui, Director of the Centre for Cancer Medicine at the University of Hong Kong (HKU), Photo by Bastille Post

Professor Hui told Bastille Post that, in Hong Kong, besides lung cancer, the most common cancers include colorectal, breast, and prostate cancer. But lung cancer remains the biggest challenge, since its mortality rate is higher than the other three combined.

She said that besides smoking, other risk factors for lung cancer include second‑hand smoke, the second largest contributor, as well as family history, air pollution, kitchen fumes, occupational exposure (e.g., asbestos and radon), and prior radiotherapy. Smoking, however, remains by far the leading cause.

EGFR Mutations Common in HK Lung Adenocarcinoma

Professor Hui noted that Hong Kong's smoking rate has dropped to 8.5%, according to the latest figures released by the Health Bureau in April. While smoking‑related cancers like small cell lung cancer and squamous cell carcinoma are declining, lung adenocarcinoma is increasing, with half of patients carrying EGFR mutations. "Knowing the cancer type and genetic status is the first step for effective treatment," she said.

She also emphasised that the earlier one quits smoking, the lower the risk of getting cancer. "Quitting need not be abrupt. Nicotine patches and chewing gum can serve as supportive aids. The essential step is to discard all cigarettes, eliminate temptation, and reframe quitting as a long‑term health investment," she advised.

Professor Hui suggested that lung cancer screening is essential for high‑risk individuals. Photo source: reference image

Professor Hui suggested that lung cancer screening is essential for high‑risk individuals. Photo source: reference image

Lung Cancer Screening: Essential for High‑Risk Individuals

Last year, the government announced plans to commission local universities to conduct AI‑assisted lung cancer screening. Professor Hui said that HKU and CUHK are currently running relevant trials, given their importance.

"High‑risk people, like those aged 50 to 75, heavy smokers (30 pack‑years), and those exposed to second‑hand smoke, should get screened regularly," she said. "Taiwan offers a noteworthy approach, where they screen non‑smokers with a family history of lung cancer."

She acknowledged that free lung cancer screening for every individual in Hong Kong is unlikely to be feasible at this stage, due to the high costs involved. However, screening could be carried out through collaboration between the government and private healthcare providers, targeting high‑risk groups. "As I tell my patients, getting screened is like saving up to pay taxes. You're actually gaining in the long run. Early detection means better outcomes and lower treatment costs."

She said that lung cancer treatment regimens are becoming increasingly advanced. "Patients with genetic alterations can use targeted therapies; those without can benefit from immunotherapy, and survival rates have improved significantly." However, she also pointed out that lung cancer remains the world's "number one cancer killer", underscoring the urgent need for continued related research and clinical trials.

Recognising the rapid evolution of cancer treatment, HKUMed has launched an eight‑month integrated cancer medicine course starting in October 2024. Photo source: reference image

Recognising the rapid evolution of cancer treatment, HKUMed has launched an eight‑month integrated cancer medicine course starting in October 2024. Photo source: reference image

New Course to Train Future Doctors

Recognising the rapid evolution of cancer treatment, HKUMed has launched an eight‑month integrated cancer medicine course starting in October 2024, which is delivered in six cohorts per year, ensuring that future doctors stay abreast of the latest developments. "We bring together surgeons, researchers, public health experts, oncologists (including medical oncologists and radiation oncologists), pathologists, and radiologists to teach medical students the basics of immunotherapy, targeted therapies, smart chemotherapy, and radiation, so that no matter what field they go into, they'll be able to handle cancer patients when they see them," she said.

New Cancer Treatments Bring New Hope

Beyond well‑established immunotherapy, Professor Hui highlighted emerging treatments:

One is called Antibody‑Drug Conjugate (ADC), often referred to as "smart chemotherapy" or "missile‑guided chemotherapy." "The antibody carries the chemotherapy drug, entering cancer cells with precision like a missile. When the linker dissolves, it releases the drug directly into the cancer cells, killing them effectively," she explained.

She noted that ADCs have now been proven to benefit patients with stage IV metastatic cancer. Clinical trials are currently combining these drugs with immunotherapy, and data have already shown effectiveness in early‑stage triple‑negative breast cancer patients.

Another future trend in cancer treatment is bispecific antibodies, which combine two different antibodies with fewer side effects and a synergistic effect. For example, VEGF bispecific antibodies combine the dual mechanisms of immune checkpoint inhibitors and anti‑angiogenic therapy, and have already shown effectiveness in cancers such as lung and breast cancer. Combining two targeted drugs also results in fewer side effects and better treatment outcomes for lung cancer patients.

T‑Cell Engagers: A Breakthrough for Small Cell Lung Cancer

Professor Hui also mentioned a new treatment trend called T-cell engagers. "For example, a therapy targeting DLL3 on the surface of small cell lung cancer cells — on one side, it targets DLL3, and on the other side, it attracts the immune system's T-cells, which act like soldiers attacking the cancer cells together. This type of drug is already on the market and has been shown to improve overall survival in extensive-stage small-cell lung cancer. Clinical trials are currently exploring its use in first-line treatment and for stage III patients," she explained.

However, she pointed out that targeted therapy remains a future priority. Since many cancers occur due to genetic alterations, if the genes driving cancer growth can be identified, targeted medications can be utilized and show improved therapeutic efficacy across various cancers. For example, 60% to 70% of breast cancers are hormone receptor-positive, and of those, 30% to 40% have PIK3CA gene mutations. "The corresponding targeted drugs are currently available in Hong Kong, but they are expensive. There is now a phase III clinical trial in which patients can use this type of medication for free, and may even have access to better new drugs. However, patients need to undergo genetic sequencing to confirm whether they have the corresponding genetic mutation before they can participate in the relevant trial," she said.

According to Professor Hui, since many cancers occur due to genetic alterations, if the genes driving cancer growth can be identified, targeted medications can be utilized and show improved therapeutic efficacy across various cancers. Photo by Bastille Post

According to Professor Hui, since many cancers occur due to genetic alterations, if the genes driving cancer growth can be identified, targeted medications can be utilized and show improved therapeutic efficacy across various cancers. Photo by Bastille Post

Recommended Articles