Prof. Gary TSE | Symposium Speakers | Hong Kong Metropolitan University

Prof. Gary Tse is Associate Dean (Innovations and Research) at the School of Nursing and Health Sciences, Hong Kong Metropolitan University (HKMU), and a Visiting Professor at the Faculty of Health and Medical Sciences, University of Surrey. Prior to joining HKMU, Prof. Tse held a joint position as Clinical Reader at the University of Kent (with permanent appointment until the retirement age) and Honorary Public Health Consultant at the Medway Council in local government, UK.

He is a Fellow of the Faculty of Public Health, Royal College of Pathologists and Royal College of Physicians. He serves as a Nucleus Committee Member of the Population Health Section, European Association of Preventive Cardiology (EAPC), where he is deputy representative for the Accreditation subcommittee and Certification subcommittee.

He leads the Hong Kong Risk Modelling Team focusing on the use of big data and artificial intelligence for cardiovascular risk prediction. For his big data research, he was elected a Member of the European Academy of Sciences and Arts (Class II: Medicine) and an invited faculty for the Association of British Chinese Professors Annual Conference 2024 and the EAPC Congress 2025. He has been listed on the World’s Top 2% Scientists Released by Stanford University for the Cardiovascular System & Hematology subfield since 2020 and is ranked 26^th on the Top Cardiovascular Researchers from China in 2023. He was listed by Expertscape in 2024 as Top Expert in electrocardiography (0.023%, 1^st in China, 4^th in Asia and 30^th Worldwide) and cardiac arrhythmias (0.073%, 5^th in China and 15^th in Asia). Altogether, he has delivered more than 70 lectures as Faculty in international conferences, has an H-index of 63 and has obtained more than HK$168 million research-related funding.

Healthcare Big Data: a Showcase from PowerAI-CVD, a Chinese-specific Artificial Intelligence-powered Predictive Model for Cardiovascular Disease

Routinely collected electronic health records (EHRs) data contain a vast amount of valuable information for conducting epidemiological studies. With the right tools, we can gain insights into disease processes and development, identify the best treatment and develop accurate models for predicting outcomes. Our recent systematic review has found that the number of big data studies from Hong Kong has rapidly increased since 2015, with an increasingly common application of artificial intelligence (AI). The advantages of big data are that i) the models developed are highly generalisable to the population, ii) multiple outcomes can be determined simultaneously, iii) ease of cross-validation by for model training, development and calibration, iv) huge numbers of useful variables can be analyzed, v) static and dynamic variables can be analysed, vi) non-linear and latent interactions between variables can be captured, vii) AI approaches can enhance the performance of prediction models. Our team has developed risk models for common non-communicable diseases such as cardiovascular disease (CVD) and diabetes mellitus, as well as disease-specific models for preventing adverse cardiovascular events.

In this presentation, we will showcase using PowerAI-CVD, a Chinese-specific artificial intelligence-driven predictive model for CVD. This will illustrate our collaborative efforts between clinicians, data scientists and statisticians in utilising multi-modality data. In the form of dashboards, unique features include real-time trends analysis and risk updates using newly accumulated data from ongoing testing. AI-driven models outperform traditional models in terms of sensitivity, specificity, accuracy, area under the receiver operating characteristic and precision-recall curve, and F1 score. Web and/or mobile versions of the risk models allow clinicians to risk stratify patients quickly in clinical settings, thereby facilitating decision-making. Efforts are required to identify the best ways of implementing AI algorithms on the web and mobile apps. In conclusion, the benefits of a big data approach are that only routinely collected EHR data are required for developing high-performance predictive models.