2024 ABCP Annual Conference: Life Sciences and Health

Abstract:

Professor Gary Tse, MEASA, BA (Hons. Cantab.), MBBS (Imperial), MA. (Dubl.), MD (Cantab.), DM (Oxon.), PhD (Cantab.), FFPH, FRCP, FRCPath

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 rare congenital heart diseases of Brugada syndrome and long QT syndrome using population-based datasets.
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.

Bio:

Prof. Gary Tse matriculated at Trinity Hall, University of Cambridge in 2005 to read pre-clinical medicine. He subsequently completed his clinical training at Imperial College London, as well as PhD and MD from the University of Cambridge. He is Associate Dean (Innovations and Research) at the School of Nursing and Health Studies, Hong Kong Metropolitan University (HKMU). He is also a Professor at the Department of Cardiology, Second Hospital of Tianjin Medical University, China 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 serves as a Nucleus Committee Member of the Population Health Section, European Association of Preventive Cardiology. He is a Fellow of the Faculty of Public Health, Royal College of Pathologists and Royal College of Physicians, and an elected Member of the European Academy of Sciences and Arts (Class II: Medicine). 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 26th on the Top Cardiovascular Researchers from China in 2023. He has delivered more than 70 lectures as Faculty in international conferences, has an H-index of 59 and has obtained more than HK$94 million research-related funding. He leads the Hong Kong Risk Modelling Team focusing on the use of big data and artificial intelligence for cardiovascular risk prediction.

Bio:

Dr Xin Li, University of Leicester

Dr Xin Li obtained BEng in Electrical Information Engineering from the University of Science and Technology Beijing 2011 and MSc in Electrical Electronic Engineering from the University of Leeds in 2012. He has been awarded his PhD in Biomedical Engineering from the University of Leicester in 2016. He was appointed as Research Associate from 2016 and promoted to Lecturer in 2019 at Departments of Cardiovascular Sciences and Engineering, University of Leicester, UK. His research focused on using advanced signal processing and mathematical intelligent algorithms for improving target identification for catheter ablation during human persistent atrial fibrillation and better risk assessment for sudden cardiac death. He serves as the associated editors for Biomedical Signal Processing and Control and reviewers of several high impact journals (IEEE Trans, Mbec, CirC EP etc.) and guest editor of Frontiers in Physiology.

Bio:

Chandini Subramanyam, University of Leicester

Chandini is a 2nd year PhD student in the Population Health Sciences department at the University of Leicester. Her research interests include global mental health, health inequity, and supporting family carers. Her PhD aims to understand how communities can better support ethnically diverse, young adult family carers. Her PhD is a collaboration between the University of Leicester and the LOROS Hospice Centre for Excellence. Chan is also the College of Life Sciences student representative and co-chairs the Student Voice committee and the College’s Race and Ethnicity committee.