Health Data Science MSc

Program Overview

This Master's program equips students with skills in artificial intelligence, clinical sciences, and biomedicine to navigate the intersection of these fields. The program emphasizes health data science techniques for improving patient outcomes and optimizing medical procedures, catering to students from diverse backgrounds in biomedical, computer science, and public health domains.

Program Outline

Degree Overview:

This Masters programme takes you into the fascinating world of cutting-edge technology, health data, and the limitless potential of artificial intelligence. The programme is designed to prepare you for a career in industry or academia at the intersection of AI, clinical sciences, and biomedicine. Health data science is transforming the healthcare landscape by harnessing the power of data to improve patient outcomes and optimize medical procedures. It enables evidence-based decision-making, empowers healthcare professionals, and contributes to the development of innovative treatments and personalized medicine. The demand for health data scientists is experiencing exponential growth, driven by the ever-increasing volume and complexity of health data. In recent years, we have transitioned from facing a shortage of data to having shortage in experts who can effectively analyse this wealth of information. In this dynamic programme, we'll equip you with the expertise and tools needed to unravel the potential of health data and how it can transform medicine. You will learn how to use advanced computational techniques to unlock new frontiers in clinical and biomedical research and be at the forefront of innovation in this rapidly evolving field. Our students come from diverse backgrounds from the biomedical and medical domains, including clinical trainees, as well as individuals with expertise in computer science, mathematics, and statistics. Additionally, we welcome students from public health, epidemiology, and biotechnology/engineering disciplines, fostering a rich and multidisciplinary learning environment.

Outline:

• Delivery: This course is delivered in the evenings and on weekends.
• Modules:
• Foundations of Computing Practices in Health Data Science (20 credits):
This module covers the fundamentals of health data management, extraction, and manipulation using Python programming. It also introduces students to data visualisation techniques for health data analytics.
• Essentials of Mathematics and Statistics (20 credits): This module provides an introduction to essential quantitative theory in health data science.
It covers concepts through a series of core problems, which will be explored in more detail in later modules. The quantitative topics include Probability Theory, Descriptive Statistics, Hypothesis Testing, and an introduction to Statistical Modeling using the R programming language, including linear models and estimation.
• Data Analytics & Statistical Machine Learning (20 credits): The aim of this module is to provide a comprehensive understanding of the current advancements in data integration, mining, and analysis, with a focus on applications in health data science and biomedicine.
The topics covered include various aspects of data, such as data types, data modelling, data management, integration techniques, as well as supervised and unsupervised machine learning models and validation approaches. It covers data governance, ethical implications, patient and public involvement, and informed consent. Additionally, it introduces the fundamentals of various -omics and genetics fields and their role in revealing disease pathobiology and implications in personalised medicine. It covers topics such as descriptive epidemiology, measures and comparisons of disease occurrence (incidence, prevalence), and various study designs in epidemiology, including ecological studies, cross-sectional studies, case-control studies, cohort studies, and randomised controlled trials.
• Integrative Multimodal Data Analytics (20 credits): This module builds upon previous modules and covers advanced topics in health data science.
It introduces image analysis, electronic health records data, longitudinal modelling, and integration with multi-omics datasets. The module also explores advanced modelling methods, including deep neural networks and omics fusion strategies.
• Interdisciplinary Health Data Research Project (60 credits): The dissertation module offers students the opportunity to demonstrate their acquired knowledge and skills from the taught modules.
Dissertations must include a computational work in the health data field, and students are encouraged to select their own topics with the guidance of a supervisor. Successful dissertations delve deeply into a health data subject, posing clear research questions, employing suitable methodology, and critically analysing the results.

Assessment:

You will be assessed through a variety of methods, including essays, exams, oral presentations, computer-based problem solving exercises and a thesis.

Teaching:

• Faculty:
• Programme Deputy Director: Dr Animesh Acharjee, Assistant Professor of Integrative Analytics and AI.
• Teaching Methods: The course is delivered through a combination of evening and weekend classes.
Each module is block taught over 2 weeks.

Careers:

This programme will give you clear and compelling experience of working across academic, healthcare and industry sectors, with extensive supervisory and mentoring arrangements to maximise your exposure to these environments. Not only will this prepare you mentally and practically, it will also help identify specific opportunities and contacts for progress into relevant career pathways.

Other:

• Subject to Ministry of Education accreditation
• The MSc Health Data Science programme offers you the opportunity to:
• Learn about the dynamic, collaborative, and interdisciplinary healthcare ecosystem that spans academia and industry.
• Develop a profound comprehension of healthcare systems, their ethical underpinnings, and the intricacies of governance.
Learn about the present and prospects of health data science and its role in personalised medicine.
• Recognize the transformative potential of health data science skills in reshaping healthcare data and unlocking the power of patient-specific information including genomics.
These capabilities are driving advancements in research, clinical care, and fostering innovation in the 21st century.
• Grasp the significance of diverse health information sources, systems, integration methods, and the role of information technologies in healthcare delivery.
• Acquire hands-on experience working in diverse, multi-disciplinary healthcare environments and related research.
• Enhance your communication and delivery skills within the broader healthcare landscape.