91³ÉÈ˰涶Òô

Ìý

Course

Ìý

Session Dates

Ìý

Context of Health Data Science

Ìý

This course provides an introduction to how data are generated and used in a contemporary health system. We look at how health outcomes can be measured and reported in various forms of health data, and how these health data can reveal inequalities in health. The course describes the major sources of health data, including those relating to primary care, hospital stays and prescription medicines, and how this (and other) information can be used by the health data scientist to create evidence for policy and research.Ìý

Activities are structured to foster a scientific, questioning attitude in the student. Students are encouraged to think critically about how health data are recorded, what this reveals about the underlying health delivery systems, and be creative in their use of health data sources to create or critically appraise evidence.

Pre-requisites: none

Software used: none

Ìý

Registration Open

Ìý

Term 1(F2F & online):

Ìý

Ìý

Ìý

Statistical Foundations for Health Data Science

Ìý

Almost all aspects of health data science, from the most basic descriptive analyses through to the development of the most sophisticated deep learning models, are built on a set of foundation statistical concepts and principles, encompassing both frequentist and Bayesian paradigms.

The course will provide the student with a thorough understanding of

the Law of Large Numbers and the Central Limit Theorem, probability distributions, likelihood and likelihood estimation, Bayes theorem and Bayesian estimation, Monte Carlo methods and resampling methods such as the bootstrap, frequentist inference, and essential epidemiological and study design concepts. The approach is highly computational. Rather than relying on mathematical proofs and theorems, students investigate and verify these concepts through simulations which they construct themselves, while simultaneously gaining proficiency in the widely-used, open-source R statistical programming language. The end result is a sound knowledge of statistical computing and good programming practice, allied to a hands-on understanding of the statistical underpinnings of both regression modelling and machine learning.

Pre-requisites: none

Software used: R

Ìý

Registration Open

Ìý

Term 1(F2F & online):

Ìý

Term 3(Online only):

Ìý

Ìý

Ìý

Management and Curation of Health Data

Ìý

This course is designed to equip students with the skills required to collect or obtain data, design data management strategies aligned with best practice, and appreciate the day to day practicalities of data curation for sound data management. Students will develop data wrangling skills required to assemble data suitable for analysis and research purposes, including data from linked data sources.

Data wrangling skills will focus on the key areas of data security, data exploration, documentation of data (for example data dictionaries) and data management, with the ultimate aim of creating analysis-ready datasets and ensuring reproducible results.

Pre-requisites: none

Software used: SAS

Ìý

Registration Open

Ìý

Term 2(Online only):Ìý

Ìý

Term 3(F2F & online):

Ìý

Ìý

Ìý

Computing for Health Data Science

Ìý

Computing now pervades nearly every aspect of modern life, including health care delivery and health services management. The objective of this course is to develop 'computational thinking' in health data science students, by providing them with a thorough and principled introduction to computer programming, algorithms, data structures and software engineering best practices. The ability to write clear, efficient and correct computer code is at the core of most data science practice, and is a foundation skill set.

Ìý

In this course, students will learn to program in the Python language through tackling health-related problems. Topics include data types, functions, data processing, simulation, software development and program testing and debugging. Theoretical principles are reinforced with extensive ‘hands-on’ coding in Python, including the NumPy package.

Pre-requisites: none

Software used: Python

Ìý

Registration Open

Ìý

Term 1(F2F & online):

Ìý

Term 3(F2F & online):

Ìý

Ìý

Ìý

Ìý

Visualisation and Communication of Health Data

Ìý

Health Data Scientists present information to audiences across a range of backgrounds, spanning a spectrum from naïve or non-practitioners of a discipline to highly informed and expert audiences. Effective communication across different media types is essential. Appropriate data visualisation techniques can greatly increase the effectiveness of communication. An understanding of some basic simple techniques can ensure communication remains effective across diverse audiences. An understanding of the computation and presentation aspects of health data visualisation can increase not only the effectiveness of communication but also the efficiency of work effort.

Ìý

This course takes a practical approach to creating appropriate, reproducible and transparent analyses and visualisations. Using R and RStudio, it develops useful data science analysis and visualisation techniques for different types of data visualisation and communication, including charts and graphs and written and oral communication forms. What makes a good map is discussed and the use of geospatial information is explored through the construction of an interactive Shiny application.

Pre-requisites: none

Software used: R, Git

Ìý

Registration Open

Ìý

Term 2(F2F & online):

Ìý

Ìý

Ìý

Ìý

Ìý

Ìý

Ìý

Ìý

Ìý

Health Data Analytics: Statistical Modelling I

Ìý

This course provides a sound grounding in the theory and practice of fitting statistical regression models, including linear models; generalised linear models (GLMs) for outcomes that are non-liner, binary or count; and survival analysis and time to event models. A major theme of the course is best practice in model fitting, including thorough exploratory data analysis, model assumption checking, data preparation and transformation, including the use of imputation, and careful attention to model adequacy and diagnostics. The presentation and visualisation of statistical models is considered, with emphasis on the explanatory insights that can be gained from well-constructed models.Ìý

Pre-requisites: Statistical Foundations for Health Data Science or equivalent

Software used: R, Git

Ìý

Registration Open

Ìý

Term 1(Online only):

Ìý

Term 2(F2F & online):

Ìý

Ìý

Ìý

Ìý

Health Data Analytics: Machine Learning I

Ìý

Machine learning and data mining bring together methods coming from statistics and computer science and apply these to databases both large and small. They use a powerful and diverse set of techniques and algorithms to discover patterns and relationships in data with the final goal of creating knowledge from these data. These methods are increasingly being applied to the vast amounts of health data that are generated through sources including electronic medical records, medical and pharmaceutical claims, medical imaging, wearable and implantable devices and social media.

Ìý

This course provides an introduction to data mining and machine learning, including both supervised and unsupervised techniques. You will learn about the underlying theory, as well as gain the practical know-how required to effectively apply these techniques to real-world health datasets to answer new health data science problems. The widely-used, open-source Python programming language is used to teach the course.

Pre-requisites: Statistical Foundations for Health Data Science or equivalent, and Computing for Health Data Science or equivalent

Software used: Python

Ìý

Registration Open

Ìý

Term 2(F2F & online):

Ìý

Ìý

Ìý

Ìý

Health Data Analytics: Statistical Modelling II

Ìý

SophisticatedÌýmodelling techniques are essential for the analysis of real-world health data. Building on Health Data Analytics: Statistical Modelling I, this course expands the statistical toolkit and broadens students' understanding of relevant statistical approaches for the analysis of realistically complex data structures and research questions. The course is aimed at those currently working or planning on working in health or a health-related field, and who are interested in applying advanced statistical methods to analyse complex data.

Ìý

Topics covered in this course include multilevel models for hierarchical data; analysis of time series and longitudinal data; methods for drawing causal inferences from observational data; and multiple imputation for missing values.

Ìý

Content is delivered through a combination of online readings, expert lectures and interactive tutorials. Statistical concepts are illustrated with a variety of health examples, and students will learn how to implement methods usingÌýleadingÌýstatistical software.

Pre-requisites: Health Data Analytics: Statistical Modelling I or equivalent

Software used: R, Git

Ìý

Registration Open

Ìý

Term 2(Online only):

Ìý

Term 3(F2F & online):

Ìý

Ìý

Health Data Analytics: Machine Learning II

Ìý

This course provides an introduction to

• Unsupervised and supervised deep learning techniques including autoencoders, variational autoencoders, recurrent neural networks and transformers
• Reinforcement learning

Students will learn about the underlying supporting theory of the above techniques, as well as gain the applied practical skills required to effectively apply these techniques to new health data problems.

This course is not only about algorithms and techniques, but also about posing the right questions, extracting reasonable conclusions and designing the process and steps that are followed from the beginning until the end of the health question.

Pre-requisites: Health Data Analytics: Machine Learning I or equivalentÌý

Software used: Python

Ìý

Registration Open

Ìý

Term 3(F2F & online):

Ìý

Clinical Artificial Intelligence

Ìý

The course will start by explainingÌýthe fundamental concepts of AI systems and what they can and cannot do. This will be followed by an examination of the idiosyncrasies of AI for healthcare practice covering electronic medical records data (including images, clinical notes, pathology and patient reported outcomes), clinical settings and workflows, as well as the ethical, social, and legal issues posed by the use of AI technologies in clinical practice. Students will generate and discuss a survey of major AI solutions in healthcare practice. The course will then provide students with best-practice guidance, methods and tools on when to use AI to improve patient care, how to deploy an AI project pipeline, how to critically assess the performance and impact of the proposed AI solution and what pitfalls to avoid.

Ìý

Registration open

Ìý

Term 2 (F2F and online):