Health Data Science MSc

Program Overview

Lancaster University's MSc in Health Data Science combines expertise in statistics, health, and computer science to prepare students for careers as data scientists in the healthcare sector. Through core modules and pathways in Global Health or Health Informatics, students develop advanced technical skills in health data analysis while gaining real-world experience through a placement project with partners like the World Health Organization.

Program Outline

Degree Overview:

The MSc in Health Data Science at Lancaster University aims to equip students with advanced technical skills in health data science, allowing them to pursue careers as data scientists within the health and care sector. This program combines expertise in statistics, health, and computer science to address global public health challenges. The program's initial focus is on building foundational skills in epidemiology, statistics, and computer science through four core modules: Topics covered include exploratory data analysis, linear regression, binomial and Poisson regression, hypothesis-testing, and linear mixed models.

• Programming for Health Data Science: Students learn the fundamentals of computing, including data storage, computational processing, and the development of computer science.
The module focuses on programming languages like R and Python, covering topics such as structured programming, data structures, writing functions, data file input/output, exploratory graphics, and reproducible research practices.
• Fundamentals for Health Data Science: This module provides students with a formal understanding of research methods and develops their ability to critically reflect on research approaches and practices.
It covers topics such as the data science role, research methodologies, data processing and integration, ethical implications of research, and industrial data science practices.
• Introduction to applied epidemiology: This introductory module covers key epidemiological concepts, including types of health outcomes, definitions of exposure and risk, metrics used to quantify disease in a population, and common epidemiological study designs (case-control studies, randomized control trials, and cohort studies).
It also discusses the limitations and issues arising from recruitment and sampling biases and focuses on drawing inferences from epidemiological studies, defining association and causality. After completing the core modules, students choose one of two pathways:
• Global Health: This pathway emphasizes using data to inform health policy decisions.
It further develops skills in statistical science with a focus on spatio-temporal methods of analysis of infectious diseases.
• Health Informatics: This pathway focuses on analyzing routinely collected health data and evaluating healthcare economically.
It enhances students' knowledge and statistical skills in this area. A 12-week placement project with partners like the World Health Organization and the National Health Service is a critical component of the program. This real-world experience allows students to apply their skills and knowledge to solve real-world challenges and gain valuable professional experience in a multidisciplinary team.

Outline:

Course Structure:

The program is structured around a set of core modules followed by a pathway selection. Students also undertake a placement project.

Core Modules:

• Fundamentals for Health Data Science
• Introduction to applied epidemiology
• Modelling Multilevel and Longitudinal Data
• Programming for Health Data Science
• Statistical methods and models for health research

Pathways:

• Global Health
• Health Informatics

Placement Project:

A 12-week project with partners like the World Health Organization and the National Health Service.

Module Descriptions:

• Fundamentals for Health Data Science: This module provides students with a formal understanding of research methods, and develops their ability to critically reflect on research approaches and practices in the field.
On completion of this module students will be:
• able to understand what the data science role entails, and how that individual performs their job within an organisation on a day-to-day basis;
• able to understand how research is performed in terms of formulating a hypothesis and the implications of research findings, and be aware of different research strategies and when these should be applied;
• able to critique research proposals in terms of their ethical implications;
• able to learn how data science problems are tackled in an industrial settings, and how such findings are communicated to people within the organisation.
• Introduction to applied epidemiology: This is an introductory module on epidemiology with a strong focus on applied and quantitative topics.
The module introduces key epidemiological concepts, including types of health outcomes, definitions of exposure and risk, and metrics used to quantify disease in a population. The students will be given an overview of the most commonly used epidemiological study designs: case-control studies, randomized control trials and cohort studies. Limitations and issues arising from recruitment and sampling biases will be discussed for each design. An important topic of the module will be how to draw inferences from epidemiological studies, defining association, causality and how these differ. In the lab sessions of the module, the students will analyse epidemiological data using R statistical programming language.
• Modelling Multilevel and Longitudinal Data: Hierarchical data arise in a multitude of settings, specifically whenever a sample is grouped (or clustered) according to one or more factors with each factor having many levels.
For instance, school pupils may be grouped by teacher, school and local education authority. There is a hierarchical structure to this grouping since schools are grouped within local education authority and teachers are grouped within schools. If multiple measurements of a response variable, say test score, are made for each pupil across multiple measurement times, the data are also longitudinal. The differences between marginal and conditional models, and the advantages and disadvantages of each, will be discussed. Longitudinal data will be introduced as a special case of hierarchical data motivating the need for temporal dependence structures to be incorporated within LMMs. Finally, the drawbacks of LMMs will be used to motivate generalised linear mixed effects models (GLMMs), with the former a special case of the latter. GLMMs broaden the scope of data sets which can be analysed using mixed-effects models to incorporate all common types of response variable. All modelling will be carried out using the statistical software package R.
• Programming for Health Data Science: The module will teach the fundamentals of computing: historical development of computational machines, data storage, computational processing, the development of computer science.
The students will be taught how to handle the R language for data file input/output; selection and filtering; exploratory graphics. Throughout the module, the students will also learn how to develop good computational research practice: project management for data and code; dynamic documents for reproducible research; source code management. In the second part of the module the students will learn the Python language basics: fundamentals for calculation and programming; writing functions and modules for code re-use; creating new classes and programming with objects; Python including command line and notebooks. The module starts with the use of graphical tools for exploratory analysis: scatter plots; box plots; transformation of the response and outcome variables. The linear regression modelling framework is introduced with a focus on: critical evaluation of assumptions; link between regression analysis and ANOVA; interpretation of regression coefficients; multicollinearity and dealing with confounding factors; analysis of residuals. Building on this, the module covers Binomial and Poisson regression, and students will learn how to carry out hypothesis-testing through the analysis of deviance and the use of regression diagnostics.

Optional Modules:

• Handling routinely collected Health Data: This module will give students an understanding of the nature of routinely collected NHS data including ways of coding it (such as the 10th revision of the International Statistical Classification of Diseases and Related Health Problems (ICD-10)).
Furthermore there will be exploration of other routinely collected data sets such as those held by the Office of National Statistics. Alongside this the module will cover relevant structures within the NHS with particular reference to data collection, coding and analysis as well as information governance and ethics. Students will also explore stakeholder engagement in the NHS including business intelligence and clinical staff. The module will cover approaches to identifying research priorities in the NHS. Methodologically, students will learn about methods such as systematic review and meta-analysis and standard methods for data cleaning and preparation (such as methods for identifying missing data and data engineering). For example, participants in a survey or clinical trial may drop-out of the study, measurement instruments may fail, or human error invalidate instrumental readings. In this module you will learn about the different ways in which missing data can arise, and how these can be handled to mitigate the impact of the missingness on the data analysis. Topics covered include single imputation methods, Bayesian imputation, multiple imputation (Rubin's rules, chained equations and multivariate methods, as well as suitable diagnostics) and modelling dropout in longitudinal modelling.
• Model-based geostatistics for public health: Using motivating examples from environmental and health sciences, this module first introduces key data concepts of geostatistical analysis.
The students will then learn how to perform the different stages of a geostatistical analysis, including: spatial exploratory analysis, model formulation, parameter estimation and spatial prediction. Building on the students' knowledge of standard linear regression, they will learn how to formulate and apply linear geostatistical models using maximum likelihood and Bayesian methods of estimation.

Assessment:

The program utilizes various assessment methods, including coursework, exams, and a final project. Specific assessment methods and criteria for each module are likely outlined in the course syllabus.

Teaching:

The teaching methods used in the Health Data Science MSc program are likely to include a combination of lectures, seminars, workshops, and group work. The faculty consists of experienced researchers and academics in the fields of epidemiology, statistics, and computer science. The program may feature unique approaches like case studies, guest lectures, and collaborations with industry partners.

Careers:

Graduates of the Health Data Science MSc program are well-prepared for a range of careers in the health and care sector. Potential career paths include:

• Data Scientist: Working for healthcare organizations, research institutions, or government agencies to analyze health data and inform decision-making.
• Biostatistician: Contributing to clinical trials, epidemiological studies, or public health research.
• Health Informatics Specialist: Managing and analyzing healthcare data to improve patient care, optimize healthcare delivery, and conduct research.
• Health Policy Analyst: Using data to evaluate health policies, identify trends, and develop recommendations.
• Consultant: Providing expertise in health data science to organizations in the health and care sector.

Other:

The program benefits from partnerships with leading organizations, including the World Health Organization and the National Health Service. The program aims to train the data scientists of the future, equipping them with the skills and knowledge needed to address complex health challenges. The program features a summer school on Pemba Island, Mozambique, hosted by the Fondazione Ivo de Carneri at their Public Health Laboratory. the "Assessment" and "Teaching" sections have limited detail.

Location Full Time (per year) Part Time (per year) Home £13,600 £6,800 International £29,150 £14,575