MSc Health Data Science

• Fundamental data types and structures
• Core programming concepts such as iteration, selection, file handling and control flow
• Develop awareness of programming languages used in Data Science (e.g. Python, R, Julia)
• The fundamentals of using a modern programming language (e.g. Python) for data science and associated commonly used libraries/modules
• How data is stored and accessed using database systems
• Data manipulation and pre-processing (cleaning, imputation, encoding and transforming data)
• Combining datasets (data linkage)

The unit aims to:

• Facilitate the practice of writing code scripts in a modern programming language suitable for data science tasks, while applying best software engineering practices & standards
• Give learners experience of manipulating data presented and stored in different formats (e.g. JSON, XML, CSV)
• Build familiarity with using, accessing and querying data in different database storage systems (e.g. relational database systems)
• Understand and practice data wrangling, transformation and cleaning strategies to make data usable for analytic purposes
• Produce data visualisations to explore and present data
• To develop 'algorithmic thinking' and problem solving strategies

The unit is delivered in a blended format. Self-directed learning material is delivered through interactive digital (Jupyter) notebooks to impart core knowledge and skills with weekly online synchronous sessions allowing learners to work in teams to solve and practice coding problems. This is further supported by two face-to-face hackathon events allowing learners to load, combine and visualise data in the first hackathon. Building on this in the second hackathon, learners apply methods to clean and process data in order to carry out subsequent analysis.

Upon completion, students should be able to: 

LO1: Demonstrate a critical understanding of the fundamental principles and concepts of programming (e.g. iteration, selection, control flow and data representation using data-frames) using a modern programming language for data science (e.g. Python) 

LO2: Identify and explain key modules essential for health data science (e.g. NumPy, Pandas, re, and Matplotlib), with a focus on data-frame manipulation 

LO3: Describe basic statistical concepts and their application in health data analysis, and how they are represented/used within a programming language

Upon completion, students should be able to: 

LO4: Apply 'algorithmic thinking' to solve problems using programming concepts (e.g. selection, iteration, functions, etc.) 

LO5: Analyse and manipulate health-related datasets using data-frames, including indexing, filtering, aggregation, and integration with SQL databases 

LO6: Interpret and visualise data effectively for insights and decision-making in health-related contexts, using common visualisation libraries

Upon completion, students should be able to: 

LO7: Write code for basic statistical analysis and data visualisation tasks, incorporating data-frame operations 

LO8: Clean and pre-process health-related datasets using regular expressions and data-frame methods 

LO9: Write and execute queries in SQL and integrate with code 

LO10: Implement best practices in coding to structure and document code (e.g. use of data structures, functions, classes, comments, code standards such as PEP8)

Upon completion, students should be able to: 

LO11: Experience 'team science' to solve problems collaboratively 

LO12: Develop an analytical problem solving mind-set

Feedback will be provided via Blackboard 15 working days after submission.

• Dawson, M (2010) Python Programming 3rd Ed. Australia: Course Technology PTR
• Molin, S (2019) Hands-On Data Analysis with Pandas. Birmingham: Packt
• Medium (2024) Towards data science: A Medium publication sharing concepts, ideas and codes. https://towardsdatascience.com/about 
• NHS (2024) NHS Python Community. https://nhs-pycom.net/