Module information
Module details
- Title
- Data Science and Engineering
- Type
- Specialist
- Module code
- S-HI-S1
- Credits
- 10
- Phase
- 2
- Requirement
- Compulsory
Aim of this module
Data Science and Engineering is key to the application of meaningful health data science and informatics. This module aims to give trainees the key concepts to be able to work in a multidisciplinary team with those that are data engineers and give them hands-on experience in designing, managing and optimising the flow of health data throughout a healthcare organisation.
Work-based content
Training activities
| # | Learning outcome | Training activity | Type | Action |
|---|---|---|---|---|
| # 1 | Learning outcome 1 |
Training activities
Analyse an existing operational data set to determine the original sources of data and present this information in a diagram |
Type DTA | Action View |
| # 2 | Learning outcome 1 |
Training activities
Plan a dataflow required to establish a data set that will generate operationally relevant information |
Type DTA | Action View |
| # 3 | Learning outcome 2 |
Training activities
Create a quality assurance and quality control plan for a data collection that will be repeated regularly ensuring that limitations of the methodology are reported |
Type DTA | Action View |
| # 4 | Learning outcome 2 |
Training activities
Collect data from new and existing data sources |
Type ETA | Action View |
| # 5 | Learning outcome 3 |
Training activities
Plan the statistical analysis of data to answer a research or operational question relating to healthcare using appropriate methods |
Type DTA | Action View |
| # 6 | Learning outcome 3 |
Training activities
Devise the data analysis to answer a real-world clinical question |
Type DTA | Action View |
| # 7 | Learning outcome 3 |
Training activities
Present the plan for data analysis to an audience of peers to ensure the reasoning is sound |
Type DTA | Action View |
| # 8 | Learning outcome 3 |
Training activities
Execute a planned statistical analysis in order to generate novel information |
Type DTA | Action View |
| # 9 | Learning outcome 4 |
Training activities
Using the results generated by a statistical analysis make use of appropriate data visualisation tools and communicate the relevant findings to:
|
Type DTA | Action View |
Assessments
Complete 2 Case-Based Discussions
Complete 2 DOPS or OCEs
Direct Observation of Practical Skills Titles
- Load a dataset into R/Python or alternative software and run summary/descriptive statistics.
- Evaluate the application of analytical method to a dataset.
Observed Clinical Event Titles
- Explain summary/descriptive data analysis to a healthcare professional.
Learning outcomes
| # | Learning outcome |
|---|---|
| 1 | Appraise the health data landscape, articulate how different data sets relate to each other and curate a data set to generate novel information. |
| 2 | Apply data collection methodologies using both pre-existing and new data sources, considering quality assurance, quality control and limitations relating to data collection. |
| 3 | Plan and execute the statistical analysis of data to answer questions relating to healthcare using appropriate methods with a clear and defensible rationale. |
| 4 | Summarise findings from data analysis for stakeholders using a variety of data visualisation techniques and considering the audiences understanding of the subject matter. |
Clinical experiences
Clinical experiences help you to develop insight into your practice and a greater understanding of your specialty's impact on patient care. Clinical experiences should be included in your training plan and you may be asked to help organise your experiences. Reflections and observations from your experiences may help you to advance your practice and can be used to develop evidence to demonstrate your awareness and appreciation of your specialty.
Activities
- Review a completed data analysis and conclusions to appreciate the steps required, rationale and the implications of the conclusions.
- Attend a clinical meeting where data outputs developed by the department and the actions based on the data analysis are discussed to appreciate the impact of the analysis on practice.
Academic content (MSc in Clinical Science)
Important information
The academic parts of this module will be detailed and communicated to you by your university. Please contact them if you have questions regarding this module and its assessments. The module titles in your MSc may not be exactly identical to the work-based modules shown in the e-portfolio. Your modules will be aligned, however, to ensure that your academic and work-based learning are complimentary.
Learning outcomes
On successful completion of this module the trainee will be able to:
- Critically evaluate the health data landscape, what information different datasets include and how they can be linked together.
- Discuss and apply, data cleaning and data wrangling methodologies and steps to produce a dataset that is “analysis-ready”.
- Apply a type of statistical analysis for the data science tasks.
- Discuss hypothesis testing and quantifying uncertainty.
- Critically appraise regression modelling methods and apply them to datasets.
- Design a statistical analysis plan for a particular study.
Indicative content
Programming
- Use of R/Python for data analysis, data wrangling and data visualisation, including an appreciation of version control (e.g. git and github)
Data curation
- Explore the health data landscape, including how and where health data are stored
- Recap the key steps that are required for data access
- Data wrangling and manipulation techniques that are required to transform a dataset into a format that is ready for analysis
- Coding skills to enable data engineering
Data analysis
- Principles of good research/analysis design (e.g. formulating sound research questions, and how to design studies for analysis)
- Statistical thinking and critical appraisal as an approach to designing analysis requirements
- Three data science tasks: (i) description, (ii) prediction, and (iii) causal inference
- Communication of findings from data analysis to different stakeholders (e.g. data visualisation), including ‘what not to do’
- Translating of data analysis into policy (e.g. presenting statistical output/design to lay audiences)