Module manager: Samuel Relton
Email: s.d.relton@leeds.ac.uk
Taught: Semester 2 (Jan to Jun) View Timetable
Year running 2025/26
As per programme entry requirements
This module is not approved as an Elective
In healthcare and other areas, there are increasingly vast quantities of complex, heterogeneous data produced. This includes medical images, electronic healthcare records, and genetic data. An increasingly popular method of analysing (and combining) such datasets is using machine learning to identify significant trends and patterns. This module will introduce students to a variety of different machine learning algorithms for supervised and unsupervised learning problems. These include random forest, support vector machines, k-means clustering, and neural networks with use-cases identified from across the healthcare domain. Students will also be introduced to techniques for feature selection, dimensionality reduction, and in avoiding overfitting.
The purpose of this module is to:
- Introduce students to methods for the appropriate training and testing of various machine learning models using healthcare data
- Equip students with the ability to run an analysis independently and critique the work of others
- Give students an understanding of fundamental concepts of machine learning theory, allowing students to expand their knowledge by reading the current literature
- Familiarise students with a variety of alternative approaches to traditional statistical modelling, including experience in using them within languages such as Python
On successful completion of the module students will have demonstrated the following learning outcomes relevant to the subject:
1. Explain the use-case for machine learning within healthcare applications, and how this compares with more traditional statistical models.
2. Critically appraise scenarios where supervised and unsupervised learning approaches may be used.
3. Critically appraise health data analysis of others, identifying potential sources of bias and modelling issues.
4. Demonstrate a critical understanding by selecting and applying a range of machine learning approaches to data using Python and analyse the results appropriately.
5. Apply the technology underlying cutting-edge healthcare applications (i.e. automated diagnosis of disease from MRI imaging) and demonstrate a sophisticated understanding of the resources and tools available to advance their knowledge.
Skills Learning Outcomes
On successful completion of the module students will have demonstrated the following skills learning outcomes:
1. Demonstrate understanding of the impact of various working practices in the healthcare system that change the way that data is captured and recorded for research
2. Plan a solution to address a research question using data, and consider how it may fit into a clinical workflow, appreciating any potential benefits and limitations of these changes
3. Critically evaluate different approaches to analysing data, and consider the advantages and disadvantages of each approach
This module covers the following concepts:
- Variety of approaches to supervised learning problems
- Approaches to unsupervised learning problems
- Designing analysis plans to give robust answers to clinical questions
- Implementing analysis plans in software
| Delivery type | Number | Length hours | Student hours |
|---|---|---|---|
| Lecture | 10 | 1 | 10 |
| Practical | 15 | 1 | 15 |
| Seminar | 5 | 1 | 5 |
| Independent online learning hours | 6 | ||
| Private study hours | 114 | ||
| Total Contact hours | 30 | ||
| Total hours (100hr per 10 credits) | 150 | ||
Lectures and seminars will be interactive, including group discussion and problem-based exercises. There will be plenty of opportunity for rapid face-to-face feedback and clarification from the tutors during classes.
A draft outline of the written coursework will be submitted for formative assessment, so students will gain individual feedback directly applicable to their preparation for the summative work.
| Assessment type | Notes | % of formal assessment |
|---|---|---|
| Coursework | Formative - Statistical analysis plan for the summative report described below | 0 |
| Coursework | Summative - Summative report - Design and implementation of statistical analysis (requiring regression modelling) on a real-world dataset from a previous clinical trial or similar data source. (3000 words) | 100 |
| Total percentage (Assessment Coursework) | 100 | |
Students who fail the first attempt at the summative coursework will be offered an opportunity to resubmit. The resubmission will take the same format as the first attempt.
The reading list is available from the Library website
Last updated: 08/05/2025
Errors, omissions, failed links etc should be notified to the Catalogue Team