Last modified: 4 Days, 21 Hours, 42 Minutes ago
The course aims to equip students with the conceptual understanding, practical skills and critical awareness required to apply machine learning methods to healthcare prediction problems.
Using R language, students will develop the ability to design, implement and evaluate reproducible machine learning workflows, select and compare appropriate modelling approaches, and critically consider their performance, limitations and suitability for use in healthcare contexts.
| Study Type | Postgraduate | Level | 5 |
|---|---|---|---|
| Term | Second Term | Credit Points | 15 credits (7.5 ECTS credits) |
| Campus | Aberdeen | Sustained Study | No |
| Co-ordinators |
|
||
This introductory course provides a practical and critical introduction to machine learning for healthcare prediction. Students will learn how to identify healthcare problems that may be addressed using machine learning, understand the main stages of a machine learning workflow, and implement these stages using R language.
The course covers data preparation, model development, validation, performance evaluation and interpretation, supported by healthcare case studies. It also considers the methodological, ethical and practical challenges associated with developing and applying machine learning models in healthcare. Students will integrate these concepts by developing and critically evaluating a complete machine learning workflow for a specified healthcare prediction problem.
The course assumes prior knowledge of basic statistics and basic R programming skills.
Teaching and learning for this course will involve a combination of tutorials, self-study, discussion boards and assignments. You will receive approximately 40 hours of synchronous tutorials to discuss each topic and get support with the practical aspects of the course. These tutorials are optional for online students. You are expected to spend a further 110 hours in private study and preparation for assessments.
| Assessment Type | Summative | Weighting | 40 | |
|---|---|---|---|---|
| Assessment Weeks | 41 | Feedback Weeks | 43 | |
| Feedback |
Students will be assigned one publication from a selected set and will record an oral presentation summarising the study and providing a critical appraisal, including suggestions for methodological improvements or applications to other healthcare domains. Students will record a short video presentation and upload to MyAberdeen. |
|||
| Knowledge Level | Thinking Skill | Outcome |
|---|---|---|
| Conceptual | Evaluate | Discuss current challenges with implementing machine learning in healthcare |
| Procedural | Analyse | Relate a range of healthcare problems to appropriate machine learning algorithms |
| Procedural | Understand | Describe the machine learning workflow |
| Procedural | Understand | Explain how machine learning is used to address healthcare problems |
| Assessment Type | Summative | Weighting | 60 | |
|---|---|---|---|---|
| Assessment Weeks | 33 | Feedback Weeks | 35 | |
| Feedback |
RMarkdown report (focused on ML models covered in lectures); workflow plan, methodology used, presentation of results, interpretation of results and conclusions. Students should also outline future directions, highlighting handling possible constraints, application of advanced modelling approaches, addressing other challenges, etc. |
|||
| Knowledge Level | Thinking Skill | Outcome |
|---|---|---|
| Procedural | Apply | Apply machine learning methods using R to address healthcare problems |
| Procedural | Understand | Describe the machine learning workflow |
| Procedural | Understand | Explain how machine learning is used to address healthcare problems |
| Assessment Type | Formative | Weighting | ||
|---|---|---|---|---|
| Assessment Weeks | 28,29,30,31,32,33,34,35,36,37,38 | Feedback Weeks | ||
| Feedback |
Weekly conceptual quizzes with automatic grading and feedback. |
|||
| Knowledge Level | Thinking Skill | Outcome |
|---|---|---|
| Procedural | Analyse | Relate a range of healthcare problems to appropriate machine learning algorithms |
| Procedural | Understand | Describe the machine learning workflow |
| Procedural | Understand | Explain how machine learning is used to address healthcare problems |
| Assessment Type | Summative | Weighting | 100 | |
|---|---|---|---|---|
| Assessment Weeks | 50 | Feedback Weeks | ||
| Feedback |
RMarkdown report applying a ML method to a dataset, including analysis, model development, evaluation, and reflection. |
|||
| Knowledge Level | Thinking Skill | Outcome |
|---|---|---|
|
|
||
| Knowledge Level | Thinking Skill | Outcome |
|---|---|---|
| Procedural | Understand | Explain how machine learning is used to address healthcare problems |
| Procedural | Understand | Describe the machine learning workflow |
| Conceptual | Evaluate | Discuss current challenges with implementing machine learning in healthcare |
| Procedural | Analyse | Relate a range of healthcare problems to appropriate machine learning algorithms |
| Procedural | Apply | Apply machine learning methods using R to address healthcare problems |
We have detected that you are have compatibility mode enabled or are using an old version of Internet Explorer. You either need to switch off compatibility mode for this site or upgrade your browser.
