Module information
Details
- Title
- Artificial Intelligence
- Type
- Specialist
- Module code
- S-HI-S5-2
- Credits
- 10
- Requirement
- Compulsory
Aim of this module
This module introduces the field of Artificial Intelligence (AI) providing the key concepts and knowledge in how it is used or has the potential to be used to solve healthcare challenges, whilst also discussing the wider issues considering its usage. This module will also provide hands-on experience in developing algorithms/systems to address real world healthcare problems.
Work-based content
Competencies
| # | Learning outcome | Competency | Action |
|---|---|---|---|
| # 1 | Learning outcome 1 |
Competency
Analyse a tool making use of AI which has been implemented in a healthcare setting through the lens of medical device and information governance regulations, present conclusions as a compliance report |
Action View |
| # 2 | Learning outcome 2 |
Competency
Critically appraise a range of competing AI technologies for their use and suitability |
Action View |
| # 3 | Learning outcome 3 |
Competency
Plan the implementation of an existing AI solution to improve a process within your area of work |
Action View |
| # 4 | Learning outcome 3 |
Competency
Analyse the process used to develop an existing machine learning solution |
Action View |
| # 5 | Learning outcome 2 |
Competency
Critically appraise common tools used in machine learning |
Action View |
| # 6 | Learning outcome 4 |
Competency
Develop a machine learning solution to a clinical problem |
Action View |
| # 7 | Learning outcome 4 |
Competency
Pre-process and analyse unstructured clinical data using NLP techniques |
Action View |
| # 8 | Learning outcome 2 |
Competency
Identify applications and potential applications of AI in the local environment, reflect on application and benefit in moving healthcare forward |
Action View |
| # 9 | Learning outcome 3 |
Competency
Prepare data for AI use |
Action View |
Assessments
Complete 2 Case-Based Discussions
Complete 2 DOPS or OCEs
Direct Observation of Practical Skills Titles
- Write pseudo-code for an ML algorithm to analyse a dataset.
- Write an analysis workflow/protocol for a specific dataset/problem.
- Demonstrate an AI solution to a healthcare professional.
Observed Clinical Event Titles
- Discuss the application of AI for a specified problem with members of a clinical multidisciplinary team/non-technical healthcare professionals.
Learning outcomes
| # | Learning outcome |
|---|---|
| 1 | Analyse, interpret and report on the regulation around AI and machine learning methods, and its application. |
| 2 | Critically appraise the application of AI and machine learning in healthcare. |
| 3 | Plan the implementation of AI and machine learning solutions. |
| 4 | Apply AI and machine learning techniques to address healthcare provision and clinical questions. |
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 appraise the uses of AI in healthcare and how they could impact the delivery of healthcare.
- Demonstrate an understanding of the main advanced analytic and machine learning methodologies, and settings where each method might be more/less applicable.
- Demonstrate an understanding of the current limitations of common AI/ML methods, including their dependence on data, computational resources and causal explanation.
- Critically evaluate existing AI/ML solutions in healthcare, and be able to explain the key strengths and limitations.
- Design and implement AI/ML systems in a suitable programming language and evaluate their performance using standard performance metrics.
Indicative content
- Big data in biomedicine and health (including open resources)
- Overview of use cases of AI/ML in healthcare, including their critical evaluation
- e.g., robotic surgery, health monitoring with wearables, automated image diagnosis and deep-learning in image classification
- Programming for AI in python (or similar software)
- Explanation of the following methods, including the strengths and limitations of each, and how to interpret their outputs to draw meaning:
- High dimensional methods (e.g., PCA)
- Supervised machine learning (introduction, fundamental and advanced methods)
- Unsupervised machine learning
- Model performance metrics
- Ethics and bias
- Reporting – standards for journal articles and quality guidelines
- Regulatory environment
Clinical experiences
Important information
Clinical experiential learning is the range of activities trainees may undertake in order to gain the experience and evidence to demonstrate their achievement of module competencies and assessments. The list is not definitive or mandatory, but training officers should ensure, as best training practice, that trainees gain as many of these clinical experiences as possible. They should be included in training plans, and once undertaken they should support the completion of module assessments and competencies within the e-portfolio.
Activities
- Visit a department implementing or trialing direct AI solutions to existing clinical problems to appreciate processes and the (potential) impact on patient care.