COMP41840

Learning Outcomes:

- Understanding of the motivation, potential and challenges of applying AI in the healthcare domain
- Understanding of foundational ML concepts and evaluation techniques which are most relevant to health applications
- Able to identify and describe major types of health data and their inherent characteristics and challenges
- Develop unsupervised learning methods to discover patterns and structure within health datasets
- Ability to apply CNNs to medical image analysis tasks
- Apply sequence models (RNNs, Transformers) and NLP techniques to analyse temporal clinical and health data
- Understanding of how to evaluate, validate, and interpret AI models in a clinical context, including fairness considerations

Indicative Module Content:

Introduction to AI in Health
Machine Learning Fundamentals for Health including Data Preprocessing and handling
Supervised Learning for Clinical Prediction
Deep Learning Models for Medical Image Analysis
Sequence Models for Health and Clinical Data
Evaluation and Interpretability, also issues of ethics and fairness

Student Effort Hours:

Approaches to Teaching and Learning:

Requirements, Exclusions and Recommendations

Not applicable to this module.

Module Requisites and Incompatibles

Assessment Strategy

Feedback Strategy/Strategies

• Feedback individually to students, post-assessment
• Peer review activities

How will my Feedback be Delivered?

Solutions to assignments will be discussed as a collaborative exercise at the weekly tutorials.