MDCS42290 AI for Personalised Medicine

Academic Year 2021/2022

*** Not available in the academic year indicated above ***

This module teaches computational methods (with a focus on AI and ML) for generating personalised disease models and patient models. The module has a special focus on pathway and network approaches for stratifying patients and predicting clinical outcomes. It will cover, supervised and unsupervised machine learning techniques for analysing ~omics patient data, including genomic, transcriptomic and proteomics data, and dynamic modelling of disease and drug response mechanisms for the construction of personalised models. Lectures will introduce the concepts and required mathematics, but most of the learning will be delivered through student-led, problem-based activities. This module forms part of the core curriculum for the MSc AI for Medicine and Medical Research.

Show/hide contentOpenClose All

Curricular information is subject to change

Learning Outcomes:

After successful completion of this module, the student will be able to
• Interpret and model various types of ~omics data from patients, including genomic, transcriptomic and proteomics data
• Apply unsupervised and supervised machine learning to stratify patients and predict clinical outcomes
• Formulate strategies for building, calibrating and validating personalised models
• Construct personalised models to gain insight into disease and drug response mechanism
• Appraise machine learning and dynamic modelling approaches for personalised medicine

Indicative Module Content:

• Unsupervised and supervised learning of patients ~omics data
• Pathway and network analysis of biomolecular data
• Survival analysis
• Dynamic modelling of intracellular disease networks

Student Effort Hours: 
Student Effort Type Hours
Lectures

24

Computer Aided Lab

24

Autonomous Student Learning

152

Total

200

Approaches to Teaching and Learning:
1) Problem based learning
2) Lectures
3) Tutorials
 
Requirements, Exclusions and Recommendations

Not applicable to this module.


Module Requisites and Incompatibles
Not applicable to this module.
 
Assessment Strategy  
Description Timing Open Book Exam Component Scale Must Pass Component % of Final Grade
Assignment: Machine learning mini project Varies over the Trimester n/a Graded No

20

Assignment: Write modelling proposal Varies over the Trimester n/a Graded No

30

Essay: Self-assessment essay Varies over the Trimester n/a Graded No

20

Presentation: Group work: modeling project Varies over the Trimester n/a Graded No

30


Carry forward of passed components
No
 
Remediation Type Remediation Timing
In-Module Resit Prior to relevant Programme Exam Board
Please see Student Jargon Buster for more information about remediation types and timing. 
Feedback Strategy/Strategies

• Feedback individually to students, post-assessment
• Group/class feedback, post-assessment
• Peer review activities
• Self-assessment activities

How will my Feedback be Delivered?

The class will receive feedback thRough discussions in the class Students will receive individual feedback on their assignments through the VLE system Feedback on self-assessment Students will receive feedback on their presentation by their peers