Description
Modelling for Decision Science (M4DS) will provide you with a technical overview of modern modelling methods and equip you with skills that can be used to support and enhance decision making in healthcare. This is increasingly relevant for bodies such as the National Institute for Health Research (NIHR). You will be exposed to a range of mathematical and statistical modelling techniques, with a focus on utilising these applied methods to real life problems in public health and healthcare. The course will be taught both in lectures and parallel practical. Coding sessions using or other relevant software (e.g. Python). In these coding sessions, you will gain hands-on experience in the analysis and interpretation of results. There may also be guest lectures from applied mathematicians, statisticians and healthcare professionals.
Note: Previous coding experience is not required. However, it is expected that you will be proactive in enhancing your skills through practice and further experimentation with the scripts written in the lab.
After taking this module you should be able to:
1. Understand the various definitions of decision science, and how mathematical and statistical modelling can be applied to public health and healthcare.
2. Identify and apply the appropriate modelling technique for the specific healthcare problem at hand.
3. Understand the difference between unsupervised and supervised machine learning and develop a solid understanding of some of the most widely used methods and algorithms in this area.
4. Understand different approaches of modelling infectious diseases including simple compartmental models such as SEIR models. You should accumulate skills to understand the assumptions within the models, as well as be able to run and check the models and their outputs.
5. Use key principles of queueing theory and stochastic simulation to support capacity planning decisions through 鈥渨hat-if鈥 analyses.
6. Be able to process data and implement simple mathematical and machine learning models using numerical software such as Python.
The module is open to anyone with a 2.1 or above in a quantitative first degree.
You will be taught the material through lectures with practical sessions following the lecture material closely and giving you a hands-on approach. Moodle will be used to provide a repository of course materials.
Reading list:
1. Introduction to Statistical Learning (2021) James, Witten, Hastie and Tibshirani.
2. Mathematics for Machine Learning (2020) Deisenroth, Faisal and Ong.
3. Pattern Recognition and Machine Learning (2006) Bishop.
4. Probability, Markov Chains, Queues, and Simulation: The Mathematical Basis of Performance Modeling (2009) William J. Stewart.
Module deliveries for 2024/25 academic year
Last updated
This module description was last updated on 19th August 2024.
听