Description:

This module gives you a practical introduction on how to approach Prediction Modelling in medicine and the health sciences.

Prediction modelling is distinct from statistical modelling in that the primary objective is to deliver models that make accurate predictions, rather than estimate parameters such as risk factors.

The main areas covered are:

• Data pre-processing - what you need to do to data before it can be used to train predictive models, for example handling missing data
• Model training - principally using penalised generalised linear models and Survival models, for regression and classification
• Model validation - assessing the model's performance

The course pre-requisites are:

• Some background in basic statistical methods (e.g. probability distributions, hypothesis testing) and high school mathematics (e.g. basic calculus, basic linear algebra).
• A working knowledge of the R programming language

This course is for you if you want to:

• Have a good understanding of core clinical prediction concepts, such as prognosis, prognostic factors, prognostic models, and stratified medicine and want to be able to apply this understanding to the design, conduct, and interpretation of clinical prediction modelling research studies, and the critical appraisal of research papers.
• Be able to describe how modern statistical concepts, regression and machine learning methods can be applied to medical prediction problems.
• Be familiar with the principles that play a role in internal validation such as over-fitting, optimism and shrinkage and understand key components of internal validation methods such as cross-validation and bootstrapping.
• Be able to develop simple prediction models, assess their quality and validate them using R software
• Be able to critically assess the general applicability of a developed model to predict future outcomes.
• Be equipped with a range of statistical and machine learning skills, which will enable you to take prominent roles in a wide spectrum of employment and research.