The objective of this course is to provide an overview of predictive modeling technologies. Predictive modelling, which usually refers to the identification of patients at high risk of an event (e.g. emergency readmission, heart failure, risk of death, long term care placement) has been a major concern for many healthcare providers (hospitals, clinicians) or purchasers (primary care trusts, local authorities). A number of predictive tools have been developed, such as the PARR case finding tool however, these are often complex to set up, expensive, and may not be applicable to all domains.
Participants will gain practical experience of developing predictive models based on routinely collected data (e.g. a PCT acute activity data) using a standard statistical computer package such as SPSS.
At the end of this module students should be able to:
- Select existing predictive modelling tools in health and social care
- Understand the predictive modelling process
- Prepare data for the purpose of predictive modelling
- Appreciate the use and importance of multiple data sources, e.g. A&E, inpatient care, outpatient care, mental health, etc.
- Compare and contrast the underlying predictive modelling algorithms, e.g. Logistic Regression and Classification Trees
- Select appropriate predictive modelling approaches to identify those cases that are at high risk of an event
- Apply these approaches using SPSS
- What is predictive modelling?
- Predictive modelling in health and social care
- Predictive modelling process
- Data preparation using multiple datasets
- Basic concepts of regression and other algorithms, such as classification trees
- Choosing the right predictive model
- Checking the predictive power of the model (misclassification rates)
- Interpretation of results
- Practical session: Illustration of simple predictive models that can be developed based on routinely collected data
Students will be given data sampled from HES to work on developing a model to predict readmission of patients to hospital within a given time window [30 days, 90 days, etc]. They should aim at improving the predictive power of the model.
In general each module of the course is associated with one day’s face-to-face training in our Central London premises supported by additional material and resources. Distance learning might be considered in the future depending on need.
We can also deliver customized in-house courses.
For face-to-face delivery, a mixed structure is generally adopted. There is a blend of sessions introducing the topics and techniques of interest and use examples to illustrate key themes, and of sessions engaging participants in interactive and hands-on experience of tools and techniques drawing on case material of direct relevance to commissioning or provision of services.
Overall in order to take part in this module, potential participants will need mathematical skills to include simple algebraic manipulation (GCSE grade B or better) and some understanding of basic statistical techniques.
Basic IT skills are required, e.g. use of excel spreadsheet.
The software needed for this module are SPSS (predictive analytics software) and Microsoft Excel 2007/2010.
Prof. Thierry Chaussalet:HSCMG@westminster.ac.uk
Tel: +44 (0)20 3506 4575