Professional and short courses
|Location||Cavendish, Central London|
|Faculty||Science and Technology|
Today we frequently come across gigabytes of information, due to the development of mathematical and computer science. The human brain cannot closely examine more than a few dozens of records with 6 to 8 variables at a time to profile a problem even from well-organised data. But the algorithms of predictive modelling can analyse millions of data points with hundreds of variables to make a diagnosis or predict a risk.
The aim of this course is to provide an overview of predictive modelling technologies. Predictive modelling in health care, which usually refers to the identification of patients at high risk of an event (such as emergency readmission, heart failure, risk of death or long-term care placement) has been a major concern for many health care 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 (for example PCT acute activity data) using a standard statistical computer package such as SPSS.
Who is this course for?
The course is relevant to all those with an interest in the rigorous evaluation of predictive modelling in health care, particularly in local authorities and primary care trusts, and others working or intending to work in the health services or related areas.
Participants are expected to have the basic level of numeracy.
|No course dates available|
|This course will be running soon. If you would like to be kept informed please contact us.|
- what predictive modelling is
- predictive modelling in health and social care
- predictive modelling process
Data preparation and preliminary analysis
- data preparation using multiple datasets
- data analysis
Core modelling technologies
- 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
Hands-on predictive modelling
- illustration of simple predictive models that can be developed based on routinely collected data using standard packages, such as SPSS
At the end of this module you will:
- have learnt the application of existing predictive modelling tools in health and social care specially using the multiple data sources, A&E, inpatient care, outpatient care, mental health, etc
- understand the predictive modelling process
- be able to prepare data for predictive modelling
- be able to select appropriate predictive modelling approaches to identify those cases that are at high risk of an event
- be able to compare and contrast the underlying predictive modelling algorithms, such as logistic regression and classification trees
- be able to apply these approaches using a suitable statistical package such as SPSS
- have practical experience of using the latest version of SPSS (IBM version 20)
Philip Worrall obtained a BA (Econ) in Economics from the University of Manchester and an Operational Research and Management Science MSc from Lancaster University. His MSc project was conducted at the NHS Derbyshire County Primary Care Trust, where he investigated the challenges of building COPD strategic planning models to model long term future demand. At present he studies for a PhD at the University of Westminster on strategic healthcare planning and forecasting long-term care demand in particular, and works part-time for the NHS London Procurement Program. He has extensive experience in applying problem structuring and forecasting methods to develop health care modelling tools.