Course Outline

The objective of this course is to provide an overview of predictive modelling 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 the standard statistical computer package SPSS .

Learning Outcomes

Upon completion of this short course, you will have the knowledge to apply predictive modelling approaches to identify those cases that are at high risk of an event.

Teaching

The course will be led by Professor Thierry Chaussalet, Dr Eren Demir, Dr Salma Chahed and other members of the Health and Social Care Modelling Group (www.healthcareinformatics.org.uk), who have expertise in operational research, statistics, and data mining applied to health and medicine.

Course Content

Overview

• What is predictive modelling?
• 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 (e.g. a PCT acute activity data) using standard packages such as SPSS.

Methods of Assessment

There will be no formal examination. A certificate of attendance will be awarded to all completing this day-course and may count towards continuous professional development.

Course Materials

The course will include some lectures introducing various predictive modelling methods, where the focus is on demonstrating the main concepts on real case studies. There will be a participatory practical sessions using the computer package SPSS.

The following books are recommended:

• Giudici, P. (2003) Applied Data Mining: Statistical Methods for Business and Industry. Wiley.
• Hand, D. J., Mannila, H. and Smyth, P. (2001) Principles of Data Mining. MIT Press.
• Carver and Nash (2000) Doing data analysis with SPSS 15. Duxbury Press.

Prerequisites

Participants are expected to have the basic level of numeracy.

Who should apply for this course?

The course is relevant to all those with an interest in the rigorous evaluation of predictive modelling in healthcare, particularly in local authorities and primary care trusts and others working or intending to work in the health services or related areas.

Venue and Contacts

The course will be delivered at University of Westminster
School of Electronics and Computer Science
115 New Cavendish Street
London
W1W 6UW
London, UK
For more information contact Dr Eren Demir or Dr Salma Chahed
by phone: 0207 911 5000 ext 2842 or by email demirer@wmin.ac.uk or chaheds@wmin.ac.uk

Course date and times, fee and deadlines

The course will be 10 June 2010 between 9:30 and 17:00. An indicative schedule is as follows:
09:30-10:00 Meet peers and tutors
10:00-12:00 Overview, Data preparation and preliminary analysis
12:00-12:45 Lunch
12:45-14:45 Core modelling technologies
14:45-15:00 Break
15:00-17:00 Hands-on session

Maximum Capacity: 16
Fees: £305 before 27 May 2010 (£335 thereafter), including lunch

Registration Deadline: 8 June 2010
Note this is a repeat of the course given 30 September 2009 and 20 January 2010. Due to the course popularity and limited capacity, early registration is advised to avoid disappointment.