Following the annoucement by the Department of Health that it will not be upgrading existing predictive risk models such as the Patients at Risk of Re-hospitalisation tool (PARR++) and the Combined Predictive Model, the Nuffield Trust has published a guide to help commissioners navigate an open market for risk tools.
What is a predictive risk model?
Predictive risk models are part of the strategy for managing patients with chronic illness. They are a series of statistical methods designed to identify patients most at risk of future unplanned hospital admissions, and who may benefit from preventive measures such as that provided by community matrons, or through admission to a community-based ‘virtual ward’.
The guide for commissioners
The guide Choosing a predictive risk model: a guide for commissioners in England suggests a range of factors to be taken under consideration when choosing whether to ‘make or buy’ a predictive model, such as the outcome to be predicted, the accuracy of the predictions made and the cost of the model. The guide also provides advice on how to assess the performance of a model once a choice is made, and informs on the likely set up and running costs of different options.
For more information and to download the guide visit the Nuffield Trust's publications page.