Predictive risk

Predictive risk adjustment tools use relationships in historic, routinely collected electronic health data to determine the expected future health care resource use of each individual in a population.

We are regarded as a centre of expertise on risk adjustment and many of our projects use predictive risk modeling techniques with innovative data linkage.

This includes work on the development of case finding tools, such as PARR and the Combined Model; person-based resource allocation; and national evaluations of interventions to reduce hospital use, such as the Whole System Demonstrator Project, integrated care pilots, and selected Partnership for Older People Projects (POPPs) and Virtual Wards. Our research in this area is making a valuable contribution to the work of commissioners and policy-makers.

These tools can be used to estimate future events for people at different levels of risk, providing commissioners with more accurate estimates of likely future costs.

Our methods allow us to follow care pathways over time and across sectors – this is fundamental to understanding which patients are at highest risk, the services used and the care outcomes

^{Stephen Sutch, Independent Consultant, discusses his research into risk stratification models and improving the use of clinical data}

In the US and Europe, risk adjustment models are used widely to help determine health payments, either for fixing ‘capitated’ budgets or for deciding reimbursement rates for individual patients.

In the NHS, the most widespread use of these techniques so far has been in the use of ‘case finding’ tools, such as the Patients At Risk of Re-hospitalisation (PARR) and the ’Combined Model’.

Our latest work in this area includes an analysis of new applications for predictive risk modeling – for example, testing models that can be used to predict short-term readmissions.

We continue to conduct several analyses that will help to address the shortage of information about the care people receive at the end of life, as well as using the techniques for ‘data surveillance’ to spot evidence of changes in patterns of service use across England.

_{Photo credit: Tunstall Telehealthcare, Flickr}