Being able to identify those people most at risk of beginning high-cost care so that they might be offered intensive ‘upstream’ preventive care and support could potentially promote independent living and be more cost-effective. One way of identifying people who are at high risk is with predictive risk models.
Predictive models are increasingly being used in health care to identify people at high risk of unplanned hospital admission, so that preventive care can be effectively targeted.
In addition to the predictive models we developed, this work generated important lessons about the potential of linked health and social care data to support policy analysis and to guide the planning and commissioning of services. This report, by Dr Martin Bardsley, Professor John Billings, Ludovic Jean Chassin, Dr Jennifer Dixon, Elizabeth Eastmure, Theo Georghiou, Dr Geraint Lewis, Adam Steventon, will be of interest to health and social care policy-makers, senior managers and practitioners, and others involved in commissioning, as well as academics and students in the fields of health care and social policy.