Using predictive analysis to prevent mental health crisis Birmingham and Solihull Mental Health NHS Foundation Trust

Risk stratification tools are currently used across the NHS, for example to help identify which general practice patients are at highest risk of being admitted to hospital. The potential benefits of this are that patients are prevented from experiencing an adverse event and emergency care costs are avoided.

This project set out to apply risk stratification to mental health by building models that predict the likelihood of mental health crisis. The aim was to develop a risk stratification model to help clinicians prevent mental health patients from needing crisis or urgent care by providing targeted, early intervention to those at highest risk.

The model has incorporated six years of clinical data, which was a sub-set of historic, anonymised data from the Trust’s electronic health record, to provide an overall indication of a patient’s risk of experiencing a mental health crisis. It was piloted as a decision support tool within four Birmingham and Solihull Mental Health NHS Foundation Trust Community Mental Health Teams.

Clinicians reviewed risk information and completed evaluation questions via an internal feedback platform, which was developed during the project to make model outputs more manageable and understandable. Clinicians largely engaged positively with the tool and were able to use it to prevent a flagged crisis, manage their caseload priorities or identify patients that may have otherwise been lost in the system.

This project successfully introduced the concept of predictive analytics to the Trust, which now has the capability to use crisis prediction as part of standard practice. Since this project ended, the Trust has been investigating how best to further implement and enhance the risk stratification model.

Contact details

For more information about this project, please contact applied.analytics@health.org.uk