Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.

Mental health problems in children and adolescents contribute to outcomes with long-lasting effects, such as suicidality, self-harm, violence towards others and risky behaviours. For each individual, predicting the likelihood of these consequences is challenging. Professionals use a range of methods to assess risk, including structured risk assessment tools. However, there is no standardised method for risk assessment and many tools lack a scientific evidence-base and have poor accuracy. The purpose of this project is to develop a risk prediction tool for adolescents attending mental health clinics.

Part of our Mental Health across the Life-course research theme



  • To use the CRIS database to develop a new tool to predict the risk of self harm in adolescents in secondary mental health care. 



  1. A review of the literature on tools to predict self harm in adolescents.
  2. Development of a tool to predict self harm in adolescents. 
  3. If the tool appears sufficiently robust, the next stage will be to engage with local health decision makers about how such a tool can be used to improve patient care.  


Expected Impact

This research will contribute to improving the health of young people accessing secondary mental health care services. Our work will help to refine the picture of the risk factors for self harm in young people accessing secondary mental health care.

The research will also progress the use of natural language processing of healthcare records.

Those accurately assessed as being of higher risk can benefit from being offered interventions, and those accurately assessed as being of lower risk may avoid unnecessary interventions, thereby avoiding associated harm and waste of resources. Structured tools have the potential to make risk assessment less subject to bias and susceptible to errors of individual clinicians. They can support discussions between patients, families and professionals about suicide risks.