The feasibility and implementation of a psychosis risk prediction algorithm (P Risk) for use in primary care


National Institute for Health (NIHR) Health Service & Delivery Research (HS&DR) Ref. NIHR130547.

What is the research question?

Can the P Risk prediction algorithm be implemented on Primary Care computers? What is the acceptability of P Risk to stakeholders?

What is the problem?

Psychosis is a serious, long-lasting mental illness. Symptoms include hallucinations and strange, fixed thoughts, called delusions. Treating psychosis costs the NHS about £2 billion per year. Psychosis can be devastating for sufferers and their families. Additionally, outcomes are often poor with many people becoming ill again after recovery. Only about 20% of people with psychosis are in paid employment and many have a poor quality of life. There is convincing evidence that shortening the duration of untreated psychosis improves outcomes but being able to identify at-risk patients has proved difficult. GPs have highlighted that it can be difficult to spot patients who are at risk of psychosis because many of the early signs are nonspecific, and the lack of care continuity means that small changes in the mental health of patients at risk of psychosis may be missed.


What is the aim of the research?

The study team has developed a risk prediction algorithm which produces a psychosis risk score using consultation history stored in the primary care computer system. The tool has been internally and externally validated and is statistically accurate. During this project, the study team will assess whether the tool works in the real world on GP computers and will collect the views of GPs and patients, as well as feedback from mental health staff, to determine the tool’s acceptability.


How will this be achieved?

The P Risk study team will work with the primary care medical records software provider to install P Risk on their software. The team will also collect data on the number of referrals for a psychosis assessment made by GPs in the Bristol and Camden and Islington ICB areas and the result of these referrals. The statistical accuracy of P Risk will also be investigated using ICB data. Focus groups and interviews will be held with clinicians and patients and their carers to explore their views on the acceptability and potential value and implications of using P Risk in general practice.


Who is leading the research?

Dr Sarah A Sullivan, Senior Research Fellow (Psychiatric Epidemiologist), Bristol Medical School (PHS).

Further information

For more information or to get involved with this project, please contact

The views expressed are those of the author(s) and not necessarily those of the NIHR or the Department of Health and Social Care.