Qualitative study on the use of prediction models in mental healthcare

  • Research type

    Research Study

  • Full title

    Qualitative study on the views of service users and clinicians on the use of clinical prediction models in mental healthcare

  • IRAS ID

    348173

  • Contact name

    Daniel Stahl

  • Contact email

    daniel.r.stahl@kcl.ac.uk

  • Sponsor organisation

    King's College London

  • Duration of Study in the UK

    1 years, 3 months, 0 days

  • Research summary

    Prediction models use information from many people such as age, gender, medical history, and test results, to predict how likely it is that an individual may develop a certain health condition or how likely a new treatment will work for them. These prediction models can be used to inform treatment decisions to personalise and improve health care. They have been successfully used in certain fields of medicine, but they have had limited success in the field of mental health. This has been in part due to the poor accuracy of models when applied to new settings, financial and logistical challenges to implementation, and the potential harms of using these prediction models. The aim of this project is to understand better what people think about these prediction models in the context of mental health, with the hope of informing the future development of prediction models, increasing the likelihood of their use in clinical care, and improving health care provision.

    Participants will be recruited from secondary mental health teams in the South London and Maudsley NHS Foundation Trust (SLaM). Eligible participants are (a) service users aged 18 years or older with a formal diagnosis of schizophrenia-spectrum disorders, bipolar disorder or personality disorder and accessing care at SLaM and (b) clinicians working directly with service users who have received these diagnoses. We will conduct one-hour long interviews with participants. This will involve a brief questionnaire and exploring their views on prediction models using a semi-structured topic guide. Interviews will be analysed by a qualitative method called reflexive thematic analysis, which can help identify and interpret patterns of meaning within the data. This study is funded by the Medical Research Council.

  • REC name

    North West - Greater Manchester South Research Ethics Committee

  • REC reference

    25/NW/0323

  • Date of REC Opinion

    14 Nov 2025

  • REC opinion

    Further Information Favourable Opinion