Journal article 123 views 12 downloads
Machine learning for prediction of childhood mental health problems in social care
,
Katherine Parkin ,
Emma Rocheteau ,
Efthalia Massou,
Yasmin Friedmann,
Ann John ,
Rachel Sippy,
Pietro Liò,
Anna Moore
BJPsych Open, Volume: 11, Issue: 3, Start page: e86
Swansea University Author:
Ann John
-
PDF | Version of Record
© The Author(s), 2025. Published by Cambridge University Press on behalf of Royal College of Psychiatrists. This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (CC BY).
Download (875.2KB)
DOI (Published version): 10.1192/bjo.2025.32
Abstract
Background: Rates of childhood mental health problems are increasing in the UK. Early identification of childhood mental health problems is challenging but critical to children’s future psychosocial development. This is particularly important for children with social care contact because earlier ide...
| Published in: | BJPsych Open |
|---|---|
| ISSN: | 2056-4724 |
| Published: |
Royal College of Psychiatrists
2025
|
| Online Access: |
Check full text
|
| URI: | https://cronfa.swan.ac.uk/Record/cronfa69347 |
| Abstract: |
Background: Rates of childhood mental health problems are increasing in the UK. Early identification of childhood mental health problems is challenging but critical to children’s future psychosocial development. This is particularly important for children with social care contact because earlier identification can facilitate earlier intervention. Clinical prediction tools could improve these early intervention efforts. Aims: Characterise a novel cohort consisting of children in social care and develop effective machine learning models for prediction of childhood mental health problems. Method: We used linked, de-identified data from the Secure Anonymised Information Linkage Databank to create a cohort of 26 820 children in Wales, UK, receiving social care services. Integrating health, social care and education data, we developed several machine learning models aimed at predicting childhood mental health problems. We assessed the performance, interpretability and fairness of these models. Results: Risk factors strongly associated with childhood mental health problems included age, substance misuse and being a looked after child. The best-performing model, a gradient boosting classifier, achieved an area under the receiver operating characteristic curve of 0.75 (95% CI 0.73–0.78). Assessments of algorithmic fairness showed potential biases within these models. Conclusions: Machine learning performance on this prediction task was promising. Predictive performance in social care settings can be bolstered by linking diverse routinely collected data-sets, making available a range of heterogenous risk factors relating to clinical, social and environmental exposures. |
|---|---|
| Keywords: |
Mental health services, medical technology, community mental health teams, machine learning methods, precision medicine |
| College: |
Faculty of Medicine, Health and Life Sciences |
| Funders: |
All research at the Department of Psychiatry in the University of Cambridge is supported by the National Institute for Health and Care Research (NIHR) Cambridge Biomedical Research Centre (grant number BRC-1215-20014) and NIHR Applied Research Collaboration East of England. A.M. is funded through a UK Research and Innovation Future Leaders Fellowship and an Anna Freud fellowship. The Delphi study was funded by Medical Research Council Adolescent Engagement Awards (number MR/T046430/1). Data access and data linkage were funded by What Works for Children’s Social Care and Cambridgeshire and Peterborough NHS Foundation Trust. K.P. is funded by the NIHR School for Public Health Research (grant number PD-SPH-2015) and the NIHR Applied Research Collaboration East of England. |
| Issue: |
3 |
| Start Page: |
e86 |