Related Experiment Video
Updated: May 14, 2025
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Machine learning for prediction of childhood mental health problems in social care
Ryan Crowley1, Katherine Parkin2,3,4, Emma Rocheteau5
1New York University Grossman School of Medicine, New York, US.
Insights
Machine learning models show promise in predicting childhood mental health issues for children in social care. Linking diverse data sources improves prediction accuracy, aiding early intervention efforts for better psychosocial development.
Area of Science:
- Child and Adolescent Psychiatry
- Machine Learning in Healthcare
- Social Care Informatics
Background:
- Rising rates of childhood mental health problems in the UK necessitate early identification.
- Early intervention is critical for psychosocial development, especially for children in social care.
- Clinical prediction tools offer a potential avenue for improving early identification and intervention.
Purpose of the Study:
- To characterize a novel cohort of children receiving social care services.
- To develop and evaluate machine learning models for predicting childhood mental health problems.
- To assess the performance, interpretability, and fairness of developed predictive models.
Main Methods:
- Utilized linked, de-identified health, social care, and education data from Wales, UK.
- Created a cohort of 26,820 children accessing social care services.
- Developed and assessed multiple machine learning models for predicting mental health issues.
Main Results:
- Identified key risk factors: age, substance misuse, and being a looked-after child.
- The top-performing gradient boosting model achieved an AUC of 0.75 (95% CI 0.73-0.78).
- Algorithmic fairness assessments revealed potential biases in the predictive models.
Conclusions:
- Machine learning demonstrates promising performance for predicting childhood mental health problems in this cohort.
- Integrating diverse, routinely collected datasets enhances predictive accuracy in social care settings.
- Linking varied data sources provides a broader range of clinical, social, and environmental risk factors for improved prediction.
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.
More Related Videos
12:18A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
11:14A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
Published on: October 4, 2015
Related Concept Videos
01:30Socioemotional Development during Infancy
Primary Temperament Types
01:29Psychological and Sociocultural Causes of Schizophrenia
01:26Modeling in Therapy
Participant Modeling
Participant modeling involves therapists demonstrating calm and effective behaviors in...
01:19Autism Spectrum Disorder
These core symptoms manifest differently among individuals, ranging from mild to severe. The disorder's complexity extends beyond its clinical presentation, encompassing a diverse range of biological, cognitive, and sociocultural influences.