Skip to main content
AIH Lab
Sign in
LibraryFamily 7 · Mental Health & Neurology

AI triage for child & adolescent mental health

Under reviewPilotDeveloping evidence

Undergoing in-depth clinical, technical and governance review.

Collects symptom information conversationally and routes the referral to the right CAMHS clinical team, escalating safety risks to a clinician in under five minutes.

Plain-language summary

AI

Choose an audience and generate a tailored summary on demand. The AI uses only what is on this page.

Clinical context
Clinical problem
Support communication
Point of care
Triage
Nature of AI output
A classification
Clinical specialty
Psychiatry
Care setting
Community care
Patient population
Adolescents (13–17) self-referring to a child and adolescent mental-health service.
Intended use
Collects symptom information conversationally and routes the referral to the right CAMHS clinical team, escalating safety risks to a clinician in under five minutes.
Technology
AI technique
NLP / large language model
Input data
Patient-reported data
Output type
Classification
Autonomy level
Human in the loop (human acts)
Model provenance
Vendor proprietary
Model version
care-1.3
Built on a general-purpose model
Yes
Deployment
Status
Pilot
Country
Sweden
Deployment date
1 February 2025
Sites
1
Regulatory & governance
EU AI Act risk tier
Limited risk
High-risk basis
Not applicable
Medical device
No
EU MDR class
Not a device
CE marking
Not required
FDA status
Not applicable
ISO 14971 risk class
Low
GDPR processing basis
Consent
GDPR DPIA
Completed
Data identifiability
Pseudonymised
Explainability method
None
Human oversight model
A clinician reviews every referral before the first appointment; risk responses raise an immediate human alert.
NICE evidence standards
ESF tier
Tier B — inform / monitor
Evidence category
Category 2
Performance summary
Headline metric
Accuracy
Value
0.88
Subgroup performance assessed
Yes
Known bias signals
Reduced sensitivity for under-15s — flagged for additional validation.

Similar deployments

AI
Looking for close matches in the Library…
Safety signals
Post-deployment concerns flagged by clinicians, patients or monitoring (proposal §3.7). High or critical signals re-enter a validated use case into maturation automatically.

  • Clinician reports a misrouted referral for an adolescent with neurodivergent presentation.

    Raised 17 May 2026, 21:01

    LowInvestigating

Evidence records

Studies and evaluations attached to this use case.

  • Retrospective validation

    Sensitivity: 0.92

    Population: Retrospective comparison vs senior clinician triage, 1.5k cases

    Subgroup: female

  • Prospective observational

    Accuracy: 0.88

    Population: CAMHS self-referral pilot, 8k referrals

Contributors

Deploying organisation
[demo] Karolinska University Hospital · Hospital / health system · Sweden
AI vendor
[demo] Limbic · United Kingdom
Product name
Limbic Care