LibraryFamily 17 · Research & Clinical Trials
Trial-matching for paediatric oncology
CuratedPilotEmerging evidence
Reviewed for completeness and published to the Library.
Cross-matches structured records, genomic markers and trial eligibility criteria to surface a prioritised list of candidate clinical trials per patient.
Plain-language summary
AIChoose an audience and generate a tailored summary on demand. The AI uses only what is on this page.
Clinical context
- Clinical problem
- Discover a research insight
- Point of care
- Back office
- Nature of AI output
- A prioritised list
- Clinical specialty
- Oncology
- Care setting
- Back office
- Patient population
- Children and young people newly diagnosed with cancer at the tertiary paediatric oncology centre.
- Intended use
- Cross-matches structured records, genomic markers and trial eligibility criteria to surface a prioritised list of candidate clinical trials per patient.
Technology
- AI technique
- NLP / large language model, Classical machine learning
- Input data
- Structured EHR data, Genomic data, Clinical notes / free text
- Output type
- Prioritisation / schedule
- Autonomy level
- Informs a human (advisory)
- Model provenance
- Research model
- Model version
- tmpo-1.1
- Built on a general-purpose model
- Yes
Deployment
- Status
- Pilot
- Country
- Sweden
- Deployment date
- 10 March 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
- Post-hoc
- Human oversight model
- Multidisciplinary tumour board reviews every match before approach.
NICE evidence standards
- ESF tier
- Tier A — system / service
- Evidence category
- —
Performance summary
- Headline metric
- Positive predictive value
- Value
- 0.71
- Subgroup performance assessed
- No
- Known bias signals
- Coverage skewed toward Northern-European genetic backgrounds; cohort expansion under way.
Similar deployments
AILooking for close matches in the Library…
Evidence records
Studies and evaluations attached to this use case.
Retrospective validation
Positive predictive value: 0.71
Population: Paediatric oncology trial screening, 1k candidates
Contributors
- Deploying organisation
- [demo] Karolinska University Hospital · Hospital / health system · Sweden
- AI vendor
- —
- Product name
- —