LibraryFamily 6 · Genomics & Precision Medicine
AI-assisted tumour-board genomic variant interpretation
Under reviewPilotDeveloping evidence
Undergoing in-depth clinical, technical and governance review.
Synthesises somatic + germline variants from next-generation sequencing into a ranked, evidence-backed recommendation for the multidisciplinary tumour board.
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
- Treatment planning
- Nature of AI output
- A recommendation
- Clinical specialty
- Oncology
- Care setting
- Hospital — outpatient
- Patient population
- Adult oncology patients with tumour-board indication for genomic testing.
- Intended use
- Synthesises somatic + germline variants from next-generation sequencing into a ranked, evidence-backed recommendation for the multidisciplinary tumour board.
Technology
- AI technique
- NLP / large language model, Classical machine learning
- Input data
- Genomic data, Clinical notes / free text
- Output type
- Recommendation
- Autonomy level
- Informs a human (advisory)
- Model provenance
- Vendor proprietary
- Model version
- insight-1.5
- Built on a general-purpose model
- Yes
Deployment
- Status
- Pilot
- Country
- Sweden
- Deployment date
- 2 April 2025
- Sites
- 1
Regulatory & governance
- EU AI Act risk tier
- High-risk
- High-risk basis
- Annex III use case
- Medical device
- No
- EU MDR class
- Not a device
- CE marking
- Not required
- FDA status
- Not applicable
- ISO 14971 risk class
- Medium
- GDPR processing basis
- Consent
- GDPR DPIA
- Completed
- Data identifiability
- Pseudonymised
- Explainability method
- Post-hoc
- Human oversight model
- Every recommendation is reviewed and approved by the tumour board before being acted on.
NICE evidence standards
- ESF tier
- Tier C — treat / diagnose / calculate risk
- Evidence category
- Category 2
Performance summary
- Headline metric
- AUC / AUROC
- Value
- 0.86
- Subgroup performance assessed
- Yes
- Known bias signals
- Genomic reference panels skew toward European ancestry; expansion underway.
Similar deployments
AILooking for close matches in the Library…
Evidence records
Studies and evaluations attached to this use case.
External validation
Sensitivity: 0.81
Population: External NGS cohort, 1.2k cases
Retrospective validation
AUC / AUROC: 0.86
Population: NGS oncology cohort, 2k cases
Contributors
- Deploying organisation
- [demo] Karolinska University Hospital · Hospital / health system · Sweden
- AI vendor
- [demo] Paige AI · United States
- Product name
- Paige Insight