Verification register Bio, Health & Neuro
Current reading
The readiness gap, in one scan
AI-assisted assembly · derived results
- Claimed
- 55
- Reported
- 55
- Verified
- 50
- Gap
- +5
Public ambition and stated capability
Observed practitioner reporting
Independently supported evidence
Claimed minus verified
Evidence strength Growing
Decision
What the current evidence supports
Human editorial judgment · 2026-06-28
Track; not yet
- Why
- Reported AUC uplift on a hard subgroup (no-nodule scans 0.76 vs 0.64), MIT-licensed and reproducible, peer-reviewed in CHEST, but retrospective-only validation, no clearance, and an immature two-stage codebase keep it at evaluation stage.
- Next
- Pilot the open-source Sybil-Epi against an internal retrospective LDCT cohort to reproduce the reported AUC uplift over Sybil; assess clinical-variable data availability before any prospective consideration.
Constraints
Blockers
No named blocker is present in the current public projection.
Evidence summary
Derived counts
AI-assisted assembly
- Total
- 7
- Tier 1
- 1
- Tier 2
- 5
- Tier 3
- 1
- Supports
- 4
- Contradicts
- 1
- Context
- 2
- Latest observed
- 2026-03-01
Counts and dates only. Raw signals, private excerpts, trust records, and internal corpus material are not published here.
Publication record
Revisions
Initial public reading
This is the initial public reading. No earlier readiness change is recorded.