An audit trail that survives the submission cycle.
Per-cycle provenance and frozen rollup snapshots give the audit trail submissions need — with a deterministic statistical engine a regulator can replay months later from the same inputs.
Deterministic engine · frozen snapshots · full provenanceFrom disconnected tools to one sanctioned trail.
Same workflow, two states. Flip the switch to see what changes.
Live · re-runs with signed provenance
- Each division
- One sanctioned, living trail
- central
- The evidence base
- Re-runs on a schedule
- living
- Audit trail
- Signed and current each cycle
- provenance
Regulatory-grade synthesis, replayable on demand.
Build the comparison once, keep it current, and inspect every step — with a signed, replayable record at each stage.
Build the comparison once
- A systematic review and a network meta-analysis
- Anchored against every relevant comparator
- Defensible from the first submission
Re-runs on a schedule
- The whole pipeline re-runs on a cadence
- Flags when a new trial moves the result
- A signed record of what changed, each cycle
No black box
- Deterministic statistics — same inputs, same result
- Every estimate traces to its source study
- Change an assumption and re-run
A result a committee can reproduce.
We reproduced a published meta-analysis: 3 of 4 endpoints within 6%.
One analyst rebuilt a peer-reviewed meta-analysis end to end in 2 days. Pooled estimates for three of four endpoints landed within 6% of the published values, and the case study explains the fourth. The statistics are deterministic: the same inputs always give the same result.
Read the case studyComparisons a committee will accept
Pairwise and network meta-analysis, plus population-adjusted indirect comparisons, with certainty grading — every step inspectable.
- Network meta-analysis
- MAIC
- STC
- ML-NMR
- Custom methods
- GRADE certainty