Two ways to work
with your own data.
An academic institution meets us in two roles, and they are different deals. You can run a study against an external comparator we assemble. You can contribute governed data and keep publishing rights over a structured layer built on your own records. Some labs do both.
A defensible comparator, on an academic budget.
A rigorous study rarely fails for want of a good question. It fails for want of a comparator the field will accept. We assemble a protocol-aligned external cohort with item-level traceability, and return documentation suitable for peer review and for regulatory scrutiny.
A comparator the field will accept.
We assemble a protocol-aligned external cohort matched to your inclusion and exclusion criteria, so a reviewer can interrogate its construction rather than take it on faith.
Traceability for the record.
Every derived endpoint carries a link to the source record it was drawn from. Provenance of this kind is what distinguishes a defensible comparator from a convenient one.
The academic trial is our beachhead.
The academic study is where we chose to begin, so a principal investigator receives genuine attention rather than the residual capacity of a larger commercial engagement.
- FDA 2023 (draft)
- Design and Conduct of Externally Controlled Trials for Drug and Biological Products.
- FDA Jan 2025 (draft)
- Use of AI to support regulatory decision-making, a seven-step credibility-assessment framework.
- EMA 2022
- Qualification of an AI method for sample-size reduction in Phase 2/3 trials with continuous outcomes.
Publish on your own data. We build the research infrastructure.
This is a barter, and the exchange is the crux of the deal, so we state it plainly. The lab gains analysis-ready data and publications at no cash cost. Sapien gains a commercial data foundation. The data itself never moves.
The data stays in place, inside the governance boundary. Only rights move across it: publishing and a query layer to the lab, commercial cohort rights to Sapien. Nobody sells raw records.
What the lab gives
On-site access to its clinical data, structured and de-identified in place by Sapien under a governed research key. The data never leaves the lab's servers.
What the lab keeps
Academic publishing rights and a trial-ready query layer over its own data, plus a longitudinal research cohort built from records it already holds.
What Sapien gets
Commercial rights to build external control arms and cohorts for sponsors from the structured data. We never sell raw records.
Why it is fair
The lab gets analysis-ready data and publications with zero infrastructure spend. Sapien gets a commercial data foundation. Nobody sells raw records, and nothing leaves the lab.
We will structure a research-ready cohort on one of your datasets at no cash cost, so you can see the value before any commitment.