OnCo
ideasIdea

A global federated real-world evidence network at regulatory grade

Connect hospital records across countries so that questions about how treatments work in real patients can be answered in weeks without moving the data, to a standard regulators accept.

Real-world evidence is fragmented, of variable quality and rarely accepted for decisions beyond safety. Federated analytics (OHDSI, DARWIN EU, Flatiron-style curated networks) demonstrate feasibility. The proposal is a global federated oncology network: common data model with oncology extensions, automated quality scoring, pre-registered analysis protocols executed locally with only aggregates shared, external control arm generation for rare indications, and a regulatory framework specifying when network evidence can support label expansions, pricing revisions and post-approval commitments.

Hypothesis
Network-generated evidence supports at least ten regulatory or reimbursement decisions in five years and reproduces trial results in emulation studies with high fidelity.
Rationale
Trial emulation has shown real-world data can reproduce randomised results when design is rigorous; federation solves privacy and sovereignty and scale simultaneously.
What would test it
Run twenty pre-registered trial emulations across the network and compare with the trials; then submit external control evidence for a rare indication.
Maturity
early clinical
Who has to act
data
Cost to try
Large (over $50M)
Years to first evidence
4
Bottlenecks it attacks
  • Weak real-world evidence and registries · We do not reliably know what happens to patients after approval, so we cannot tell which drugs deliver in practice.
  • Data silos · Records, scans, genomes and outcomes sit in separate systems that cannot talk. Every patient's experience is lost to the next.

Connected

5top