Skip to main content
Search

# MedCheckpoint

1 related articles

Subscribe to updates
  1. medRxiv

    Postmarketing pharmacovigilance handed to a multi-agent system: MedCheckpoint logs zero misleading failures on seven data-limited trap questions

    A University of Hong Kong team built MedCheckpoint, a multi-agent system that carries postmarketing pharmacovigilance from a natural-language question to an auditable observational analysis. The system locks core study-design parameters before execution, delegates patient-level statistics to human-written deterministic tools, and uses checkpoint rules to abort infeasible analyses. On a 54-question drug-safety benchmark over a 2.7-million-person simulated EHR, three independent LLM judges gave it overall means of 4.81 to 4.88, above two coding-agent baselines; across 21 runs on seven trap questions with known data limitations, the judges found no misleading failures.

You’re all caught up