AI

VirtualTrialHarness: Coordinating Agentic Operationalization of Virtual Trial Protocols Across Complex Clinical Schemas

Read full article at source ↗

Based on a feed excerpt; full article content has not been acquired. Source evidence retrieved 05/11/2026, 05:03:25 UTC.

Briefings

VirtualTrialHarness (VTHarness) is an agent framework that coordinates virtual-trial operationalization by selecting reusable procedural skills for each workflow stage and using explicit contracts to maintain consistent study decisions. VTHarness was tested across three complex synthetic environments, achieving 95.1% success in producing required cohort outputs matching references after requirement clarification, compared to 60.4% using standard retrieval. The framework improved source recovery across three language models and increased source overlap with analyst code in 13 Mayo Clinic cases. Site-specific adaptation enabled reference-matched cohort execution across eight MIMIC-IV tasks.

Key points

• VTHarness successfully produced all required cohort outputs matching references in 95.1% of workflows after requirement clarification.
• VTHarness improved source recovery across three language models and increased source overlap with analyst code in 13 Mayo Clinic cases.

Context

Virtual trials use routinely collected clinical data to evaluate treatment strategies, but translating a study protocol into an executable analysis requires determining how clinical concepts and study requirements should be represented in the available data and applied consistently across the workflow. This finding supports coordinating procedural guidance with workflow decisions to improve virtual-trial implementation across complex clinical schemas.

Limitations

Evidence is limited to three complex synthetic environments and eight MIMIC-IV tasks. Results are based on a single preprint (arXiv:2611.05551v1) from November 2026, with no additional validation or longitudinal data provided.

Generated by Bittrees-hosted qwen35-2b sha256:aaf42c8b7c3c on 05/11/2026, 05:05:48 UTC. Based on publisher-provided feed evidence; may not cover the full original article. Check the source for details.

View archived briefing on IPFS
bafybeihxtluszcfxcph4odz6nnu4whexn3y57ctqp2wbi2cftifwv5cvcy