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

VirtualTrialHarness (VTHarness), an agent framework that coordinates virtual-trial operationalization by selecting reusable procedural skills for each workflow stage and enforcing explicit contracts across stages, produced all required cohort outputs matching references in 95.1% of workflows after requirement clarification, compared with 60.4% for retrieval from the same procedural corpus, according to the arXiv paper announcing it. The framework was tested across three complex synthetic environments, and procedural skills 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, and the framework supported investigator review of cohort construction and endpoint analysis within the Mayo Clinic Virtual Trials Program.

arXiv:2611.05551v1 Announce Type: new Abstract: 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. These decisions depend on local data representations and operational conventions and can involve source selection, patient and encounter identity, linkage, and temporal interpretation. Here we introduce VirtualTrialHarness VTHarness , an agent framework that coordinates virtual-trial operationalization by selecting reusable procedural skills for each workflow stage and uses explicit contracts to maintain consistent study decisions across stages. We also introduce VTBenchmark for evaluating source selection and cohort construction. Across three complex synthetic environments, VTHarness successfully produced all required cohort outputs matching the references in 95.1% of workflows after requirement clarification, compared with 60.4% using retrieval from the same procedural corpus. Procedural skills 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. Within the Mayo Clinic Virtual Trials Program, the framework supported investigator review of cohort construction and endpoint analysis. These findings support coordinating procedural guidance with workflow decisions to improve virtual-trial implementation across complex clinical schemas.