CohortFlow: A Steerable Clinical Cohort Curation Agent with Localized Semantic Correction
中文摘要
CohortFlow是一个可引导的临床队列筛选智能体,利用局部语义修正和持久化执行图,无需重复处理即可高效更新筛选标准。
English Summary
CohortFlow is a steerable agent for clinical cohort curation that efficiently updates eligibility criteria via localized semantic corrections and persistent execution graphs.
arXiv:2610.36100v1 Announce Type: new Abstract: Language model agents for clinical cohort curation should accommodate evolving eligibility criteria without repeatedly processing unchanged requirements. We introduce CohortFlow, a steerable agent that represents natural language corrections as localized updates to a structured cohort specification and reconciles them with a persistent execution graph. Explicitly recorded semantic dependencies enable affected computations to be selectively invalidated while preserving valid prior results. On 100 scenarios derived from clinical-trial eligibility criteria, comprising 126 correction turns, localized steering achieves 77.0% requirement micro-F1 versus 76.4% for full regeneration using the same 8B model, a small numerical advantage that is not statistically significant ($p=0.493$). It reduces mean correction latency by 64.8% after completion and 44.3% during execution, with 38.1% fewer model calls. In a separate proof-of-concept evaluation over MIMIC, all 13 cohort states execute successfully, while correction trajectories demonstrate selective preservation of unaffected computations and recomputation of changed or dependent nodes. Togethe…