Cohort Discovery: A Survey on LLM-Assisted Clinical Trial Recruitment

2025-06-18

AI Summary

Clinical trial patient matching suffers from methodological fragmentation, closed-model architectures, and a lack of standardized evaluation. Method: This work formally redefines the task as “cohort discovery” and introduces a generalizable, large language model (LLM)-centric paradigm for AI-assisted recruitment. It establishes the first LLM-specific evaluation framework, exposes critical flaws in existing benchmarks, and proposes standardized remediation strategies; designs a cross-modal reasoning approach integrating structured electronic health records (EHRs) and unstructured clinical narratives; and systematically identifies three core bottlenecks—data silos, evaluation inaccuracies, and weak interpretability. Contribution/Results: We propose reproducible benchmark design principles and six concrete research directions. Our framework advances clinical recruitment from bespoke, opaque solutions toward a generalizable, evaluable, and interpretable LLM-powered paradigm.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

Abstract

Recent advances in LLMs have greatly improved general-domain NLP tasks. Yet, their adoption in critical domains, such as clinical trial recruitment, remains limited. As trials are designed in natural language and patient data is represented as both structured and unstructured text, the task of matching trials and patients benefits from knowledge aggregation and reasoning abilities of LLMs. Classical approaches are trial-specific and LLMs with their ability to consolidate distributed knowledge hold the potential to build a more general solution. Yet recent applications of LLM-assisted methods rely on proprietary models and weak evaluation benchmarks. In this survey, we are the first to analyze the task of trial-patient matching and contextualize emerging LLM-based approaches in clinical trial recruitment. We critically examine existing benchmarks, approaches and evaluation frameworks, the challenges to adopting LLM technologies in clinical research and exciting future directions.

Problem

• LLM-assisted clinical trial recruitment lacks adoption
• Matching trials and patients requires knowledge aggregation
• Existing LLM approaches use weak evaluation benchmarks

Innovation

• LLMs for clinical trial-patient matching
• Consolidating structured and unstructured data
• Analyzing benchmarks and evaluation frameworks