Lightweight Retrieval-Augmented Generation and Large Language Model-Based Modeling for Scalable Patient-Trial Matching

TL;DR

This paper introduces a scalable, efficient patient-trial matching framework combining retrieval-augmented generation and large language models to handle long, heterogeneous EHRs with reduced computational costs.

Contribution

It presents a lightweight, modular approach that separates retrieval and modeling, enabling scalable clinical data processing with competitive accuracy.

Findings

Retrieval-based segment selection reduces computational load.

Frozen LLMs effectively encode structured clinical data.

Fine-tuning improves modeling of unstructured narratives.

Abstract

Patient-trial matching requires reasoning over long, heterogeneous electronic health records (EHRs) and complex eligibility criteria, posing significant challenges for scalability, generalization, and computational efficiency. Existing approaches either rely on full-document processing with large language models (LLMs), which is computationally expensive, or use traditional machine learning methods that struggle to capture unstructured clinical narratives. In this work, we propose a lightweight framework that combines retrieval-augmented generation and large language model-based modeling for scalable patient-trial matching. The framework explicitly separates two key components: retrieval-augmented generation is used to identify clinically relevant segments from long EHRs, reducing input complexity, while large language models are used to encode these selected segments into informative representations. These representations are further refined through dimensionality reduction and modeled using lightweight predictors, enabling efficient and scalable downstream classification. We evaluate the proposed approach on multiple public benchmarks (n2c2, SIGIR, TREC 2021/2022) and a real-world multimodal dataset from Mayo Clinic (MCPMD). Results show that retrieval-based information selection significantly reduces computational burden while preserving clinically meaningful signals. We further demonstrate that frozen LLMs provide strong representations for structured clinical data, whereas fine-tuning is essential for modeling unstructured clinical narratives. Importantly, the proposed lightweight pipeline achieves performance comparable to end-to-end LLM approaches with substantially lower computational cost.