Neurosymbolic Clinical Trial Matching via LLM-Driven Abduction and Logical Verification

2026-06-18

AI Summary

Clinical trial matching faces challenges due to the lack of verifiable certainty in large language models and the difficulty of purely symbolic approaches in handling noisy patient records. This work proposes αNeSy-CTM, a novel neuro-symbolic framework that introduces abductive reasoning into clinical trial matching for the first time. By integrating the linguistic and world knowledge of large language models with formal logical verification and an auditable hybrid reasoning architecture, αNeSy-CTM significantly enhances matching accuracy, specificity, and robustness. The method achieves a relative performance improvement of up to 30% over zero-shot baselines, demonstrating the efficacy of neuro-symbolic approaches in automating clinical trial matching and offering complementary advantages to chain-of-thought reasoning.

Abstract

Large Language Models (LLMs) offer a promising path to automate Clinical Trial Matching (CTM), but still struggle with the deterministic verification required for complex eligibility criteria. Conversely, purely symbolic methods provide formal rigour but break down when faced with incomplete patient records and noisy clinical evidence. To bridge this gap, we investigate a hybrid framework for CTM combining LLMs with logical verification. In particular, we introduce an abductive neurosymbolic CTM framework (αNeSy-CTM), which leverages the linguistic and world knowledge in LLMs to support reasoning over noisy and underspecified clinical text. Extensive evaluation demonstrates that αNeSy-CTM substantially outperforms standalone LLM baselines, achieving up to 30% relative improvement over zero-shot baselines. In addition, our analyses confirm the impact of abductive reasoning on CTM, with αNeSy-CTM exhibiting improved accuracy, specificity, and robustness over a non-abductive neurosymbolic setting. Furthermore, αNeSy-CTM and Chain-of-Thought (CoT) reasoning prove highly complementary, highlighting the potential for a hybrid routing policy. Ultimately, this paper demonstrates the impact of neurosymbolic methods for automating CTM, providing a path toward the next generation of auditable, LLM-driven clinical applications.

Problem

• Clinical Trial Matching
• Eligibility Criteria
• Neurosymbolic Reasoning
• Abductive Reasoning
• Large Language Models

Innovation

• neurosymbolic reasoning
• abductive inference
• clinical trial matching
• large language models
• logical verification