TrialMatchAI: An End-to-End AI-powered Clinical Trial Recommendation System to Streamline Patient-to-Trial Matching

2025/05/13 by Abdallah, Majd, Nakken, Sigve, Bierkens, Mariska +11
#Artificial Intelligence (cs.AI) #FOS: Biological sciences #FOS: Computer and information sciences #Machine Learning (cs.LG) #Quantitative Methods (q-bio.QM)

paper · doi:10.48550/arxiv.2505.08508

Abstract

Patient recruitment remains a major bottleneck in clinical trials, calling for scalable and automated solutions. We present TrialMatchAI, an AI-powered recommendation system that automates patient-to-trial matching by processing heterogeneous clinical data, including structured records and unstructured physician notes. Built on fine-tuned, open-source large language models (LLMs) within a retrieval-augmented generation framework, TrialMatchAI ensures transparency and reproducibility and maintains a lightweight deployment footprint suitable for clinical environments. The system normalizes biomedical entities, retrieves relevant trials using a hybrid search strategy combining lexical and semantic similarity, re-ranks results, and performs criterion-level eligibility assessments using medical Chain-of-Thought reasoning. This pipeline delivers explainable outputs with traceable decision rationales. In real-world validation, 92 percent of oncology patients had at least one relevant trial retrieved within the top 20 recommendations. Evaluation across synthetic and real clinical datasets confirmed state-of-the-art performance, with expert assessment validating over 90 percent accuracy in criterion-level eligibility classification, particularly excelling in biomarker-driven matches. Designed for modularity and privacy, TrialMatchAI supports Phenopackets-standardized data, enables secure local deployment, and allows seamless replacement of LLM components as more advanced models emerge. By enhancing efficiency and interpretability and offering lightweight, open-source deployment, TrialMatchAI provides a scalable solution for AI-driven clinical trial matching in precision medicine.

Citations

• LLM-Match: An Open-Sourced Patient Matching Model Based on Large Language Models and Retrieval-Augmented Generation
• HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs
• Phi-4 Technical Report
• Gemma 2: Improving Open Language Models at a Practical Size
• Panacea: A foundation model for clinical trial search, summarization, design, and recruitment
• A Survey on Knowledge Distillation of Large Language Models
• M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation
• Distilling Large Language Models for Matching Patients to Clinical Trials
• An LLM Compiler for Parallel Function Calling
• GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer
• QLoRA: Efficient Finetuning of Quantized LLMs
• GPT-4 Technical Report
• BNAI, NO-TOKEN, and MIND-UNITY: Pillars of a Systemic Revolution in Artificial Intelligence
• Review of deep learning: concepts, CNN architectures, challenges, applications, future directions
• Self-Alignment Pretraining for Biomedical Entity Representations
• COMPOSE: Cross-Modal Pseudo-Siamese Network for Patient Trial Matching
• Language Models are Few-Shot Learners
• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• Biomedical Entity Representations with Synonym Marginalization
• A generic rule-based system for clinical trial patient selection
• Attention Is All You Need
• Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs

Related

• MatchMiner-AI: An Open-Source Solution for Cancer Clinical Trial Matching
• End-To-End Clinical Trial Matching with Large Language Models
• Toward an AI Reasoning-Enabled System for Patient-Clinical Trial Matching
• A systematic review of trial-matching pipelines using large language models
• Real-world validation of a multimodal LLM-powered pipeline for High-Accuracy Clinical Trial Patient Matching leveraging EHR data