ClinicalTrialsHub: Bridging Registries and Literature for Comprehensive Clinical Trial Access

2025-12-08

AI Summary

Clinical trial information is fragmented across registries (e.g., ClinicalTrials.gov) and scholarly literature (e.g., PubMed), impeding accessibility and evidence synthesis. Method: We introduce the first interactive retrieval platform integrating registry data with full-text biomedical literature. Leveraging large language models (GPT-4, Gemini-1.5-Pro), it performs end-to-end structured extraction of trial information from PubMed articles, natural language query translation, and traceable question answering—while deeply aligning extracted entities with ClinicalTrials.gov metadata. Contribution/Results: Compared to registry-only approaches, our platform increases coverage of structured trial data by 83.8%. Rigorous evaluation—including clinical expert assessment and automated metrics—demonstrates significant improvements in information completeness, accuracy, and usability. The system delivers trustworthy, evidence-based decision support for patients, clinicians, researchers, and policymakers.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: Information Extraction
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

We present ClinicalTrialsHub, an interactive search-focused platform that consolidates all data from ClinicalTrials.gov and augments it by automatically extracting and structuring trial-relevant information from PubMed research articles. Our system effectively increases access to structured clinical trial data by 83.8% compared to relying on ClinicalTrials.gov alone, with potential to make access easier for patients, clinicians, researchers, and policymakers, advancing evidence-based medicine. ClinicalTrialsHub uses large language models such as GPT-5.1 and Gemini-3-Pro to enhance accessibility. The platform automatically parses full-text research articles to extract structured trial information, translates user queries into structured database searches, and provides an attributed question-answering system that generates evidence-grounded answers linked to specific source sentences. We demonstrate its utility through a user study involving clinicians, clinical researchers, and PhD students of pharmaceutical sciences and nursing, and a systematic automatic evaluation of its information extraction and question answering capabilities.

Problem

• Integrates trial data from ClinicalTrials.gov and PubMed articles
• Extracts structured trial information using large language models
• Provides search and question-answering for evidence-based medicine

Innovation

• Integrates ClinicalTrials.gov with PubMed using large language models
• Automatically extracts structured trial data from full-text research articles
• Translates queries into database searches and provides attributed question-answering