AI-assisted Protocol Information Extraction For Improved Accuracy and Efficiency in Clinical Trial Workflows
Not on the map. Why?
Abstract (arXiv)
Increasing clinical trial protocol complexity, amendments, and challenges around knowledge management create significant burden for trial teams. Structuring protocol content into standard formats has the potential to improve efficiency, support documentation quality, and strengthen compliance. We evaluate an Artificial Intelligence (AI) system using generative LLMs with Retrieval-Augmented Generation (RAG) for automated clinical trial protocol information extraction. We compare the extraction accuracy of our clinical-trial-specific RAG process against that of publicly available (standalone) LLMs. We also assess the operational impact of AI-assistance on simulated extraction Clinical Research Coordinator (CRC) workflows. Our RAG process shows higher extraction accuracy (89.0%) than standalone LLMs with fine-tuned prompts (62.6%) against expert-supported reference annotations. In simulated extraction workflows, AI-assisted tasks are completed 40% faster, are rated as less cognitively demanding and are strongly preferred by users. While expert oversight remains essential, this suggests that AI-assisted extraction can enable protocol intelligence at scale, motivating the integration of similar methodologies into real-world clinical workflows to further validate its impact on feasibility, study start-up, and post-activation monitoring.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 16 of its 45 references that are in the map. First posted on arXiv 19 Jan 2026.
Builds on
16 of 45 references.
References · 16
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
- 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
- 2024A Survey on LLM-as-a-Judgecited by 1,384
- 2025PaperBench: Evaluating AI's Ability to Replicate AI Researchcited by 286
- 2019Image-based table recognition: data, model, and evaluationcited by 233
- 2023Large language models can accurately predict searcher preferencescited by 129
- 2021PubTables-1M: Towards comprehensive table extraction from unstructured documentscited by 122
- 2024Searching for Best Practices in Retrieval-Augmented Generationcited by 83
- 2023Visual cognition in multimodal large language modelscited by 38
- 2024Efficient Solutions For An Intriguing Failure of LLMs: Long Context Window Does Not Mean LLMs Can Analyze Long Sequences Flawlesslycited by 23
- 2025Enhancing Retrieval-Augmented Generation: A Study of Best Practicescited by 22
- 2021Clinical Trial Information Extraction with BERTcited by 7
4 more
- 2025A Case Study of Scalable Content Annotation Using Multi-LLM Consensus and Human Reviewcited by 7
- 2025Beyond Pointwise Scores: Decomposed Criteria-Based Evaluation of LLM Responsescited by 7
- 2024From RAGs to riches: Utilizing large language models to write documents for clinical trialscited by 6
- 2024Clinical Trials Protocol Authoring using LLMscited by 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Retrieval-Augmented LLMs for Evidence Localization in Clinical Trial Recruitment from Longitudinal EHR Narratives
- 2026Configurable Clinical Information Extraction with Agentic RAG: What Works, What Breaks, and Why
- 2025TrialMatchAI: An End-to-End AI-powered Clinical Trial Recommendation System to Streamline Patient-to-Trial Matching
- 2025A Survey on LLM-Assisted Clinical Trial Recruitment
- 2025Rethinking Retrieval-Augmented Generation for Medicine: A Large-Scale, Systematic Expert Evaluation and Practical Insights
- 2025Leveraging LLMs for Structured Data Extraction from Unstructured Patient Records
- 2024Retrieval-Reasoning Large Language Model-based Synthetic Clinical Trial Generation
- 2025Retrieval-Augmented Generation in Medicine: A Scoping Review of Technical Implementations, Clinical Applications, and Ethical Considerations