Home / Current Issue / Paper 1724385
ReguVigil: An AI-Driven Framework for Real-Time Regulatory Compliance Automation in Clinical Trials
Subject area: Science,Engineering and Technology · Area of research: Artificial Intelligence, Machine Learning
Abstract
In the current process, when the FDA or EMA releases an updated safety guideline, trial-clinical staff need to read the document, determine the changes to the clinical guidance, modify their monitoring guidelines, and then check all enrolled patients against this. From our understanding, based on reported timelines, this process currently takes between ten to thirty days. During this period, patients continue to be monitored against the old criteria. We introduce ReguVigil – a system that accepts an updated guideline PDF file as an input, extracts structured monitoring guidelines using a large language model, stores these guidelines as versioned objects with complete diff history, and finally re-ranks the entire active patient population against the updated guidelines. In a 500-patient trial, the end-to-end processing pipeline can be designed to process the above process in under ninety seconds. The guideline processing pipeline includes a schema-validated rule engine and a hash-chained audit log for each rule change. The system complies with HIPAA and 21 CFR Part 11 standards. We discuss the architecture and provide a walkthrough of the seven steps of the pipeline. We also compare ReguVigil against prior work in provenance tracking, blockchain-based compliance auditing, and LLM-based rule extraction, and we set out a plan for evaluating the system.
Keywords
regulatory compliance; clinical trials; artificial intelligence; large language models; pharmacovigilance; audit trail; HIPAA; 21 CFR Part 11; rule engine; patient safety
References
[1] Rhodes C, Moore S, Clark K, Maffitt D, Perry J, Handzel T, et al. Regulatory compliance requirements for an open source electronic image trial management system. In: Proc. 32nd Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. (EMBC); 2010. p. 3475–3478.
[2] Clavin J, Joshi KP. Policy integrated blockchain to automate HIPAA Part 2 compliance. In: Proc. 2023 IEEE Int. Conf. Digital Health (ICDH); 2023. p. 307–314.
[3] Liu X, Liao Y, Zhang Z, Hu J, Huang L. Feature extraction and compliance classification of text files using large language models. IEEE Trans Comput Soc Syst. 2025;12(6):5106–5117.
[4] Hassani S. Enhancing legal compliance and regulation analysis with large language models. In: Proc. 2024 IEEE 32nd Int. Requirements Eng. Conf. (RE) - Doctoral Symposium; 2024. p. 507–511.
[5] U.S. Food and Drug Administration. FDA guidance documents. Available from: https://www.fda.gov/regulatory-information/search-fda-guidance-documents
[6] European Medicines Agency. Scientific guidelines. Available from: https://www.ema.europa.eu/en/human-regulatory-overview/research-development/scientific-guidelines
[7] Verschraegen C, et al. Assessment of academic effort for clinical trials among oncology faculty. The Ohio State University Comprehensive Cancer Center; Association of American Cancer Institutes.
[8] Getz KA. Characterizing the real cost of site regulatory compliance. Applied Clinical Trials. 2015;24(6/7):18.
[9] U.S. Department of Health and Human Services. HIPAA Security Rule. 45 CFR Parts 160 and 164.
[10] U.S. Food and Drug Administration. 21 CFR Part 11: Electronic Records; Electronic Signatures. Code of Federal Regulations.
How to cite this paper
@article{1724385,
author = {Shibu Chacko, Sathwik K Bhat, Nikhil N Kankatri, Gagan Shetty, Aniketh},
title = {ReguVigil: An AI-Driven Framework for Real-Time Regulatory Compliance Automation in Clinical Trials},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {10},
number = {4},
pages = {3872-3881},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1724385.pdf},
abstract = {In the current process, when the FDA or EMA releases an updated safety guideline, trial-clinical staff need to read the document, determine the changes to the clinical guidance, modify their monitoring guidelines, and then check all enrolled patients against this. From our understanding, based on reported timelines, this process currently takes between ten to thirty days. During this period, patients continue to be monitored against the old criteria. We introduce ReguVigil – a system that accepts an updated guideline PDF file as an input, extracts structured monitoring guidelines using a large language model, stores these guidelines as versioned objects with complete diff history, and finally re-ranks the entire active patient population against the updated guidelines. In a 500-patient trial, the end-to-end processing pipeline can be designed to process the above process in under ninety seconds. The guideline processing pipeline includes a schema-validated rule engine and a hash-chained audit log for each rule change. The system complies with HIPAA and 21 CFR Part 11 standards. We discuss the architecture and provide a walkthrough of the seven steps of the pipeline. We also compare ReguVigil against prior work in provenance tracking, blockchain-based compliance auditing, and LLM-based rule extraction, and we set out a plan for evaluating the system.},
keywords = {regulatory compliance; clinical trials; artificial intelligence; large language models; pharmacovigilance; audit trail; HIPAA; 21 CFR Part 11; rule engine; patient safety},
month = {October},
}