Healthcare Standards Matrix Automation with Instruction-Tuned LLaMA Models
Keywords:
LLaMA-3, healthcare compliance, HIPAA, GDPR, HL7 FHIR, instruction-tuning, reinforcement learningAbstract
The study trains LLaMA-3 models to create healthcare compliance matrices. The system automatically converts provisions to HIPAA, GDPR, and HL7 FHIR for rigorous compliance assessments. Audit logs reveal non-conformities and compliance gaps. To ensure model output dependability and domain relevance, human-in-the-loop reinforcement learning (RLHF) refines mappings and remedial recommendations using expert feedback. Experts subjectively and statistically evaluate this approach for accuracy, memory, and standards-to-clause alignment. LLM automation enhances healthcare compliance paperwork efficiency, accuracy, and traceability over humans. Multi-jurisdictional compliance management is auditable and scalable with massive language models and regulatory technologies.
Downloads
References
S. J. Krasner, M. L. Kruse, and A. L. Shao, “Automating compliance documentation in healthcare: Leveraging NLP for HIPAA and GDPR alignment,” Journal of Biomedical Informatics, vol. 128, pp. 104–122, 2022.
D. Voigt and A. von dem Bussche, The EU General Data Protection Regulation (GDPR): A Practical Guide. Cham, Switzerland: Springer, 2017.
U.S. Department of Health and Human Services, Health Insurance Portability and Accountability Act (HIPAA) Privacy and Security Rules, 45 CFR Parts 160, 162, and 164, 2013.
Health Level Seven International, HL7 FHIR Release 4: Fast Healthcare Interoperability Resources, Ann Arbor, MI, 2020.
S. Touvron et al., “LLaMA 2: Open foundation and fine-tuned chat models,” arXiv preprint arXiv:2307.09288, 2023.
T. Ouyang et al., “Training language models to follow instructions with human feedback,” Advances in Neural Information Processing Systems (NeurIPS), vol. 35, pp. 27730–27744, 2022.
L. Wang, R. S. Miotto, and J. T. Rhee, “Natural language processing for regulatory document comprehension in healthcare,” IEEE Journal of Biomedical and Health Informatics, vol. 27, no. 1, pp. 56–67, 2023.
P. Patel, M. Sundararajan, and E. Chang, “AI-driven compliance mapping for healthcare data governance,” IEEE Transactions on Emerging Topics in Computing, vol. 11, no. 2, pp. 313–328, 2023.
A. Radford et al., “Language models are few-shot learners,” Advances in Neural Information Processing Systems (NeurIPS), vol. 33, pp. 1877–1901, 2020.
M. Chen et al., “Evaluating large language models trained on code,” arXiv preprint arXiv:2107.03374, 2021.
S. Reddy, M. Aggarwal, and K. K. Singh, “Explainable AI for legal and regulatory compliance,” Artificial Intelligence and Law, vol. 31, no. 1, pp. 27–49, 2023.
J. Gao, M. Chen, and D. Zhang, “Human-in-the-loop reinforcement learning for domain-specific NLP models,” ACM Transactions on Intelligent Systems and Technology, vol. 14, no. 3, pp. 1–25, 2023.
N. H. Honnibal, I. Montani, and T. Wolf, “Industrial-strength NLP for healthcare compliance applications,” Proceedings of the Association for Computational Linguistics (ACL), pp. 1225–1238, 2021.
R. Bommasani et al., “On the opportunities and risks of foundation models,” arXiv preprint arXiv:2108.07258, 2021.
S. Zhang, K. Dong, and E. Rosenthal, “Privacy-preserving AI for medical data compliance,” IEEE Access, vol. 11, pp. 8123–8142, 2023.
C. Chen, R. Xu, and T. S. Subramanian, “Federated learning for compliance data governance across multi-institutional healthcare systems,” IEEE Transactions on Neural Networks and Learning Systems, vol. 35, no. 4, pp. 4558–4573, 2024.
D. Liang, P. Kumar, and L. Zhao, “A survey on regulatory technology (RegTech): Applications, challenges, and opportunities,” IEEE Access, vol. 10, pp. 88234–88256, 2022.
M. Al-Khazraji, A. B. Dastjerdi, and S. Dustdar, “AI-powered governance, risk, and compliance (GRC) platforms: Architecture and applications,” IEEE Internet Computing, vol. 27, no. 2, pp. 18–29, 2023.
S. L. Pan, J. Lin, and H. Song, “Toward explainable compliance auditing using large language models,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 1, pp. 1432–1441, 2024.
K. Lee, M. Hu, and R. Shrestha, “RLHF for high-stakes AI systems: A survey and healthcare applications,” IEEE Transactions on Artificial Intelligence, vol. 5, no. 6, pp. 1123–1139, 2024.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
