EUVIMEDObjevte EUVIMED
Open access

A Bilingual On-Premises AI Agent for Clinical Drafting: Implementation Report of Seamless Electronic Health Records Integration in the Y-KNOT Project

Hanjae Kim iD, So-Yeon Lee iD, Seng Chan You iD, Sookyung Huh iD, Jai-Eun Kim iD, Sung-Tae Kim iD, Dong-Ryul Ko iD, Ji Hoon Kim iD, Jae Hoon Lee iD, Joon Seok Lim iD, Moo Suk Park iD, Kang Young Lee iD

JMIR Medical Informatics · 2025-11-24 · 13 · e76848-e76848

DOI: 10.2196/76848 ↗

At a glance

Journal article in JMIR Medical Informatics, published online on 2025-11-24. Written by Hanjae Kim and 11 co-authors. Institution: Department of Biomedical Systems Informatics, College of Medicine, Yonsei University, 50-1, Yonsei-Ro, Seodaemun-gu, Seoul, 03722, Republic of Korea,…. Major MEDLINE topics: Electronic Health Records, Artificial Intelligence, Multilingualism. Cited 11 times so far (Crossref); 40 references. The full text is freely available in PubMed Central. Funded by: NCCDPHP CDC HHS.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Background

Large language models (LLMs) have shown promise in reducing clinical documentation burden, yet their real-world implementation remains rare. Especially in South Korea, hospitals face several unique challenges, such as strict data sovereignty requirements and operating in environments where English is not the primary language for documentation. Therefore, we initiated the Your-Knowledgeable Navigator of Treatment (Y-KNOT) project, aimed at developing an on-premises bilingual LLM-based artificial intelligence (AI) agent system integrated with electronic health records (EHRs) for automated clinical drafting.

Objective

We present the Y-KNOT project and provide insights into implementing AI-assisted clinical drafting tools within constraints of health care system.

Methods

This project involved multiple stakeholders and encompassed three simultaneous processes: LLM development, clinical co-development, and EHR integration. We developed a foundation LLM by pretraining Llama3-8B with Korean and English medical corpora. During the clinical co-development phase, the LLM was instruction-tuned for specific documentation tasks through iterative cycles that aligned physicians’ clinical requirements, hospital data availability, documentation standards, and technical feasibility. The EHR integration phase focused on seamless AI agent incorporation into clinical workflows, involving document standardization, trigger points definition, and user interaction optimization. Implementation (Results) The resulting system processes emergency department discharge summaries and preanesthetic assessments while maintaining existing clinical workflows. The drafting process is automatically triggered by specific events, such as scheduled batch jobs, with medical records automatically fed into the LLM as input. The agent is built on premises, locating all the architecture inside the hospital.

Conclusions

The Y-KNOT project demonstrates the first seamless integration of an AI agent into an EHR system for clinical drafting. In collaboration with various clinical and administrative teams, we could promptly implement an LLM while addressing key challenges of data security, bilingual requirements, and workflow integration. Our experience highlights a practical and scalable approach to utilizing LLM-based AI agents for other health care institutions, paving the way for broader adoption of LLM-based solutions.

Subjects

MeSH terms (MEDLINE)

Electronic Health RecordsArtificial IntelligenceMultilingualismHumansRepublic of KoreaDocumentation

Author keywords

artificial intelligence agentdocumentationelectronic health recordsinsightslarge language models

Authors and institutions

  • Department of Biomedical Systems Informatics, College of Medicine, Yonsei University, 50-1, Yonsei-Ro, Seodaemun-gu, Seoul, 03722, Republic of Korea, 82 22282500.
  • PHI Digital Healthcare, Seoul, Republic of Korea.
  • Yonsei Institute for Digital Health, Yonsei University, Seoul, Republic of Korea.
  • Department of Medical Records, Severance Hospital, Yonsei University Health System, Seoul, Republic of Korea.
  • Saltlux Inc, Seoul, Republic of Korea.
  • Department of Emergency Medicine, College of Medicine, Yonsei University, Seoul, Republic of Korea.

ORCID profiles: Hanjae Kim, So-Yeon Lee, Seng Chan You, Sookyung Huh, Jai-Eun Kim, Sung-Tae Kim, Dong-Ryul Ko, Ji Hoon Kim, Jae Hoon Lee, Joon Seok Lim, Moo Suk Park, Kang Young Lee

Funding

  • NCCDPHP CDC HHS

Cite

APA

Kim, H., Lee, S. Y., You, S. C., Huh, S., Kim, J. E., Kim, S. T., Ko, D. R., Kim, J. H., Lee, J. H., Lim, J. S., Park, M. S., & Lee, K. Y. (2025). A Bilingual On-Premises AI Agent for Clinical Drafting: Implementation Report of Seamless Electronic Health Records Integration in the Y-KNOT Project. JMIR Medical Informatics, 13, e76848-e76848. https://doi.org/10.2196/76848

Vancouver

Kim H, Lee SY, You SC, Huh S, Kim JE, Kim ST, et al. A Bilingual On-Premises AI Agent for Clinical Drafting: Implementation Report of Seamless Electronic Health Records Integration in the Y-KNOT Project. JMIR Medical Informatics. 2025;13:e76848-e76848. doi:10.2196/76848

BibTeX
@article{Kim2025,
  author = {Kim, Hanjae and Lee, So-Yeon and You, Seng Chan and Huh, Sookyung and Kim, Jai-Eun and Kim, Sung-Tae and Ko, Dong-Ryul and Kim, Ji Hoon and Lee, Jae Hoon and Lim, Joon Seok and Park, Moo Suk and Lee, Kang Young},
  title = {A Bilingual On-Premises AI Agent for Clinical Drafting: Implementation Report of Seamless Electronic Health Records Integration in the Y-KNOT Project},
  journal = {JMIR Medical Informatics},
  year = {2025},
  volume = {13},
  pages = {e76848--e76848},
  doi = {10.2196/76848}
}
Start for free →