JMIR Publications

ABSTRACT

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 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-premise bilingual LLM-based artificial intelligence agent system integrated with electronic health records (EHR) for automated clinical drafting.

Objective:

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

Methods:

The 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.

Results:

The resulting system processes emergency department discharge summaries and preanesthetic assessments with high evaluation scores across multiple clinical metrics while maintaining existing clinical workflows. The drafting process is automatically triggered, and medical records are 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 stakeholders, we could derive ways to address 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 healthcare institutions, paving the way for broader adoption of LLM-based solutions.