A Bilingual On-premise AI agent for Clinical Drafting: Seamless EHR integration in the Y-KNOT Project

Large Language Models (LLMs) have shown promise in reducing clinical documentation burden, yet their real-world implementation faces significant challenges, particularly in non-English speaking countries with strict data sovereignty requirements. Here we present Your-Knowledgeable Navigator of Treatment (Y-KNOT), the first successful implementation of an on-premise bilingual LLM-based artificial intelligence system integrated with electronic health records (EHR) for automated clinical documentation. In collaboration with multiple stakeholders, we developed and deployed Y-KNOT at a tertiary hospital in South Korea. The system processes emergency department discharge summaries and pre-anesthetic assessments with high evaluation scores across multiple clinical metrics while maintaining FHIR compliance for scalability. Our study demonstrates a practical framework for implementing LLM-based clinical documentation systems in resource-constrained healthcare settings while addressing key challenges of data security, bilingual requirements, and workflow integration.