Seoul Nationwide College Hospital has developed what could possibly be the primary medical giant language mannequin in South Korea.
The mission to develop the medical LLM started final yr in March. The SNUH analysis staff began by gathering 38 million medical texts, together with hospital admissions, outpatients, surgical, prescription, and nursing information, and de-identified and anonymised them to create a base corpus for mannequin studying.
Then, at first of 2025, it developed department-specific information bases that had been later built-in into the LLM by means of retrieval-augmented era (RAG). These information bases encompass native medical legal guidelines, paper abstracts, and remedy tips in Korean, in addition to medical terminology requirements and abbreviation dictionary.
The LLM was examined on questions from the Korean Medical Licensing Examination of the previous three years and scored 86.2%, which surpassed the common takers’ rating of 79.7%. SNUH additionally mentioned the mannequin has proven excessive translation efficiency, processing 50,000-word texts concurrently.
The SNUH analysis staff will confirm the LLM’s efficiency and security for a yr earlier than it may be utilized to help medical work and analysis. They additionally plan to broaden its software in varied medical fields and additional improve the mannequin’s medical knowledge processing functionality.
WHY IT MATTERS
In keeping with SNUH, present medical LLMs developed by tech giants, together with Google’s Med-PaLM 2 and Microsoft’s LLaVA-Med, are restricted to comprehending Korean medical texts, legal guidelines, and remedy tips. As these fashions are optimised within the Western context, these are discovered unreliable for Korean medical professionals. Therefore, the hospital researchers started growing a Korean medical LLM to satisfy the wants of native clinicians.
THE LARGER TREND
Late final yr, a startup backed by conglomerate SK Group claimed to introduce the primary LLM-based search platform particular to healthcare in South Korea. PhynX Lab’s Cheiron assists pharmacists and pharmaceutical business researchers in retrieving related info by choosing up the consumer’s intent by means of pure language processing. It will probably additionally self-reverify info and rapidly generate high-quality solutions.
Korea College Anam Hospital can be reportedly growing its personal LLM, which is predicted to be piloted this yr.
Asan Medical Middle has additionally utilised an LLM to create its voice-based medical scribe, which is now used throughout its 16 departments.
In the meantime, SNUH is at the moment engaged on different AI tasks to free clinicians from administrative work. This features a multimodal AI that may mechanically generate affected person summaries, AI for enhancing insurance coverage declare processing, and AI that curates the most recent papers for researchers.
ON THE RECORD
“By means of the event of this Korean-style medical LLM, we’ve got opened a brand new chapter in medical innovation by maximising the work effectivity of medical workers and offering quicker and extra correct medical companies to sufferers,” mentioned SNUH president and CEO Dr Kim Younger-tae in an announcement.
Discussion about this post