Skip to main navigation Skip to search Skip to main content

Advancing medical question answering with a knowledge embedding transformer

Research output: Contribution to journal › Article › peer-review

Abstract

Efficient medical question answering is essential for better patient care. Despite progress since Eliza (1966), even advanced LLMs (e.g., GPT-4) struggle with medical data. This study presents a system combining knowledge embedding and transformers. It includes a knowledge understanding layer and an answer generation layer. Tested on the MedQA dataset, it achieved 82.92% accuracy, outperforming GPT-4’s 71.07%. The results demonstrate the system’s ability to deliver accurate and ethical answers. This integrated method improves response speed and quality. Future work will enhance precision, support patient interaction, and integrate multimodal data for improved healthcare query processing.

Original languageEnglish
Article numbere0329606
JournalPLoS ONE
Volume20
Issue number8 August
DOIs
Publication statusPublished - Aug 2025

ASJC Scopus subject areas

  • General

Fingerprint

Dive into the research topics of 'Advancing medical question answering with a knowledge embedding transformer'. Together they form a unique fingerprint.

Cite this