메뉴 건너뛰기
소속 기관 / 학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
고객센터 ENG
주제분류

논문 기본 정보

저자정보
(Inje University) (Inje University) (Inje University)
저널정보
한국정보통신학회 한국정보통신학회 종합학술대회 논문집 한국정보통신학회 2024년도 추계종합학술대회 논문집 제28권 제2호
오류 신고하기

피인용 0

검색

    초록·키워드

    Advances in artificial intelligence, particularly through Recurrent Neural Networks (RNNs), Convolutional Neural Networks (CNNs), and Transformer-based models such as the Generative Pre-trained Transformer (GPT), have significantly shifted the landscape from rule-based to dynamic, data-driven text generation approaches. We review state-of-the-art techniques, highlighting the crucial shift towards Large Language Models (LLMs) that excel in generating nuanced, context-aware medical texts. This study reviews existing methodologies and examines the challenges of implementing these technologies in real-world healthcare settings, including data privacy, integration complexities, and the need for domain-specific training. Additionally, the paper showcases several case studies to illustrate the practical benefits and significant efficiency gains from automated medical report generation. The paper aims to provide a comprehensive overview of text-generation models’ current capabilities, limitations, and future potential in healthcare.

    최근 본 자료 전체보기