From information overload to lucidity: a survey on leveraging gpts for systematic summarization of medical and biomedical artifacts

dc.contributor.authorChalapathi, G.S.S.
dc.contributor.authorSingh, Amit Rajnarayan
dc.date.accessioned2025-02-24T09:45:04Z
dc.date.available2025-02-24T09:45:04Z
dc.date.issued2024-12
dc.description.abstractIn medical research, the rapid proliferation of condition-specific studies has led to an information overload, making it challenging for researchers and practitioners to stay abreast of the latest findings. This paper presents a comprehensive survey on leveraging Generative Pretrained Transformers (GPTs) to summarize medical and biomedical artifacts systematically. We delve into the current applications of GPTs in this domain, discussing their role in understanding and summarizing research papers, medical dialogues, and medical records. Through a comparative analysis of recent studies and methodologies, we highlight the effectiveness of GPTs in distilling complex medical information into concise, understandable summaries. Our survey underscores the potential of GPTs as a tool for navigating the information overload in medical research and bringing clarity to healthcare professionals. This transformation will enhance patient care and outcomes, such as improving the accessibility and comprehensibility of medical research, assisting in rapid information retrieval, and facilitating the summarization of complex medical studies for broader audiences.en_US
dc.identifier.urihttps://ieeexplore.ieee.org/abstract/document/10812718/authors#authors
dc.identifier.urihttp://dspace.bits-pilani.ac.in:8080/jspui/handle/123456789/17992
dc.language.isoenen_US
dc.publisherIEEEen_US
dc.subjectMechanical Engineeringen_US
dc.subjectBiomedicalen_US
dc.subjectChatGPTen_US
dc.subjectGenerative pretrained transformersen_US
dc.subjectNatural Language Processing (NLP)en_US
dc.titleFrom information overload to lucidity: a survey on leveraging gpts for systematic summarization of medical and biomedical artifactsen_US
dc.typeArticleen_US

Files