Skip to main navigation Skip to search Skip to main content

How Good Is ChatGPT for Medication Evidence Synthesis?

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

With its seeming competence to mimic human responses, ChatGPT, an emerging AI-powered chatbot, has spurred great interest. This study aims to explore the role of ChatGPT in synthesizing medication literature and compare it with a hybrid summarization system. We tested ten medications' effectiveness with reference to their definitions and descriptions extracted from DrugBank. ChatGPT could generate coherent summaries that are not backed by evidence. In contrast, our approach can provide a highly structured and concise synthesis of related evidence, but the resulting summary is not as fluent and convincing as ChatGPT. Therefore, we recommend integrating both techniques to achieve the best performance.

Original languageEnglish
Title of host publicationCaring is Sharing - Exploiting the Value in Data for Health and Innovation - Proceedings of MIE 2023
EditorsMaria Hagglund, Madeleine Blusi, Stefano Bonacina, Lina Nilsson, Inge Cort Madsen, Sylvia Pelayo, Anne Moen, Arriel Benis, Lars Lindskold, Parisis Gallos
PublisherIOS Press BV
Pages1062-1066
Number of pages5
ISBN (Electronic)9781643683881
DOIs
StatePublished - 18 May 2023
Event33rd Medical Informatics Europe Conference: Caring is Sharing - Exploiting the Value in Data for Health and Innovation, MIE2023 - Gothenburg, Sweden
Duration: 22 May 202325 May 2023

Publication series

NameStudies in Health Technology and Informatics
Volume302
ISSN (Print)0926-9630
ISSN (Electronic)1879-8365

Conference

Conference33rd Medical Informatics Europe Conference: Caring is Sharing - Exploiting the Value in Data for Health and Innovation, MIE2023
Country/TerritorySweden
CityGothenburg
Period22/05/2325/05/23

Keywords

  • ChatGPT
  • Natural Language Processing
  • Summarization

Fingerprint

Dive into the research topics of 'How Good Is ChatGPT for Medication Evidence Synthesis?'. Together they form a unique fingerprint.

Cite this