Your browser doesn't support javascript.
loading
Artificial Intelligence-Generated Editorials in Radiology: Can Expert Editors Detect Them?
Ozkara, Burak Berksu; Boutet, Alexandre; Comstock, Bryan A; Van Goethem, Johan; Huisman, Thierry A G M; Ross, Jeffrey S; Saba, Luca; Shah, Lubdha M; Wintermark, Max; Castillo, Mauricio.
Afiliación
  • Ozkara BB; From the Department of Neuroradiology (B.B.O., M.W.), MD Anderson Cancer Center, Houston, TX, USA; Joint Department of Medical Imaging (A.B.), University of Toronto, Toronto, ON, Canada; Department of Biostatistics (B.A. C.), University of Washington, Seattle, WA, USA; Department of Radiology (J.V.G
  • Boutet A; From the Department of Neuroradiology (B.B.O., M.W.), MD Anderson Cancer Center, Houston, TX, USA; Joint Department of Medical Imaging (A.B.), University of Toronto, Toronto, ON, Canada; Department of Biostatistics (B.A. C.), University of Washington, Seattle, WA, USA; Department of Radiology (J.V.G
  • Comstock BA; From the Department of Neuroradiology (B.B.O., M.W.), MD Anderson Cancer Center, Houston, TX, USA; Joint Department of Medical Imaging (A.B.), University of Toronto, Toronto, ON, Canada; Department of Biostatistics (B.A. C.), University of Washington, Seattle, WA, USA; Department of Radiology (J.V.G
  • Van Goethem J; From the Department of Neuroradiology (B.B.O., M.W.), MD Anderson Cancer Center, Houston, TX, USA; Joint Department of Medical Imaging (A.B.), University of Toronto, Toronto, ON, Canada; Department of Biostatistics (B.A. C.), University of Washington, Seattle, WA, USA; Department of Radiology (J.V.G
  • Huisman TAGM; From the Department of Neuroradiology (B.B.O., M.W.), MD Anderson Cancer Center, Houston, TX, USA; Joint Department of Medical Imaging (A.B.), University of Toronto, Toronto, ON, Canada; Department of Biostatistics (B.A. C.), University of Washington, Seattle, WA, USA; Department of Radiology (J.V.G
  • Ross JS; From the Department of Neuroradiology (B.B.O., M.W.), MD Anderson Cancer Center, Houston, TX, USA; Joint Department of Medical Imaging (A.B.), University of Toronto, Toronto, ON, Canada; Department of Biostatistics (B.A. C.), University of Washington, Seattle, WA, USA; Department of Radiology (J.V.G
  • Saba L; From the Department of Neuroradiology (B.B.O., M.W.), MD Anderson Cancer Center, Houston, TX, USA; Joint Department of Medical Imaging (A.B.), University of Toronto, Toronto, ON, Canada; Department of Biostatistics (B.A. C.), University of Washington, Seattle, WA, USA; Department of Radiology (J.V.G
  • Shah LM; From the Department of Neuroradiology (B.B.O., M.W.), MD Anderson Cancer Center, Houston, TX, USA; Joint Department of Medical Imaging (A.B.), University of Toronto, Toronto, ON, Canada; Department of Biostatistics (B.A. C.), University of Washington, Seattle, WA, USA; Department of Radiology (J.V.G
  • Wintermark M; From the Department of Neuroradiology (B.B.O., M.W.), MD Anderson Cancer Center, Houston, TX, USA; Joint Department of Medical Imaging (A.B.), University of Toronto, Toronto, ON, Canada; Department of Biostatistics (B.A. C.), University of Washington, Seattle, WA, USA; Department of Radiology (J.V.G
  • Castillo M; From the Department of Neuroradiology (B.B.O., M.W.), MD Anderson Cancer Center, Houston, TX, USA; Joint Department of Medical Imaging (A.B.), University of Toronto, Toronto, ON, Canada; Department of Biostatistics (B.A. C.), University of Washington, Seattle, WA, USA; Department of Radiology (J.V.G
AJNR Am J Neuroradiol ; 2024 Sep 17.
Article en En | MEDLINE | ID: mdl-39288967
ABSTRACT
BACKGROUND AND

PURPOSE:

We aimed to evaluate GPT-4's ability to write radiology editorials and to compare these with human-written counterparts, thereby determining their real-world applicability for scientific writing. MATERIALS AND

METHODS:

Sixteen editorials from eight journals were included. To generate the AI-written editorials, the summary of 16 human-written editorials was fed into GPT-4. Six experienced editors reviewed the articles. First, an unpaired approach was used. The raters were asked to evaluate the content of each article using a 1-5 Likert scale across specified metrics. Then, they determined whether the editorials were written by humans or AI. The articles were then evaluated in pairs to determine which article was generated by AI and which should be published. Finally, the articles were analyzed with an AI detector and for plagiarism.

RESULTS:

The human-written articles had a median AI probability score of 2.0%, whereas the AI-written articles had 58%. The median similarity score among AI-written articles was 3%. 58% of unpaired articles were correctly classified regarding authorship. Rating accuracy was increased to 70% in the paired setting. AI-written articles received slightly higher scores in most metrics. When stratified by perception, human-written perceived articles were rated higher in most categories. In the paired setting, raters strongly preferred publishing the article they perceived as human-written (82%).

CONCLUSIONS:

GPT-4 can write high-quality articles that iThenticate does not flag as plagiarized, which may go undetected by editors, and that detection tools can detect to a limited extent. Editors showed a positive bias toward human-written articles. ABBREVIATIONS AI = Artificial intelligence; LLM = large language model; SD = standard deviation.
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Idioma: En Revista: AJNR Am J Neuroradiol Año: 2024 Tipo del documento: Article Pais de publicación: Estados Unidos
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Idioma: En Revista: AJNR Am J Neuroradiol Año: 2024 Tipo del documento: Article Pais de publicación: Estados Unidos