Use of AI Language Engine ChatGPT 4.0 to Write a Scientific Review Article Examining the Intersection of Alzheimer's Disease and Bone.
Curr Osteoporos Rep
; 22(1): 177-181, 2024 02.
Article
en En
| MEDLINE
| ID: mdl-38225472
ABSTRACT
PURPOSE OF REVIEW This Comment represents three review articles on the relationship between Alzheimer's disease, osteoporosis, and fracture in an exploration of the benefits that AI can provide in scientific writing. The first drafts of the articles were written (1) entirely by humans; (2) entirely by ChatGPT 4.0 (AI-only or AIO); and (3) by humans and ChatGPT 4.0 whereby humans selected literature references, but ChatGPT 4.0 completed the writing (AI-assisted or AIA). Importantly, each review article was edited and carefully checked for accuracy by all co-authors resulting in a final manuscript which was significantly different from the original draft. RECENT FINDINGS:
The human-written article took the most time from start to finish, the AI-only article took the least time, and the AI-assisted article fell between the two. When comparing first drafts to final drafts, the AI-only and AI-assisted articles had higher percentages of different text than the human article. The AI-only paper had a higher percentage of incorrect references in the first draft than the AI-assisted paper. The first draft of the AI-assisted article had a higher similarity score than the other two articles when examined by plagiarism identification software. This writing experiment used time tracking, human editing, and comparison software to examine the benefits and risks of using AI to assist in scientific writing. It showed that while AI may reduce total writing time, hallucinations and plagiarism were prevalent issues with this method and human editing was still necessary to ensure accuracy.Palabras clave
Texto completo:
1
Colección:
01-internacional
Banco de datos:
MEDLINE
Asunto principal:
Fracturas Óseas
/
Enfermedad de Alzheimer
Tipo de estudio:
Prognostic_studies
Límite:
Humans
Idioma:
En
Revista:
Curr Osteoporos Rep
Asunto de la revista:
ORTOPEDIA
Año:
2024
Tipo del documento:
Article
País de afiliación:
Estados Unidos