2024
DOI: 10.1007/s11914-023-00852-0
|View full text |Cite
|
Sign up to set email alerts
|

The Use of Artificial Intelligence in Writing Scientific Review Articles

Melissa A. Kacena,
Lilian I. Plotkin,
Jill C. Fehrenbacher

Abstract: Purpose of Review With the recent explosion in the use of artificial intelligence (AI) and specifically ChatGPT, we sought to determine whether ChatGPT could be used to assist in writing credible, peer-reviewed, scientific review articles. We also sought to assess, in a scientific study, the advantages and limitations of using ChatGPT for this purpose. To accomplish this, 3 topics of importance in musculoskeletal research were selected: (1) the intersection of Alzheimer’s disease and bone; (2) th… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2

Citation Types

0
3
0

Year Published

2024
2024
2024
2024

Publication Types

Select...
5
2

Relationship

3
4

Authors

Journals

citations
Cited by 44 publications
(3 citation statements)
references
References 23 publications
0
3
0
Order By: Relevance
“…The original goal was to have a total of 9 review articles and quantifiable data related to each step of the processes to assess the benefits and limitations of each approach. Please refer to the Introductory Comment [ 12 ] for more information regarding the specifics of the study design. We had several hypotheses for this experiment.…”
Section: Introductionmentioning
confidence: 99%
“…The original goal was to have a total of 9 review articles and quantifiable data related to each step of the processes to assess the benefits and limitations of each approach. Please refer to the Introductory Comment [ 12 ] for more information regarding the specifics of the study design. We had several hypotheses for this experiment.…”
Section: Introductionmentioning
confidence: 99%
“…This is one of many articles evaluating the utility of using AI to write scientific review articles on musculoskeletal topics [ 1 ]. The first draft of this review was written entirely by humans.…”
Section: Introductionmentioning
confidence: 99%
“…4 Furthermore, research assessing the AI software currently available has verified LLMs' generation of hallucinations and inaccurate information. Kacena et al 6 constructed a study comparing 3 methods of writing a scientific manuscript: human only, chatbot only, and an integration of the 2 methods. When using chatbot alone, up to 70% of the cited references were inaccurate.…”
mentioning
confidence: 99%