1
|
Nazzal MK, Morris AJ, Parker RS, White FA, Natoli RM, Fehrenbacher JC, Kacena MA. Using AI to Write a Review Article Examining the Role of the Nervous System on Skeletal Homeostasis and Fracture Healing. Curr Osteoporos Rep 2024; 22:217-221. [PMID: 38217755 PMCID: PMC10912134 DOI: 10.1007/s11914-023-00854-y] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Accepted: 12/21/2023] [Indexed: 01/15/2024]
Abstract
PURPOSE OF REVIEW Three review articles have been written that discuss the roles of the central and peripheral nervous systems in fracture healing. While content among the articles is overlapping, there is a key difference between them: the use of artificial intelligence (AI). In one paper, the first draft was written solely by humans. In the second paper, the first draft was written solely by AI using ChatGPT 4.0 (AI-only or AIO). In the third paper, the first draft was written using ChatGPT 4.0 but the literature references were supplied from the human-written paper (AI-assisted or AIA). This project was done to evaluate the capacity of AI to conduct scientific writing. Importantly, all manuscripts were fact checked and extensively edited by all co-authors rendering the final manuscript drafts significantly different from the first drafts. RECENT FINDINGS Unsurprisingly, the use of AI decreased the time spent to write a review. The two AI-written reviews took less time to write than the human-written paper; however, the changes and editing required in all three manuscripts were extensive. The human-written paper was edited the most. On the other hand, the AI-only paper was the most inaccurate with inappropriate reference usage and the AI-assisted paper had the greatest incidence of plagiarism. These findings show that each style of writing presents its own unique set of challenges and advantages. While AI can theoretically write scientific reviews, from these findings, the extent of editing done subsequently, the inaccuracy of the claims it makes, and the plagiarism by AI are all factors to be considered and a primary reason why it may be several years into the future before AI can present itself as a viable alternative for traditional scientific writing.
Collapse
Affiliation(s)
- Murad K Nazzal
- Department of Orthopaedic Surgery, Indiana University School of Medicine, Indianapolis, IN, USA
| | - Ashlyn J Morris
- Department of Orthopaedic Surgery, Indiana University School of Medicine, Indianapolis, IN, USA
| | - Reginald S Parker
- Department of Orthopaedic Surgery, Indiana University School of Medicine, Indianapolis, IN, USA
| | - Fletcher A White
- Department of Anesthesia, Indiana University School of Medicine, Indianapolis, IN, USA
- Indiana Center for Musculoskeletal Health, Indiana University School of Medicine, Indianapolis, IN, USA
- Stark Neuroscience Research Institute, Indiana University School of Medicine, Indianapolis, IN, USA
- Richard L. Roudebush VA Medical Center, Indianapolis, IN, USA
| | - Roman M Natoli
- Department of Orthopaedic Surgery, Indiana University School of Medicine, Indianapolis, IN, USA
- Indiana Center for Musculoskeletal Health, Indiana University School of Medicine, Indianapolis, IN, USA
| | - Jill C Fehrenbacher
- Indiana Center for Musculoskeletal Health, Indiana University School of Medicine, Indianapolis, IN, USA.
- Stark Neuroscience Research Institute, Indiana University School of Medicine, Indianapolis, IN, USA.
- Department of Pharmacology and Toxicology, Indiana University School of Medicine, Indianapolis, IN, USA.
| | - Melissa A Kacena
- Department of Orthopaedic Surgery, Indiana University School of Medicine, Indianapolis, IN, USA.
- Department of Anesthesia, Indiana University School of Medicine, Indianapolis, IN, USA.
- Richard L. Roudebush VA Medical Center, Indianapolis, IN, USA.
| |
Collapse
|
2
|
Harris A, Creecy A, Awosanya OD, McCune T, Ozanne MV, Toepp AJ, Kacena MA, Qiao X. SARS-CoV-2 and its Multifaceted Impact on Bone Health: Mechanisms and Clinical Evidence. Curr Osteoporos Rep 2024; 22:135-145. [PMID: 38236510 PMCID: PMC10912131 DOI: 10.1007/s11914-023-00843-1] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Accepted: 12/15/2023] [Indexed: 01/19/2024]
Abstract
PURPOSE OF REVIEW SARS-CoV-2 infection, the culprit of the COVID-19 pandemic, has been associated with significant long-term effects on various organ systems, including bone health. This review explores the current understanding of the impacts of SARS-CoV-2 infection on bone health and its potential long-term consequences. RECENT FINDINGS As part of the post-acute sequelae of SARS-CoV-2 infection, bone health changes are affected by COVID-19 both directly and indirectly, with multiple potential mechanisms and risk factors involved. In vitro and preclinical studies suggest that SARS-CoV-2 may directly infect bone marrow cells, leading to alterations in bone structure and osteoclast numbers. The virus can also trigger a robust inflammatory response, often referred to as a "cytokine storm", which can stimulate osteoclast activity and contribute to bone loss. Clinical evidence suggests that SARS-CoV-2 may lead to hypocalcemia, altered bone turnover markers, and a high prevalence of vertebral fractures. Furthermore, disease severity has been correlated with a decrease in bone mineral density. Indirect effects of SARS-CoV-2 on bone health, mediated through muscle weakness, mechanical unloading, nutritional deficiencies, and corticosteroid use, also contribute to the long-term consequences. The interplay of concurrent conditions such as diabetes, obesity, and kidney dysfunction with SARS-CoV-2 infection further complicates the disease's impact on bone health. SARS-CoV-2 infection directly and indirectly affects bone health, leading to potential long-term consequences. This review article is part of a series of multiple manuscripts designed to determine the utility of using artificial intelligence for writing scientific reviews.
Collapse
Affiliation(s)
- Alexander Harris
- Department of Orthopaedic Surgery, Indiana University School of Medicine, Indianapolis, IN, USA
| | - Amy Creecy
- Department of Orthopaedic Surgery, Indiana University School of Medicine, Indianapolis, IN, USA
| | - Olatundun D Awosanya
- Department of Orthopaedic Surgery, Indiana University School of Medicine, Indianapolis, IN, USA
| | - Thomas McCune
- Department of Internal Medicine, Eastern Virginia Medical School, Norfolk, VA, USA
- Division of Nephrology, Eastern Virginia Medical School, Norfolk, VA, USA
| | - Marie V Ozanne
- Department of Mathematics and Statistics, Mount Holyoke College, South Hadley, MA, USA
| | - Angela J Toepp
- Department of Internal Medicine, Eastern Virginia Medical School, Norfolk, VA, USA
- Enterprise Analytics, Sentara Health, Virginia Beach, VA, USA
| | - Melissa A Kacena
- Department of Orthopaedic Surgery, Indiana University School of Medicine, Indianapolis, IN, USA.
- Richard L. Roudebush VA Medical Center, Indianapolis, IN, USA.
| | - Xian Qiao
- Department of Internal Medicine, Eastern Virginia Medical School, Norfolk, VA, USA.
- SMG Pulmonary, Critical Care, and Sleep Specialists, Norfolk, VA, USA.
- Division of Pulmonary and Critical Care Medicine, Eastern Virginia Medical School, Norfolk, VA, USA.
| |
Collapse
|
3
|
Margetts TJ, Karnik SJ, Wang HS, Plotkin LI, Oblak AL, Fehrenbacher JC, Kacena MA, Movila A. 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 2024; 22:177-181. [PMID: 38225472 PMCID: PMC10912103 DOI: 10.1007/s11914-023-00853-z] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Accepted: 12/21/2023] [Indexed: 01/17/2024]
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.
Collapse
Affiliation(s)
- Tyler J Margetts
- Department of Orthopaedic Surgery, Indiana University School of Medicine, Indianapolis, IN, 46202, USA
| | - Sonali J Karnik
- Department of Orthopaedic Surgery, Indiana University School of Medicine, Indianapolis, IN, 46202, USA
| | - Hannah S Wang
- Department of Orthopaedic Surgery, Indiana University School of Medicine, Indianapolis, IN, 46202, USA
| | - Lilian I Plotkin
- Department of Anatomy, Cell Biology & Physiology, Indiana University School of Medicine, Indianapolis, IN, 46202, USA
- Indiana Center for Musculoskeletal Health, Indiana University School of Medicine, Indianapolis, IN, USA
- Richard L. Roudebush VA Medical Center, Indianapolis, IN, 46202, USA
| | - Adrian L Oblak
- Department of Radiology & Imaging Sciences, Stark Neurosciences Research Institute, Indiana University School of Medicine, Indianapolis, IN, 46202, USA
- Stark Neurosciences Research Institute, Indiana University School of Medicine, Indianapolis, IN, 46202, USA
| | - Jill C Fehrenbacher
- Indiana Center for Musculoskeletal Health, Indiana University School of Medicine, Indianapolis, IN, USA
- Stark Neurosciences Research Institute, Indiana University School of Medicine, Indianapolis, IN, 46202, USA
- Department of Pharmacology and Toxicology, Indiana University School of Medicine, Indianapolis, IN, 46202, USA
| | - Melissa A Kacena
- Department of Orthopaedic Surgery, Indiana University School of Medicine, Indianapolis, IN, 46202, USA.
- Department of Anatomy, Cell Biology & Physiology, Indiana University School of Medicine, Indianapolis, IN, 46202, USA.
- Indiana Center for Musculoskeletal Health, Indiana University School of Medicine, Indianapolis, IN, USA.
- Richard L. Roudebush VA Medical Center, Indianapolis, IN, 46202, USA.
| | - Alexandru Movila
- Indiana Center for Musculoskeletal Health, Indiana University School of Medicine, Indianapolis, IN, USA.
- Department of Biomedical Sciences and Comprehensive Care, Indiana University School of Dentistry, Indianapolis, IN, 46202, USA.
| |
Collapse
|
4
|
Kacena MA, Plotkin LI, Fehrenbacher JC. The Use of Artificial Intelligence in Writing Scientific Review Articles. Curr Osteoporos Rep 2024; 22:115-121. [PMID: 38227177 PMCID: PMC10912250 DOI: 10.1007/s11914-023-00852-0] [Citation(s) in RCA: 13] [Impact Index Per Article: 13.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Accepted: 12/21/2023] [Indexed: 01/17/2024]
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) the neural regulation of fracture healing; and (3) COVID-19 and musculoskeletal health. For each of these topics, 3 approaches to write manuscript drafts were undertaken: (1) human only; (2) ChatGPT only (AI-only); and (3) combination approach of #1 and #2 (AI-assisted). Articles were extensively fact checked and edited to ensure scientific quality, resulting in final manuscripts that were significantly different from the original drafts. Numerous parameters were measured throughout the process to quantitate advantages and disadvantages of approaches. RECENT FINDINGS Overall, use of AI decreased the time spent to write the review article, but required more extensive fact checking. With the AI-only approach, up to 70% of the references cited were found to be inaccurate. Interestingly, the AI-assisted approach resulted in the highest similarity indices suggesting a higher likelihood of plagiarism. Finally, although the technology is rapidly changing, at the time of study, ChatGPT 4.0 had a cutoff date of September 2021 rendering identification of recent articles impossible. Therefore, all literature published past the cutoff date was manually provided to ChatGPT, rendering approaches #2 and #3 identical for contemporary citations. As a result, for the COVID-19 and musculoskeletal health topic, approach #2 was abandoned midstream due to the extensive overlap with approach #3. The main objective of this scientific study was to see whether AI could be used in a scientifically appropriate manner to improve the scientific writing process. Indeed, AI reduced the time for writing but had significant inaccuracies. The latter necessitates that AI cannot currently be used alone but could be used with careful oversight by humans to assist in writing scientific review articles.
Collapse
Affiliation(s)
- Melissa A Kacena
- Department of Orthopaedic Surgery, Indiana University School of Medicine, Indianapolis, IN, 46202, USA.
- Department of Anatomy, Cell Biology & Physiology, Indiana University School of Medicine, Indianapolis, IN, 46202, USA.
- Indiana Center for Musculoskeletal Health, Indiana University School of Medicine, Indianapolis, IN, 46202, USA.
- Richard L. Roudebush VA Medical Center, Indianapolis, IN, 46202, USA.
| | - Lilian I Plotkin
- Department of Anatomy, Cell Biology & Physiology, Indiana University School of Medicine, Indianapolis, IN, 46202, USA
- Indiana Center for Musculoskeletal Health, Indiana University School of Medicine, Indianapolis, IN, 46202, USA
- Richard L. Roudebush VA Medical Center, Indianapolis, IN, 46202, USA
| | - Jill C Fehrenbacher
- Indiana Center for Musculoskeletal Health, Indiana University School of Medicine, Indianapolis, IN, 46202, USA.
- Department of Pharmacology and Toxicology, Indiana University School of Medicine, Indianapolis, IN, 46202, USA.
- Stark Neuroscience Research Institute, Indiana University School of Medicine, Indianapolis, IN, 46202, USA.
| |
Collapse
|
5
|
Creecy A, Awosanya OD, Harris A, Qiao X, Ozanne M, Toepp AJ, Kacena MA, McCune T. COVID-19 and Bone Loss: A Review of Risk Factors, Mechanisms, and Future Directions. Curr Osteoporos Rep 2024; 22:122-134. [PMID: 38221578 PMCID: PMC10912142 DOI: 10.1007/s11914-023-00842-2] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Accepted: 12/15/2023] [Indexed: 01/16/2024]
Abstract
PURPOSE OF REVIEW SARS-CoV-2 drove the catastrophic global phenomenon of the COVID-19 pandemic resulting in a multitude of systemic health issues, including bone loss. The purpose of this review is to summarize recent findings related to bone loss and potential mechanisms. RECENT FINDINGS The early clinical evidence indicates an increase in vertebral fractures, hypocalcemia, vitamin D deficiencies, and a loss in BMD among COVID-19 patients. Additionally, lower BMD is associated with more severe SARS-CoV-2 infection. Preclinical models have shown bone loss and increased osteoclastogenesis. The bone loss associated with SARS-CoV-2 infection could be the result of many factors that directly affect the bone such as higher inflammation, activation of the NLRP3 inflammasome, recruitment of Th17 cells, the hypoxic environment, and changes in RANKL/OPG signaling. Additionally, SARS-CoV-2 infection can exert indirect effects on the skeleton, as mechanical unloading may occur with severe disease (e.g., bed rest) or with BMI loss and muscle wasting that has also been shown to occur with SARS-CoV-2 infection. Muscle wasting can also cause systemic issues that may influence the bone. Medications used to treat SARS-CoV-2 infection also have a negative effect on the bone. Lastly, SARS-CoV-2 infection may also worsen conditions such as diabetes and negatively affect kidney function, all of which could contribute to bone loss and increased fracture risk. SARS-CoV-2 can negatively affect the bone through multiple direct and indirect mechanisms. Future work will be needed to determine what patient populations are at risk of COVID-19-related increases in fracture risk, the mechanisms behind bone loss, and therapeutic options. This review article is part of a series of multiple manuscripts designed to determine the utility of using artificial intelligence for writing scientific reviews.
Collapse
Affiliation(s)
- Amy Creecy
- Department of Orthopaedic Surgery, Indiana University School of Medicine, Indianapolis, IN, USA
| | - Olatundun D Awosanya
- Department of Orthopaedic Surgery, Indiana University School of Medicine, Indianapolis, IN, USA
| | - Alexander Harris
- Department of Orthopaedic Surgery, Indiana University School of Medicine, Indianapolis, IN, USA
| | - Xian Qiao
- Critical Care, and Sleep Specialists, SMG Pulmonary, Norfolk, VA, USA
- Division of Pulmonary and Critical Care Medicine, Eastern Virginia Medical School, Norfolk, VA, USA
- Department of Internal Medicine, Eastern Virginia Medical School, Norfolk, VA, USA
| | - Marie Ozanne
- Department of Mathematics and Statistics, Mount Holyoke College, South Hadley, MA, USA
| | - Angela J Toepp
- Department of Internal Medicine, Eastern Virginia Medical School, Norfolk, VA, USA
- Enterprise Analytics, Sentara Health, Virginia Beach, VA, USA
| | - Melissa A Kacena
- Department of Orthopaedic Surgery, Indiana University School of Medicine, Indianapolis, IN, USA.
- Richard L. Roudebush VA Medical Center, Indianapolis, IN, USA.
| | - Thomas McCune
- Department of Internal Medicine, Eastern Virginia Medical School, Norfolk, VA, USA.
- Division of Nephrology, Eastern Virginia Medical School, Norfolk, VA, USA.
| |
Collapse
|