Trends in ChatGPT Publications in Health Sciences: A Bibliometric Analysis

Öz

Objective: Natural Language Processing is one of the fields of artificial intelligence. To examine articles related to ChatGPT in the field of health and explore its presence in the literature, areas of application, and development. Material and Methods: Bibliometric analysis was conducted on 699 publications from the Web of Science, Scopus, and PubMed databases. For data preprocessing, visualization, and statistical analysis, EndNote, Python, VOSviewer, Tableau, and SPSS 25 software tools were used in this study. The most frequently used keywords in this study included "Artificial intelligence", "chatgpt", "General and Internal Medicine", "chatbot", "Gpt-4", "machine learning", "natural language processing", and "Medical Writing". Results: Our review categorizes the publications into main areas: 38.9% "Medical Practice" ChatGPT, 35.6% "Scientific Research and Writing", and 25.5% "Ethics and Concerns". There was a statistically significant difference in the distribution of document types among the three groups based on the topics (chi-square value = 34.4, p<0.001). Conclusion: This study, the comprehensive analysis of ChatGPT's role in health literature, highlighted its potential in medical advice, consultation, education, and scientific writing. Despite ethical and privacy concerns, ChatGPT has proven potential in health, both at present and in the future.

Anahtar Kelimeler

• Health publications
• Bibliometric Analysis
• Artifical intelligence
• ChatGPT

Sağlık Alanındaki ChatGPT Yayınlarının Eğilimleri: Bibliyometrik Analiz

Öz

Amaç: Doğal Dil İşleme yapay zeka alanlarından biridir. Bu araştırmanın amacı, sağlık alanında ChatGPT ile ilgili makaleleri incelemek ve literatürdeki varlığını, uygulama alanlarını ve gelişimini araştırmaktır. Gereç ve Yöntemler: Web of Science, Scopus ve PubMed veri tabanlarından 699 yayın üzerinde bibliyometrik analiz yapılmıştır. Veri ön işleme, görselleştirme ve istatistiksel analiz için EndNote, Python, VOSviewer, Tableau ve SPSS 25 yazılım araçları kullanılmıştır. Bu çalışmada en sık kullanılan anahtar kelimeler arasında “Yapay zeka”, “chatgpt”, “Genel ve Dahili Tıp”, “chatbot”, “Gpt-4”, “makine öğrenmesi”, “doğal dil işleme” ve “Tıbbi Yazım” yer almaktadır. Bulgular: Bibliyometrik analiz, yayınları üç ana alanda sınıflandırmaktadır: %38,9’u “Tıbbi Uygulama”, %35,6’sı “Bilimsel Araştırma ve Yazım”, %25,5’i ise “Etik ve Kaygılar” konularına odaklanmaktadır. Ki‑kare testi, bu tematik kategoriler arasında belge türlerinin dağılımında istatistiksel olarak anlamlı bir fark olduğunu göstermiştir (χ² = 34,4, p < .001). Sonuç: ChatGPT'nin sağlık literatüründeki rolünün kapsamlı bir analizi olan bu çalışma, ChatGPT'nin tıbbi tavsiye, danışma, eğitim ve bilimsel yazım alanlarındaki potansiyelini ortaya koymuştur. Etik ve mahremiyet kaygılarına rağmen, ChatGPT'nin hem günümüzde hem de gelecekte sağlık alanında kanıtlanmış bir potansiyeli vardır.

Anahtar Kelimeler

• Sağlık yayınları
• Bibliyometrik Analiz
• Yapay Zeka
• ChatGPT

Kaynakça

1. 1. Amara A, Hadj Taieb MA, Ben Aouicha M. Network representation learning systematic review: Ancestors and current development state. Machine Learning with Applications. 2021;6:100130.
2. 2. Ayers JW, Poliak A, Dredze M, et al. Comparing Physician and Artificial Intelligence Chatbot Responses to Patient Questions Posted to a Public Social Media Forum. JAMA Intern Med. 2023.
3. 3. OpenAI. OpenI ChatGpt Guide. Chatgpt History: Timeline, Facts, Version, Current Capability. 2023; https://openichatgptguide.com/chatgpt-history-timeline-facts-versions/, June 30, 2024.
4. 4. Van Dis EAM, Bollen J, Zuidema W, van Rooij R, Bockting CL. ChatGPT: five priorities for research. Nature. 2023;614(7947):224-226.
5. 5. OpenAI. ChatGPT. https://openai.com/blog/chatgpt/ Accessed 15 June 2023. 2024.
6. 6. Arslan S. Exploring the Potential of Chat GPT in Personalized Obesity Treatment. Ann Biomed Eng. 2023. 51(9), 1887–1888.
7. 7. 7.Au Yeung J, Kraljevic Z, Luintel A, et al. AI chatbots not yet ready for clinical use. Frontiers in Digital Health. 2023;5.
8. 8. Baumgartner C. The potential impact of ChatGPT in clinical and translational medicine. Clinical and Translational Medicine. 2023;13(3):4.

9. 9. Wu Z, Chen C, Cai Y, Lu C, Wang H, Yu T. BIM-Based Visualization Research in the Construction Industry: A Network Analysis. International Journal of Environmental Research and Public Health. 2019;16(18):3473.
10. 10. Enciso-Alfaro S-Y, García-Sánchez I-M. Corporate governance and environmental sustainability: Addressing the dual theme from a bibliometric approach. Corporate Social Responsibility and Environmental Management. 2023;30(3):1025-1041.
11. 11. Kalgotra P, Sharda R, Croff JM. Examining multimorbidity differences across racial groups: a network analysis of electronic medical records. Sci Rep. 2020;10(1):13538.
12. 12. Lai YH. A network approach for the comorbidities of HIV/AIDS in Taiwan. Technol Health Care. 2015;24 Suppl 1:S377-383.
13. 13. Cascella M, Montomoli J, Bellini V, Bignami E. Evaluating the Feasibility of ChatGPT in Healthcare: An Analysis of Multiple Clinical and Research Scenarios. Journal of Medical Systems. 2023;47(1).
14. 14. Pears M, Konstantinidis S. Bibliometric Analysis of Chatbots in Health-Trend Shifts and Advancements in Artificial Intelligence for Personalized Conversational Agents. Stud Health Technol Inform. 2022;290:494-498.
15. 15. Eysenbach G. The Role of ChatGPT, Generative Language Models, and Artificial Intelligence in Medical Education: A Conversation with ChatGPT and a Call for Papers. JMIR Med Educ. 2023;9:e46885.
16. 16. Liu S, Wright AP, Patterson BL, et al. Using AI-generated suggestions from ChatGPT to optimize clinical decision support. J Am Med Inform Assoc. 2023. 30(7), 1237–1245.
17. 17. Liu S, Wright AP, Patterson BL, et al. Assessing the Value of ChatGPT for Clinical Decision Support Optimization. medRxiv. 2023. the preprint server for health sciences, 2023.02.21.23286254.
18. 18. Rao A, Kim J, Kamineni M, Pang M, Lie W, Succi MD. Evaluating ChatGPT as an Adjunct for Radiologic Decision-Making. medRxiv. 2023. 20(10), 990–997.
19. 19. Huang J, Tan M. The role of ChatGPT in scientific communication: writing better scientific review articles. Am J Cancer Res. 2023;13(4):1148-1154.
20. 20. Wen J, Wang W. The future of ChatGPT in academic research and publishing: A commentary for clinical and translational medicine. Clinical and Translational Medicine. 2023;13(3):3.
21. 21. Zheng H, Zhan H. ChatGPT in Scientific Writing: A Cautionary Tale. American Journal of Medicine. 2023. 136(8), 725–726.e6.
22. 22. Gracia-Ramos AE. In Defense of Human Authorship: Running title: In Defense of Human Authorship. Archives of Medical Research. 2023;54(3):270-271.
23. 23. Solomon DH, Allen KD, Katz P, Sawalha AH, Yelin E. ChatGPT, et al…Artificial Intelligence, Authorship, and Medical Publishing. Arthritis and Rheumatology. 2023. 75(6), 867–868.
24. 24. Yeo-Teh NSL, Tang BL. Letter to editor: NLP systems such as ChatGPT cannot be listed as an author because these cannot fulfill widely adopted authorship criteria. Account Res. 2023:1-3.
25. 25. Hallo-Carrasco A, Gruenbaum BF, Gruenbaum SE. Heat and Moisture Exchanger Occlusion Leading to Sudden Increased Airway Pressure: A Case Report Using ChatGPT as a Personal Writing Assistant. Cureus. 2023;15(4):e37306.
26. 26. Lantz R. Toxic Epidermal Necrolysis in a Critically Ill African American Woman: A Case Report Written With ChatGPT Assistance. Cureus. 2023;15(3):e35742.
27. 27. Segal S, Khanna AK. Anesthetic Management of a Patient With Juvenile Hyaline Fibromatosis: A Case Report Written With the Assistance of the Large Language Model ChatGPT. Cureus. 2023;15(3):e35946.
28. 28. Chen S, Zhu S. Unravelling the intricacies between gaming motivations and internet gaming disorder symptoms in adolescents: a network analysis of 2-year healthy and deteriorating transition profiles. Child and Adolescent Psychiatry and Mental Health. 2023;17(1):122.
29. 29. Levin G, Brezinov Y, Meyer R. Exploring the use of ChatGPT in OBGYN: a bibliometric analysis of the first ChatGPT-related publications. Archives of Gynecology and Obstetrics. 2023. 308(6), 1785–1789.
30. 30. Mariciuc DF. A Bibliometric Analysis of Publications on Customer Service Chatbots. Management Dynamics in the Knowledge Economy. 2023;11(1):48-62.