Sağlık hizmetlerinde büyük dil modellerinin uygulamaları ve araştırma eğilimleri: Bibliyometrik bir analiz

Öz

Amaç: Bu çalışma, sağlık alanında Büyük Dil Modelleri’nin (LLM) kullanımına ilişkin mevcut durumu ve araştırma eğilimlerini bibliyometrik analiz yöntemiyle ortaya koymayı amaçlamaktadır. Gereç ve Yöntemler: Veriler, 2023-2025 yılları arasında yayımlanmış açık erişimli klinik araştırma makaleleri arasından seçilerek Web of Science veri tabanından elde edilmiştir. Dahil etme kriterlerini karşılayan 173 makale, R programında “Bibliometrix” paketi ve “Biblioshiny” arayüzü kullanılarak analiz edilmiştir. Yayın eğilimleri, ortak yazarlık ağları, anahtar kelime eş-oluşumları ve tematik haritalama gibi temel bibliyometrik göstergeler incelenmiştir. Bulgular: Bulgular, sağlık alanında LLM’lere yönelik bilimsel ilginin belirgin şekilde arttığını ve ABD, Çin ve bazı Avrupa ülkelerinin bu alandaki araştırmalara öncülük ettiğini göstermektedir. “Yapay Zekâ”, “ChatGPT” ve “Tıp Eğitimi” gibi anahtar kelimelerin öne çıkması, LLM’lerin eğitim ve klinik destek sistemlerinde giderek daha fazla araştırıldığını ortaya koymaktadır. Tematik analizde, “performans”, “sağlık eşitsizlikleri” ve “etik zorluklar” gibi konuların yükselen araştırma alanları olduğu görülmüştür. LLM’ler sağlık hizmetlerinde önemli fırsatlar sunarken, veri gizliliği, yanlış bilgi üretimi ve etik denetim eksiklikleri gibi riskler de barındırmaktadır. Sonuç: Sonuç olarak, bu çalışma sağlık alanında LLM’lerin kullanımına yönelik kapsamlı bir haritalama sunarak, öne çıkan araştırma temalarını ve literatürdeki boşlukları ortaya koymaktadır.

Anahtar Kelimeler

• Bibliyometrik analiz
• ChatGPT
• üretken yapay zeka
• büyük dil modelleri
• tıp

Applications and research trends of large language models in healthcare: A bibliometric analysis

Öz

Aim: This study aims to reveal the current scientific studies and research trends on the use of Large Language Models (LLM) in the field of health by bibliometric analysis. Material and Methods: Data were sourced from open-access clinical research articles published between 2023 and 2025, extracted from the Web of Science database. A total of 173 articles meeting the inclusion criteria were analyzed using the “Bibliometrix” R package and the “Biblioshiny” interface, focusing on publication trends, co-authorship networks, keyword co-occurrences, and thematic mapping. Results: Results revealed a substantial rise in academic interest in LLMs within healthcare, with significant contributions from researchers in the United States, China, and various European countries. Prominent keywords such as "Artificial Intelligence," "ChatGPT," and "Medical Education" indicate that LLMs are increasingly explored for educational and clinical support applications. Thematic analysis identified emerging research areas including "performance," "health disparities," and "ethical challenges." While LLMs offer considerable opportunities in healthcare, they also present notable risks like data privacy issues, misinformation, and ethical oversight gaps. Conclusion: In conclusion, this study provides a comprehensive overview of LLM applications in healthcare, highlighting key research themes and identifying gaps within the current literature.

Anahtar Kelimeler

• Bibliometric analysis
• ChatGPT
• generative artificial intelligence
• large language models
• medicine

Kaynakça

1. Liu J, Yang M, Yu Y, Huang X, Zhang Q. Large language models in bioinformatics: applications and perspectives. arXiv. 2024;2401.04155.
2. Adedeji A, Sanni M, Ayodele E, Okoro M, Bello A. The multicultural medical assistant: can LLMs improve medical ASR errors across borders? arXiv. 2025;2501.15310. https://doi.org/10.48550/arXiv.2501.15310
3. Wen‑Ching Wu MSN. Effects of a Steno Diabetes Dialogue Card‑based intervention on self‑perceived health, health literacy, and glycemic control in older adults with type 2 diabetes mellitus living in the community. Hu Li Za Zhi. 2025;72(1):64-75. https://doi.org/10.6224/JN.202502_72(1).09
4. Karabacak M, Margetis K. Embracing large language models for medical applications: opportunities and challenges. Cureus. 2023;15(12):e39305. https://doi.org/10.7759/cureus.39305
5. Vrdoljak J, Boban Z, Vilović M, Kraljević T, Petrović L. A review of large language models in medical education, clinical decision support, and healthcare administration. Healthc (Basel). 2025;13(6):603. https://doi.org/10.3390/healthcare13060603
6. Alber DA, Yang Z, Alyakin A, Brown P, Chen L. Medical large language models are vulnerable to data‑poisoning attacks. Nat Med. 2025;31:1-9. https://doi.org/10.1038/s41591-024-03445-1
7. Tangsrivimol JA, Darzidehkalani E, Virk HU, Smith J, Lee V. Benefits, limits, and risks of ChatGPT in medicine. Front Artif Intell. 2025;8:1518049. https://doi.org/10.3389/frai.2025.1518049
8. Clusmann J, Kolbinger FR, Muti HS, O’Connor C, Peters G. The future landscape of large language models in medicine. Commun Med. 2023;3(1):141. https://doi.org/10.1038/s43856-023-00370-1

9. Kumar K, Ashraf T, Thawakar O, Anwer RM, Singh P. LLM post‑training: a deep dive into reasoning large language models. arXiv. 2025;2502.21321. https://doi.org/10.48550/arXiv.2502.21321
10. Donthu N, Kumar S, Mukherjee D, Pandey N, Lim WM. How to conduct a bibliometric analysis: an overview and guidelines. J Bus Res. 2021;133:285-296. https://doi.org/10.1016/j.jbusres.2021.04.070
11. Aria M, Cuccurullo C. Bibliometrix: an R-tool for comprehensive science mapping analysis. J Informetr. 2017;11(4):959-75. https://doi.org/10.1016/j.joi.2017.08.007
12. Barrington NM, Gupta N, Musmar B, Doyle D, Panico N, Godbole N, et al. A bibliometric analysis of the rise of ChatGPT in medical research. Med Sci (Basel). 2023;11(3):61. https://doi.org/10.3390/medsci11030061
13. Koo M. ChatGPT research: a bibliometric analysis based on the Web of Science from 2023 to June 2024. Knowledge. 2025;5(1):4. https://doi.org/10.3390/knowledge5010004
14. Bi Z, Dip SA, Hajialigol D, Kommu S, Liu H, Meng L, Patel R. AI for biomedicine in the era of large language models. arXiv. 2024;2403.15673. https://doi.org/10.48550/arXiv.2403.15673
15. Gencer G, Gencer K. Large language models in healthcare: a bibliometric analysis and examination of research trends. J Multidiscip Healthc. 2025;18:223-238. https://doi.org/10.2147/JMDH.S502351
16. Cascella M, Semeraro F, Montomoli J, Rossi A, Bianchi F. The breakthrough of large language models release for medical applications: 1‑year timeline and perspectives. J Med Syst. 2024;48(1):22. https://doi.org/10.1007/s10916-024-02045-3
17. Lawrence HR, Schneider RA, Rubin SB, Davis K, Williams L. The opportunities and risks of large language models in mental health. JMIR Ment Health. 2024;11(1):e59479. https://doi.org/10.2196/59479
18. Çelik Ö, Kaya E. Artificial intelligence and ethics in healthcare: a bibliometric analysis. Süleyman Demirel University Visionary Journal. 2024;15(43):1046-1062. https://doi.org/10.21076/vizyoner.1455659
19. Abd‑Alrazaq A, AlSaad R, Alhuwail D, Househ M, Shah Z. Large language models in medical education: opportunities, challenges, and future directions. JMIR Med Educ. 2023;9(1):e48291. https://doi.org/10.2196/48291
20. Khan AA, Akbar MA, Fahmideh M, Rahman N, Li C. AI ethics: an empirical study on the views of practitioners and lawmakers. IEEE Trans Comput Soc Syst. 2023;10(6):2971-2984. https://doi.org/10.1109/TCSS.2023.3251729
21. Yu D, Bondi M, Hyland K. Can GPT-4 learn to analyse moves in research article abstracts? Appl Linguist. 2024;amae071. https://doi.org/10.1093/applin/amae071
22. Zhou Z, Li J, Zhang Z, Chen F, Wu X. Examining how the large language models impact the conceptual design with human designers: a comparative case study. Int J Hum-Comput Interact. 2024;1-17. https://doi.org/10.1080/10447318.2024.2370635
23. World Health Organization. Ethics and governance of artificial intelligence for health: guidance on large multi‑modal models. Geneva: WHO; 2024. ISBN: 978-92-4-008475-9