9.310 Yayının Doğal Dil İşleme Yoluyla Sentezi ve Dermatolojide Yapay Zekanın On Yıllık Dönüşümü

Abstract

Amaç: Bu çalışma, 2015-2025 yılları arasında dermatolojide yapay zeka (YZ) araştırmalarının evrimini, doğal dil işleme (DDİ) destekli içerik analizi yoluyla geleneksel bibliyometrik göstergelerin ötesine geçerek incelemeyi; hastalık odağı, veri türleri ve teknolojik altyapıdaki zamansal değişimleri tanımlamayı amaçlamıştır. Yöntemler: Web of Science Core Collection'dan elde edilen toplam 9.310 yayın analiz edilmiştir. Klasik bibliyometrik göstergeler R-Bibliometrix, VOSviewer ve CiteSpace yazılımları kullanılarak değerlendirilmiştir. Çalışmanın özgün katkısını oluşturan DDİ tabanlı sınıflandırma aşamasında, her yayının başlığı ve özeti kural tabanlı bir algoritma kullanılarak taranmış ve sistematik olarak üç boyutta sınıflandırılmıştır: hedeflenen dermatolojik hastalık, kullanılan veri türü ve ele alınan klinik görev. Erken dönem (2015–2019) ile geç dönem (2020–2025) arasındaki tematik değişimler karşılaştırmalı olarak incelenmiştir. Bulgular: Erken dönemde onkoloji (melanom), %32,2'lik araştırma oranıyla literatüre hakimken; bu oran teledermatolojinin ivme kazandığı geç dönemde %20,9'a gerilemiştir. Araştırma odağı, onkolojiyi geride bırakarak kozmetik/yaşlanmaya (%32,4) doğru kayda değer bir klinik değişim göstermiştir. Eş zamanlı olarak, yapay zeka tarafından hedeflenen klinik görevler sadece tanının ötesine geçerek hastalık şiddeti puanlamasını (%29,7) ve tedavi yanıtı izlemini (%18,0) kapsayacak şekilde genişlemiştir. 2022'de ChatGPT'nin kullanıma sunulmasını takiben, dermatolojide büyük dil modeli (LLM) araştırmaları üstel bir büyüme sergileyerek üç yıl içinde 25 kat artmıştır. Sonuç: Dermatolojideki yapay zeka literatürü eş zamanlı olarak üç boyutlu bir dönüşüm geçirmektedir. Yapay zeka, belirli bir melanom tarama aracı olmaktan çıkarak; kozmetik ve inflamatuar hastalıkları da kapsayan, rutin poliklinik uygulamalarına entegre edilmiş bir "klinik asistan"a dönüşmektedir. Büyük dil modellerinin (LLM'ler) vizyoner yükselişi bu dönüşümü hızlandırmaktadır; ancak veri kümesi asimetrilerinin ve algoritmik halüsinasyon risklerinin aşılması, güvenli klinik entegrasyon için temel bir gereklilik olmaya devam etmektedir.

Keywords

• Yapay zeka
• dermatoloji
• doğal dil işleme
• teledermatoloji
• büyük dil modelleri

Supporting Institution

Yok

Ethical Statement

Etik Beyan: Bu çalışma, kamuya açık bibliyometrik verilerin ve akademik yayın özetlerinin analizine dayanmaktadır. Bu araştırmada insan veya hayvan denekleri veya verileri kullanılmamıştır. Bu nedenle, Helsinki Bildirgesi ve Yüksek Öğretim Kurulu (YÖK) Bilimsel Araştırma ve Yayın Etiği Yönergeleri ilkelerine uygun olarak, çalışma etik kurul onayından muaftır.

Thanks

Yok

Synthesizing 9,310 Publications Through Natural Language Processing and the Decade-Long Transformation of Artificial Intelligence in Dermatology

Abstract

Objective: This study aimed to examine the evolution of artificial intelligence (AI) research in dermatology between 2015 and 2025, extending beyond conventional bibliometric indicators through natural language processing (NLP)-assisted content analysis, and to delineate the temporal shifts in disease focus, data types, and technological infrastructure. Methods: A total of 9,310 publications retrieved from the Web of Science Core Collection were analyzed. Classical bibliometric indicators were assessed using R-Bibliometrix, VOSviewer, and CiteSpace software. In the NLP-based classification phase, which constitutes the original contribution of this study, the title and abstract of each publication were screened using a rule-based algorithm and systematically classified across three dimensions: the targeted dermatological disease, the data type employed, and the clinical task addressed. Thematic shifts between the early period (2015–2019) and the late period (2020–2025) were comparatively examined. Results: In the early period, oncology (melanoma) dominated the literature with a 32.2% research proportion; however, this rate declined to 20.9% in the late period, during which teledermatology gained momentum. The research focus exhibited a notable clinical shift toward cosmetic/aging (32.4%), surpassing oncology. Concurrently, the clinical tasks targeted by AI expanded beyond diagnosis alone to encompass disease severity scoring (29.7%) and treatment response monitoring (18.0%). Following the release of ChatGPT in 2022, large language model (LLM) research in dermatology demonstrated exponential growth, increasing 25-fold within three years. Conclusion: The AI literature in dermatology is undergoing a simultaneous three-dimensional transformation. AI is evolving from a specific melanoma screening tool into a “clinical assistant” integrated into routine outpatient practice, encompassing cosmetic and inflammatory diseases. The visionary rise of large language models (LLMs) is accelerating this transformation; however, overcoming dataset asymmetries and algorithmic hallucination risks remains essential for safe clinical integration.

Keywords

• Artificial intelligence
• dermatology
• natural language processing
• teledermatology
• large language models

Supporting Institution

None

Ethical Statement

This study is based on the analysis of publicly available bibliometric data and academic publication abstracts. No human or animal subjects or data were involved in this research. Accordingly, it is declared that the study is exempt from ethical committee approval in accordance with the principles of the Declaration of Helsinki and the Council of Higher Education (YÖK) Scientific Research and Publication Ethics Guidelines.

Thanks

None

References

1. Brinker, T. J., Hekler, A., Enk, A. H., Klode, J., Hauschild, A., Berking, C., Schilling, B., Haferkamp, S., Schadendorf, D., Holland-Letz, T., Utikal, J. S., Von Kalle, C., Ludwig-Peitsch, W., Sirokay, J., Heinzerling, L., Albrecht, M., Baratella, K., Bischof, L., Chorti, E., … Schrüfer, P. (2019). Deep learning outperformed 136 of 157 dermatologists in a head-to-head dermoscopic melanoma image classification task. European Journal of Cancer, 113, 47-54. https://doi.org/10.1016/j.ejca.2019.04.001
2. Campanella, G., Hanna, M. G., Geneslaw, L., Miraflor, A., Werneck Krauss Silva, V., Busam, K. J., Brogi, E., Reuter, V. E., Klimstra, D. S., & Fuchs, T. J. (2019). Clinical-grade computational pathology using weakly supervised deep learning on whole slide images. Nature Medicine, 25(8), 1301-1309. https://doi.org/10.1038/s41591-019-0508-1
3. Chanda, T., Hauser, K., Hobelsberger, S., Bucher, T.-C., Garcia, C. N., Wies, C., Kittler, H., Tschandl, P., Navarrete-Dechent, C., Podlipnik, S., Chousakos, E., Crnaric, I., Majstorovic, J., Alhajwan, L., Foreman, T., Peternel, S., Sarap, S., Özdemir, İ., Barnhill, R. L., … Brinker, T. J. (2024). Dermatologist-like explainable AI enhances trust and confidence in diagnosing melanoma. Nature Communications, 15(1), 524. https://doi.org/10.1038/s41467-023-43095-4
4. Daneshjou, R., Smith, M. P., Sun, M. D., Rotemberg, V., & Zou, J. (2021). Lack of Transparency and Potential Bias in Artificial Intelligence Data Sets and Algorithms: A Scoping Review. JAMA Dermatology, 157(11), 1362. https://doi.org/10.1001/jamadermatol.2021.3129
5. Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017). Dermatologist-level classification of skin cancer with deep neural networks. Nature, 542(7639), 115-118. https://doi.org/10.1038/nature21056
6. Haenssle, H. A., Fink, C., Schneiderbauer, R., Toberer, F., Buhl, T., Blum, A., Kalloo, A., Hassen, A. B. H., Thomas, L., Enk, A., Uhlmann, L., Alt, C., Arenbergerova, M., Bakos, R., Baltzer, A., Bertlich, I., Blum, A., Bokor-Billmann, T., Bowling, J., … Zalaudek, I. (2018). Man against machine: Diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists. Annals of Oncology, 29(8), 1836-1842. https://doi.org/10.1093/annonc/mdy166
7. Haggenmüller, S., Maron, R. C., Hekler, A., Utikal, J. S., Barata, C., Barnhill, R. L., Beltraminelli, H., Berking, C., Betz-Stablein, B., Blum, A., Braun, S. A., Carr, R., Combalia, M., Fernandez-Figueras, M.-T., Ferrara, G., Fraitag, S., French, L. E., Gellrich, F. F., Ghoreschi, K., … Brinker, T. J. (2021). Skin cancer classification via convolutional neural networks: Systematic review of studies involving human experts. European Journal of Cancer, 156, 202-216. https://doi.org/10.1016/j.ejca.2021.06.049
8. He, K., Gan, C., Li, Z., Rekik, I., Yin, Z., Ji, W., Gao, Y., Wang, Q., Zhang, J., & Shen, D. (2023). Transformers in medical image analysis. Intelligent Medicine, 3(1), 59-78. https://doi.org/10.1016/j.imed.2022.07.002

9. Hwang, J. K., Del Toro, N. P., Han, G., Oh, D. H., Tejasvi, T., & Lipner, S. R. (2024). Review of Teledermatology: Lessons Learned from the COVID-19 Pandemic. American Journal of Clinical Dermatology, 25(1), 5-14. https://doi.org/10.1007/s40257-023-00826-z
10. Kania, B., Montecinos, K., & Goldberg, D. J. (2024). Artificial intelligence in cosmetic dermatology. Journal of Cosmetic Dermatology, 23(10), 3305-3311. https://doi.org/10.1111/jocd.16538
11. Lewandowski, M., Kropidłowska, J., Kvinen, A., & Barańska‐Rybak, W. (2025). A Systemic Review of Large Language Models and Their Implications in Dermatology. Australasian Journal of Dermatology, 66(4). https://doi.org/10.1111/ajd.14484
12. Nahm, W. J., Sohail, N., Burshtein, J., Goldust, M., & Tsoukas, M. (2025). Artificial Intelligence in Dermatology: A Comprehensive Review of Approved Applications, Clinical Implementation, and Future Directions. International Journal of Dermatology, 64(9), 1568-1583. https://doi.org/10.1111/ijd.17847
13. Rajpurkar, P., Chen, E., Banerjee, O., & Topol, E. J. (2022). AI in health and medicine. Nature Medicine, 28(1), 31-38. https://doi.org/10.1038/s41591-021-01614-0
14. Salinas, M. P., Sepúlveda, J., Hidalgo, L., Peirano, D., Morel, M., Uribe, P., Rotemberg, V., Briones, J., Mery, D., & Navarrete-Dechent, C. (2024). A systematic review and meta-analysis of artificial intelligence versus clinicians for skin cancer diagnosis. Npj Digital Medicine, 7(1), 125. https://doi.org/10.1038/s41746-024-01103-x
15. Shen, Y., Heacock, L., Elias, J., Hentel, K. D., Reig, B., Shih, G., & Moy, L. (2023). ChatGPT and Other Large Language Models Are Double-edged Swords. Radiology, 307(2), e230163. https://doi.org/10.1148/radiol.230163
16. Takahashi, S., Sakaguchi, Y., Kouno, N., Takasawa, K., Ishizu, K., Akagi, Y., Aoyama, R., Teraya, N., Bolatkan, A., Shinkai, N., Machino, H., Kobayashi, K., Asada, K., Komatsu, M., Kaneko, S., Sugiyama, M., & Hamamoto, R. (2024). Comparison of Vision Transformers and Convolutional Neural Networks in Medical Image Analysis: A Systematic Review. Journal of Medical Systems, 48(1), 84. https://doi.org/10.1007/s10916-024-02105-8
17. Thunga, S., Khan, M., Cho, S. I., Na, J. I., & Yoo, J. (2025). AI in Aesthetic/Cosmetic Dermatology: Current and Future. Journal of Cosmetic Dermatology, 24(1), e16640. https://doi.org/10.1111/jocd.16640
18. Tricco, A. C., Lillie, E., Zarin, W., O’Brien, K. K., Colquhoun, H., Levac, D., Moher, D., Peters, M. D. J., Horsley, T., Weeks, L., Hempel, S., Akl, E. A., Chang, C., McGowan, J., Stewart, L., Hartling, L., Aldcroft, A., Wilson, M. G., Garritty, C., … Straus, S. E. (2018). PRISMA Extension for Scoping Reviews (PRISMA-ScR): Checklist and Explanation. Annals of Internal Medicine, 169(7), 467-473. https://doi.org/10.7326/M18-0850
19. Tschandl, P., Rinner, C., Apalla, Z., Argenziano, G., Codella, N., Halpern, A., Janda, M., Lallas, A., Longo, C., Malvehy, J., Paoli, J., Puig, S., Rosendahl, C., Soyer, H. P., Zalaudek, I., & Kittler, H. (2020). Human–computer collaboration for skin cancer recognition. Nature Medicine, 26(8), 1229-1234. https://doi.org/10.1038/s41591-020-0942-0
20. Wang, G., Meng, X., & Zhang, F. (2023). Past, present, and future of global research on artificial intelligence applications in dermatology: A bibliometric analysis. Medicine, 102(45), e35993. https://doi.org/10.1097/MD.0000000000035993
21. Young, J. N., Ross O’Hagan, Poplausky, D., Levoska, M. A., Gulati, N., Ungar, B., & Ungar, J. (2023). The utility of ChatGPT in generating patient-facing and clinical responses for melanoma. Journal of the American Academy of Dermatology, 89(3), 602-604. https://doi.org/10.1016/j.jaad.2023.05.024
22. Yuan, L., Jin, K., Shao, A., Feng, J., Shi, C., Ye, J., & Grzybowski, A. (2024). Analysis of international publication trends in artificial intelligence in skin cancer. Clinics in Dermatology, 42(6), 570-584. https://doi.org/10.1016/j.clindermatol.2024.09.012
23. Zhou, J., He, X., Sun, L., Xu, J., Chen, X., Chu, Y., Zhou, L., Liao, X., Zhang, B., Afvari, S., & Gao, X. (2024). Pre-trained multimodal large language model enhances dermatological diagnosis using SkinGPT-4. Nature Communications, 15(1), 5649. https://doi.org/10.1038/s41467-024-50043-3