Jinekolojik Onkolojide Cerrahi Karar Verme Sürecinde Yapay Zekânın Rolünün Araştırılması: Bir Fizibilite Çalışması

Abstract

Giriş: Tıp pratiğinde yapay zekâ (YZ) uygulamalarının kullanımı hızla artmaktadır. İlgili veriler girildiğinde, YZ sistemleri triyaj, tanı, yönetim ve cerrahi planlama konularında sağlık profesyonellerine destek sağlayabilmektedir. Amaç: Bu çalışmanın amacı, jinekolojik kanserli hastalarda ChatGPT-4o’nun cerrahi öneriler oluşturmadaki klinik geçerliliğini ve uygulanabilirliğini değerlendirmek; modelin çıktılarının deneyimli jinekolojik onkoloji uzmanlarının kararlarıyla uyumunu incelemektir. Yöntem: Bu fizibilite çalışmasında, 5 endometrium kanseri (EK), 5 adneksiyel kitle (AK) ve 5 serviks kanseri (SK) vakası olmak üzere toplam 15 kurgusal olgu senaryosu oluşturuldu. Bu senaryolar, jinekolojik onkoloji cerrahisinde en az beş yıllık deneyime sahip iki uzman tarafından uygunluk açısından gözden geçirildi. Olgular önce ChatGPT-4o tarafından analiz edilerek cerrahi yönetim önerileri oluşturuldu. Daha sonra aynı senaryolar, Avrupa Jinekolojik Onkoloji Derneği (ESGO) akreditasyonuna sahip bir merkezde görev yapan iki uzman ve iki asistan tarafından değerlendirildi. YZ tarafından oluşturulan öneriler Global Quality Score (GQS) sistemi kullanılarak değerlendirildi ve uzman kararlarıyla karşılaştırıldı. Bulgular: ChatGPT-4o tarafından sunulan cerrahi öneriler, hekimlerin kararlarıyla yüksek düzeyde uyum göstermiştir. En yüksek tutarlılık EK vakalarında gözlenmiştir. Özellikle klinik rehberlerde yönetim algoritmaları net olarak tanımlanmış olgularda, YZ modeli doğru ve kılavuza uygun öneriler sunmuştur. Ancak daha karmaşık olgularda sınırlı klinik öngörü yeteneği dikkati çekmiştir. Sonuç: Bu fizibilite çalışması, ChatGPT-4o’nun jinekolojik kanserli hastalarda klinik olarak anlamlı ve kılavuz uyumlu cerrahi öneriler sunabildiğini göstermektedir. YZ destekli cerrahi karar verme süreçlerinin etkinliğini değerlendiren ileri çalışmalara ihtiyaç vardır.

Keywords

• jinekolojik kanserler
• yapay zeka
• chatGPT
• cerrahi karar

Exploring the Role of Artificial Intelligence in Surgical Decision-Making in Gynecologic Oncology: A Feasibility Study

Abstract

Introduction: The use of artificial intelligence (AI) applications in medical practice is rapidly increasing. When relevant data are entered, AI systems can assist healthcare professionals by providing information on triage, diagnosis, management, and surgical planning. Objective: This study aimed to evaluate the clinical relevance and feasibility of ChatGPT-4o in generating surgical recommendations for patients with gynecologic cancers, by comparing its outputs with the decisions made by experienced gynecologic oncology specialists. Methods: In this feasibility study, a total of 15 fictional case scenarios were created, including 5 cases each of endometrial cancer (EC), adnexal masses (AM), and cervical cancer (CC). These scenarios were first reviewed for appropriateness by two specialists with at least five years of experience in gynecologic oncology surgery. The cases were initially analyzed by ChatGPT-4o, which provided surgical management recommendations. Subsequently, the same scenarios were evaluated by two specialists and two fellows working at a European Society of Gynaecological Oncology (ESGO)-accredited center. The AI-generated recommendations were assessed using the Global Quality Score (GQS) system and compared with expert evaluations. Results: The surgical recommendations provided by ChatGPT-4o showed a high degree of concordance with the physicians’ decisions. The highest consistency was observed in the EC cases. Particularly in cases where management pathways were clearly defined by clinical guidelines, the AI model provided accurate suggestions. However, limited clinical insight was noted in more complex scenarios. Conclusion: This feasibility study demonstrates that ChatGPT-4o is capable of providing clinically meaningful and guideline-compliant surgical recommendations for patients with gynecologic cancers. Further studies assessing the effectiveness of AI-assisted surgical decision-making processes are warranted to better establish the clinical applicability of this model.

Keywords

• Artificial İntelligence
• ChatGPT
• Gynecologic Oncology
• Surgical Desicion

References

1. Rao A, Kim J, Kamineni M, Pang M, Lie W, Dreyer KJ, Succi MD. Evaluating GPT as an Adjunct for Radiologic Decision Making: GPT-4 Versus GPT-3.5 in a Breast Imaging Pilot. J Am Coll Radiol. 2023 Oct;20(10):990-997. doi: 10.1016/j.jacr.2023.05.003. Epub 2023 Jun 21. PMID: 37356806; PMCID: PMC10733745.
2. Yin J, Ngiam KY, Teo HH. Role of Artificial Intelligence Applications in Real-Life Clinical Practice: Systematic Review. J Med Internet Res. 2021 Apr 22;23(4):e25759. doi: 10.2196/25759. PMID: 33885365; PMCID: PMC8103304.
3. He J, Baxter SL, Xu J, Xu J, Zhou X, Zhang K. The practical implementation of artificial intelligence technologies in medicine. Nat Med. 2019 Jan;25(1):30-36. doi: 10.1038/s41591-018-0307-0. Epub 2019 Jan 7. PMID: 30617336; PMCID: PMC6995276
4. Levin G, Horesh N, Brezinov Y, Meyer R. Performance of ChatGPT in medical examinations: A systematic review and a meta-analysis. BJOG. 2024 Feb;131(3):378-380. doi: 10.1111/1471-0528.17641. Epub 2023 Aug 21. PMID: 37604703.
5. Farina E, Nabhen JJ, Dacoregio MI, Batalini F, Moraes FY. An overview of artificial intelligence in oncology. Future Sci OA. 2022 Feb 10;8(4):FSO787. doi: 10.2144/fsoa-2021-0074. PMID: 35369274; PMCID: PMC8965797.
6. Elkhader J, Elemento O. Artificial intelligence in oncology: From bench to clinic. Semin Cancer Biol. 2022 Sep;84:113-128. doi: 10.1016/j.semcancer.2021.04.013. Epub 2021 Apr 26. PMID: 33915289.
7. Mysona DP, Kapp DS, Rohatgi A, Lee D, Mann AK, Tran P, Tran L, She JX, Chan JK. Applying Artificial Intelligence to Gynecologic Oncology: A Review. Obstet Gynecol Surv. 2021 May;76(5):292-301. doi: 10.1097/OGX.0000000000000902. PMID: 34032861.
8. Rajpurkar P, Chen E, Banerjee O, Topol EJ. AI in health and medicine. Nat Med. 2022 Jan;28(1):31-38. doi: 10.1038/s41591-021-01614-0. Epub 2022 Jan 20. PMID: 35058619.

9. Albright BB, Monuszko KA, Kaplan SJ, Davidson BA, Moss HA, Huang AB, Melamed A, Wright JD, Havrilesky LJ, Previs RA. Primary cytoreductive surgery for advanced stage endometrial cancer: a systematic review and meta-analysis. Am J Obstet Gynecol. 2021 Sep;225(3):237.e1-237.e24. doi: 10.1016/j.ajog.2021.04.254. Epub 2021 May 4. PMID: 33957111; PMCID: PMC8717361.
10. Kengsakul M, Nieuwenhuyzen-de Boer GM, Udomkarnjananun S, Kerr SJ, Niehot CD, van Beekhuizen HJ. Factors predicting postoperative morbidity after cytoreductive surgery for ovarian cancer: a systematic review and meta-analysis. J Gynecol Oncol. 2022 Jul;33(4):e53. doi: 10.3802/jgo.2022.33.e53. Epub 2022 Jun 7. PMID: 35712967; PMCID: PMC9250852.
11. Filis P, Mauri D, Markozannes G, Tolia M, Filis N, Tsilidis K. Hyperthermic intraperitoneal chemotherapy (HIPEC) for the management of primary advanced and recurrent ovarian cancer: a systematic review and meta-analysis of randomized trials. ESMO Open. 2022 Oct;7(5):100586. doi: 10.1016/j.esmoop.2022.100586. Epub 2022 Sep 16. PMID: 36116421; PMCID: PMC9588894.
12. Kayabaşı M, Köksaldı S, Durmaz Engin C. Evaluating the quality and reliability of YouTube videos on myopia: a video content analysis. Int Ophthalmol. 2024 Jul 18;44(1):329. doi: 10.1007/s10792-024-03250-2. PMID: 39026115.
13. Bernard, André M.D.1; Langille, Morgan B.Sc.2; Hughes, Stephanie B.Sc.2; Rose, Caren M.Sc.2; Leddin, Desmond M.D.2; van Zanten, Sander Veldhuyzen M.D.2. A Systematic Review of Patient Inflammatory Bowel Disease Information Resources on the World Wide Web. American Journal of Gastroenterology 102(9):p 2070-2077, September 2007.
14. Psilopatis I, Heindl F, Cupisti S, Fischer U, Kohlmann V, Schneider M, Bader S, Krueckel A, Emons J. The role of artificial intelligence in gynecologic and obstetric emergencies. Eur J Obstet Gynecol Reprod Biol. 2025 Mar;306:94-100. doi: 10.1016/j.ejogrb.2025.01.007. Epub 2025 Jan 6. PMID: 39799741.
15. Psilopatis I, Sipulina N, Stuebs FA, Heindl F, Poeschke P, Bader S, Krueckel A, Fasching PA, Beckmann MW, Emons J. The Role of Artificial Intelligence in Gynecologic Oncology Decision-Making: A Feasibility Study. Gynecol Obstet Invest. 2025 Feb 20:1-9. doi: 10.1159/000544751. Epub ahead of print. PMID: 39978322.
16. Reicher L, Lutsker G, Michaan N, Grisaru D, Laskov I. Exploring the role of artificial intelligence, large language models: Comparing patient-focused information and clinical decision support capabilities to the gynecologic oncology guidelines. Int J Gynaecol Obstet. 2025 Feb;168(2):419-427. doi: 10.1002/ijgo.15869. Epub 2024 Aug 20. PMID: 39161265; PMCID: PMC11726133.
17. Mysona DP, Kapp DS, Rohatgi A, Lee D, Mann AK, Tran P, Tran L, She JX, Chan JK. Applying Artificial Intelligence to Gynecologic Oncology: A Review. Obstet Gynecol Surv. 2021 May;76(5):292-301. doi: 10.1097/OGX.0000000000000902. PMID: 34032861.
18. Butt SR, Soulat A, Lal PM, Fakhor H, Patel SK, Ali MB, Arwani S, Mohan A, Majumder K, Kumar V, Tejwaney U, Kumar S. Impact of artificial intelligence on the diagnosis, treatment and prognosis of endometrial cancer. Ann Med Surg (Lond). 2024 Jan 17;86(3):1531-1539. doi: 10.1097/MS9.0000000000001733. PMID: 38463097; PMCID: PMC10923372.
19. Akazawa M, Hashimoto K. Artificial Intelligence in Ovarian Cancer Diagnosis. Anticancer Res. 2020 Aug;40(8):4795-4800. doi: 10.21873/anticanres.14482. PMID: 32727807.
20. Wu T, Lucas E, Zhao F, Basu P, Qiao Y. Artificial intelligence strengthens cervical cancer screening - present and future. Cancer Biol Med. 2024 Sep 19;21(10):864–79. doi: 10.20892/j.issn.2095-3941.2024.0198. PMID: 39297572; PMCID: PMC11523278.
21. Jiang Y, Wang C, Zhou S. Artificial intelligence-based risk stratification, accurate diagnosis and treatment prediction in gynecologic oncology. Semin Cancer Biol. 2023 Nov;96:82-99. doi: 10.1016/j.semcancer.2023.09.005. Epub 2023 Sep 30. PMID: 37783319.