Onkolojide Büyük Dil Modellerinin Klinik Karar Desteğindeki Yeri

Authors

Emre Uysal
https://orcid.org/0000-0002-4737-4304

Synopsis

In oncology, a guideline-concordant treatment recommendation may be inappropriate for an individual patient because of specific clinical circumstances. This distinction is central to evaluating large language models (LLMs) for clinical decision support. Their ability to convey guideline information accurately needs to be assessed together with the agreement of their recommendations with specialist and multidisciplinary tumor board assessments. Whether the additional information they provide improves the quality of physicians’ clinical decisions also requires evaluation. This chapter considers studies from different oncology settings within this framework. Findings on guideline interpretation, patient record summarization, and generation of treatment options are considered alongside the methods used to assess performance. Despite high performance in some studies, inappropriate recommendations may accompany valid options, and clinically important details may be overlooked. Overall accuracy therefore needs to be considered together with the nature of errors, agreement with expert assessment, and contribution to physician decision making. Privacy and ethical responsibilities associated with real patient data are also discussed. Current evidence suggests that LLMs may assist physicians with selected tasks, but remains insufficient to support their use as independent clinical decision makers. Establishing their role in clinical practice requires evidence of added benefit under physician oversight and assessment of their effects on patient safety.

 

References

Chen S, Kann BH, Foote MB, et al. Use of Artificial Intelligence Chatbots for Cancer Treatment Information. JAMA Oncology 2023;9(10):1459–1462. doi:10.1001/jamaoncol.2023.2954

Wong EYT, Verlingue L, Aldea M, et al. ESMO guidance on the use of Large Language Models in Clinical Practice (ELCAP). Annals of Oncology 2025;36(12):1447–1457. doi:10.1016/j.annonc.2025.09.001

Rydzewski NR, Dinakaran D, Zhao SG, et al. Comparative Evaluation of LLMs in Clinical Oncology. NEJM AI 2024;1(5):AIoa2300151. doi:10.1056/AIoa2300151

Hager P, Jungmann F, Holland R, et al. Evaluation and mitigation of the limitations of large language models in clinical decision-making. Nature Medicine 2024;30:2613–2622. doi:10.1038/s41591-024-03097-1

Carl N, Schramm F, Haggenmüller S, et al. Large language model use in clinical oncology. npj Precision Oncology 2024;8:240. doi:10.1038/s41698-024-00733-4

Akkus Yildirim B, Tutun B, Durak G, et al. Large language models standardize the interpretation of complex oncology guidelines for brain metastases. Communications Medicine 2026;6:56. doi:10.1038/s43856-025-01315-6

Kaiser KN, Hughes AJ, Yang AD, et al. Use of large language models as clinical decision support tools for management pancreatic adenocarcinoma using National Comprehensive Cancer Network guidelines. Surgery 2025;182:109267. doi:10.1016/j.surg.2025.109267

Griewing S, Knitza J, Boekhoff J, et al. Evolution of publicly available large language models for complex decision-making in breast cancer care. Archives of Gynecology and Obstetrics 2024;310:537–550. doi:10.1007/s00404-024-07565-4

Ah-Thiane L, Heudel PE, Campone M, et al. Large Language Models as Decision-Making Tools in Oncology: Comparing Artificial Intelligence Suggestions and Expert Recommendations. JCO Clinical Cancer Informatics 2025;9:e2400230. doi:10.1200/CCI-24-00230

Goh SSN, Mariappan R, Tan GSW, et al. Augmenting Large Language Models With National Comprehensive Cancer Network Guidelines for Improved and Standardized Adjuvant Therapy Recommendations in Postoperative Breast Cancer Cases. JCO Clinical Cancer Informatics 2025;9:e2400243. doi:10.1200/CCI-24-00243

Schmutz M, Sommer S, Sander J, et al. Large language model processing capabilities of ChatGPT 4.0 to generate molecular tumor board recommendations—a critical evaluation on real world data. The Oncologist 2025;30(10):oyaf293. doi:10.1093/oncolo/oyaf293

Benary M, Wang XD, Schmidt M, et al. Leveraging large language models for decision support in personalized oncology. JAMA Network Open 2023;6(11):e2343689. doi:10.1001/jamanetworkopen.2023.43689

Bertolo R, De Bon L, Caudana F, et al. Role of large language models in the multidisciplinary decision-making process for patients with renal cell carcinoma: a pilot experience. npj Precision Oncology 2025;9:257. doi:10.1038/s41698-025-01014-4

Rinderknecht E, Haas M, Schnabel MJ, et al. Benchmarking Large Language Models Against Multidisciplinary Tumor Boards in Urological Oncology: Results from the Blinded, Prospective CONCORDIA Study. European Urology Oncology 2026;9(3):589–597. doi:10.1016/j.euo.2025.11.016

Adaş M, Çörekci AM, Demirkale İ, et al. High Overall Performance but Limited Multidisciplinary Depth: A Cross-Sectional Evaluation of ChatGPT in Pathological Fractures of Plasma Cell Tumors. Research Square. 2026 Jul 14. Preprint (Version 1). doi:10.21203/rs.3.rs-9628103/v1

Ferber D, El Nahhas OSM, Wölflein G, et al. Development and validation of an autonomous artificial intelligence agent for clinical decision-making in oncology. Nature Cancer 2025;6:1337–1349. doi:10.1038/s43018-025-00991-6

Lajmi N, Patel M, Obery G, et al. Simulation-Based Evaluation of a Large Language Model-Enabled Clinical Decision Support Platform in Oncology. JCO Clinical Cancer Informatics 2026;10:e2500244. doi:10.1200/CCI-25-00244

Hao Y, Qiu Z, Holmes J, et al. Large language model integrations in cancer decision-making: a systematic review and meta-analysis. npj Digital Medicine 2025;8:450. doi:10.1038/s41746-025-01824-7

Kişisel Verileri Koruma Kurumu. Özel Nitelikli Kişisel Veriler. (01/10/2026 tarihinde https://www.kvkk.gov.tr/Icerik/2051/Ozel-Nitelikli-Kisisel-Veriler adresinden ulaşılmıştır).

Kişisel Verileri Koruma Kurumu. Yurt Dışına Aktarım. (01/10/2026 tarihinde https://www.kvkk.gov.tr/Icerik/2053/Yurtdisina-Aktarim adresinden ulaşılmıştır).

European Parliament and Council of the European Union. Regulation (EU) 2016/679 (General Data Protection Regulation). (01/10/2026 tarihinde https://eur-lex.europa.eu/legal-content/EN/TXT/?uri=CELEX:32016R0679 adresinden ulaşılmıştır).

Kişisel Verileri Koruma Kurumu. Üretken Yapay Zekâ ve Kişisel Verilerin Korunması Rehberi (15 Soruda). (01/10/2026 tarihinde https://www.kvkk.gov.tr/Icerik/8547/uretken-yapay-zeka-ve-kisisel-verilerin-korunmasi-rehberi-15-soruda adresinden ulaşılmıştır).

European Parliament and Council of the European Union. Regulation (EU) 2017/745 on medical devices. (01/10/2026 tarihinde https://eur-lex.europa.eu/eli/reg/2017/745/oj/eng adresinden ulaşılmıştır).

Published

November 16, 2026

License

License