Journals / Çukurova Anestezi ve Cerrahi Bilimler Dergisi / 2026 / Cilt: 9 Sayı: 3

Quality and Safety of ChatGPT Responses to Anesthesia-Related Patient Questions: An Expert Evaluation

Anestezi ile İlgili Hasta Sorularına ChatGPT Yanıtlarının Kalitesi ve Olası Risklerinin Değerlendirilmesi: Uzman Değerlendirmesi

Engin Çetin(kocaeli şehir hastanesi)0000-0002-3011-3968
Tunahan Çevik(Kocaeli Şehir Hastanesi)0000-0002-1185-4971
Pages
746–751
Publication Date
2026-09-30
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Although the overall risk rate is relatively low, the presence of potentially misleading content underscores the need for clinician oversight when such tools are used for patient education.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Abstract Aim: Large language models such as ChatGPT are increasingly used by patients to obtain perioperative information.
📊
Key Findings & Data:This study aimed to evaluate the quality and potential clinical risks of ChatGPT-generated responses to anesthesia-related questions using a structured scoring system.
💡
Conclusion & Impact:Although the overall risk rate is relatively low, the presence of potentially misleading content underscores the need for clinician oversight when such tools are used for patient education.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:ChatGPT · anesteziyoloji · yapay zeka

Abstract

Abstract Aim: Large language models such as ChatGPT are increasingly used by patients to obtain perioperative information. Given the complexity and potential risks associated with anesthetic management, the accuracy and safety of such information are of critical importance. This study aimed to evaluate the quality and potential clinical risks of ChatGPT-generated responses to anesthesia-related questions using a structured scoring system. Materials and Methods: A total of 100 anesthesia-related questions were evaluated, including 50 guideline-derived questions and 50 frequently asked public questions. All questions were submitted to the ChatGPT-4 model in Turkish using the premium version. Responses were independently evaluated by three anesthesiology specialists using the Global Quality Score (GQS; 1–5). In addition, each response was assessed for the presence of potentially harmful or misleading information. Comparisons were conducted between question categories. Results: The median Global Quality Score (GQS) differed significantly between question types, with higher scores observed for frequently asked questions than for guideline-based questions (4 [IQR: 3–5] vs. 3 [IQR: 2–4], p < 0.001). Potentially harmful or misleading information was identified in 7% of responses and was more frequent in guideline-based questions than in frequently asked questions (12% vs. 2%, p = 0.02). Conclusion: ChatGPT provides high-quality and comprehensible responses to general anesthesia-related questions. However, its performance declines in guideline-based, clinically critical topics. Although the overall risk rate is relatively low, the presence of potentially misleading content underscores the need for clinician oversight when such tools are used for patient education. Keywords: ChatGPT; anesthesiology; artificial intelligence; patient education; global quality score

Özet

Özet Amaç: Büyük dil modelleri (Large Language Models) son yıllarda hastaların tıbbi bilgiye erişiminde giderek daha sık kullanılmaktadır. Ancak anestezi uygulamalarının karmaşıklığı ve potansiyel riskleri göz önüne alındığında, bu sistemlerin sunduğu bilgilerin doğruluğu ve güvenliği büyük önem taşımaktadır. Bu çalışmada ChatGPT’nin anestezi ile ilgili hasta sorularına verdiği yanıtların kalitesi ve olası klinik riskleri değerlendirilmesi amaçlanmıştır. Gereç ve Yöntem: Bu gözlemsel kesitsel çalışmada toplam 100 anestezi ile ilişkili soru değerlendirilmiştir. Soruların 50’si uluslararası anestezi kılavuzlarından türetilmiş, 50’si ise internet ortamında sık sorulan hasta sorularından oluşturulmuştur. Tüm sorular ChatGPT-4 modeline Türkçe olarak yöneltilmiştir. Elde edilen yanıtlar üç anesteziyoloji uzmanı tarafından bağımsız olarak Global Quality Score (GQS; 1–5) kullanılarak değerlendirilmiştir. Ayrıca yanıtlarda potansiyel olarak zararlı veya yanıltıcı bilgi bulunup bulunmadığı analiz edilmiştir. Bulgular: Sık sorulan sorular için elde edilen yanıtların kalite skorlarının, kılavuz temelli sorulara kıyasla daha yüksek olduğu saptanmıştır. Yüksek kaliteli yanıt oranı (GQS ≥4) sık sorulan sorularda %76 iken kılavuz temelli sorularda %42 olarak bulunmuştur. Potansiyel olarak zararlı veya yanıltıcı içerik toplam yanıtların %7’sinde tespit edilmiş olup bu oran kılavuz temelli sorularda daha yüksek bulunmuştur (%12 vs. %2, p = 0.02). Değerlendiriciler arası uyum analizi yüksek düzeyde güvenilirlik göstermiştir (ICC = 0.88). Sonuç: ChatGPT genel anestezi ile ilgili sık sorulan sorulara anlaşılabilir ve yüksek kaliteli yanıtlar sunabilmektedir. Ancak kılavuz temelli ve klinik açıdan kritik konularda yanıt kalitesinin azaldığı görülmektedir. Bu nedenle yapay zeka tabanlı sistemlerin hasta bilgilendirmesinde yardımcı araçlar olarak kullanılabileceği, ancak klinisyen rehberliği olmadan tek başına güvenilir bir bilgi kaynağı olarak değerlendirilmemesi gerektiği düşünülmektedir. Anahtar Kelimeler: ChatGPT; anesteziyoloji; yapay zeka; hasta eğitimi; global kalite skoru

🔖

Cite This Article

Çetin, E., Çevik, T. (2026). Quality and Safety of ChatGPT Responses to Anesthesia-Related Patient Questions: An Expert Evaluation. Çukurova Anestezi ve Cerrahi Bilimler Dergisi, Cilt: 9 Sayı: 3, 746–751. https://doi.org/10.36516/jocass.1934689

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (14)

  1. Miniksar OH, Yuksek A. Does The Internet Provide Enough Information About Sepsis for The General Public. Cukurova Anestezi ve Cerrahi Bilimler Dergisi 2021;4:173–81. https://doi.org/10.36516/jocass.2021.86
  2. Yuksek A, Talih G. Quality of internet-based information on obstetric anesthesia. Ann Med Res 2019;26:2904. https://doi.org/10.5455/annalsmedres.2019.08.493
  3. Sam Ozdemir M, Ozdemir H. Is YouTube really a source of information on MRI guided prostate biopsy? Bozok Tip Dergisi 2024. https://doi.org/10.16919/bozoktip.1514887
  4. Obermeyer Z, Emanuel EJ. Predicting the Future - Big Data, Machine Learning, and Clinical Medicine. N Engl J Med 2016;375:1216–9. https://doi.org/10.1056/NEJMp1606181
  5. Yanagita Y, Yokokawa D, Uchida S, Tawara J, Ikusaka M. Accuracy of ChatGPT on Medical Questions in the National Medical Licensing Examination in Japan: Evaluation Study. JMIR Form Res 2023;7:e48023. https://doi.org/10.2196/48023
  6. Ozgor F, Caglar U, Halis A, Cakir H, Aksu UC, Ayranci A, et al. Urological Cancers and ChatGPT: Assessing the Quality of Information and Possible Risks for Patients. Clin Genitourin Cancer 2024;22:454-457.e4. https://doi.org/10.1016/j.clgc.2023.12.017
  7. Yeo YH, Samaan JS, Ng WH, Ting P-S, Trivedi H, Vipani A, et al. Assessing the performance of ChatGPT in answering questions regarding cirrhosis and hepatocellular carcinoma. Clin Mol Hepatol 2023;29:721–32. https://doi.org/10.3350/cmh.2023.0089
  8. Ortac M, Ergul RB, Yazili HB, Ozervarli MF, Tonyali S, Sarilar O, et al. ChatGPT’s competence in responding to urological emergencies. Ulus Travma Acil Cerrahi Derg 2025;31:291–5. https://doi.org/10.14744/tjtes.2024.03377
  9. Nagesh D, Keating DP, Divakaruni RV, Beutel BG. Feasibility evaluation of large language models in anesthesia-specific post-operative care instructions for total knee arthroplasty. PEC Innovation 2026;8:100444. https://doi.org/10.1016/j.pecinn.2025.100444
  10. Tulgar S, Aksu C, Selvi O, Sultan P, Dogan AT, Thomas DT, et al. A comparative evaluation of the quality of responses provided by different large language model chatbots to frequently asked questions regarding nerve blocks. BMC Anesthesiol 2026;26:98. https://doi.org/10.1186/s12871-025-03596-9
  11. Olcar HA, Aydin AG, Uluturk S, Aras DS, Korkmaz M, Korkmaz IN. Evaluation of ChatGPT-4 Artificial Intelligence Responses to Common Problems in Patients after Hip Replacement with Expert Opinion. Bozok Tip Dergisi 2023. https://doi.org/10.16919/bozoktip.1318421
  12. Balci MF, Akdemir C, Yildirim F. Is Artificial Intelligence-Assisted Pregnancy Counseling Feasible? An Evaluation of the Quality of ChatGPT Responses. Cukurova Anestezi ve Cerrahi Bilimler Dergisi 2025;8:336–40. https://doi.org/10.36516/jocass.1753846
  13. Alber DA, Yang Z, Alyakin A, Yang E, Rai S, Valliani AA, et al. Medical large language models are vulnerable to data-poisoning attacks. Nat Med 2025;31:618–26. https://doi.org/10.1038/s41591-024-03445-1
  14. Alanoglu Z, Tulgar S, Kilicaslan A, Can OS. Artificial Intelligence and Large Language Models: Editorial Reflections. Turk J Anaesthesiol Reanim 2025;53:280–1. https://doi.org/10.4274/TJAR.2025.252355