Çok Modlu Büyük Dil Modellerinin Tıptaki Güçlü Yönleri ve Sınırlarına İlişkin Örtüşen Kanıtlar: Günay-Polatkan ve Arkadaşlarının Makalesine Yorum

Öz

We read with great interest the article by Günay-Polatkan et al.1 evaluating GPT-4o and Gemini-1.5-Flash on case- and ECG-based cardiology questions relevant to emergency practice. Having recently evaluated a multimodal large language model (LLM) in a related setting, we would like to share our findings. Despite differences in domain and task, they converge with several of the authors’ observations and interpretations. It is also encouraging to see this line of research developing at our institution.

Anahtar Kelimeler

• Yapay Zeka
• Tıp Eğitimi
• Anatomi
• Ölçme Değerlendirme

Converging Evidence on the Strengths and Limits of Multimodal Large Language Models in Medicine: Comment on Günay-Polatkan et al.

Öz

We read with great interest the article by Günay-Polatkan et al.1 evaluating GPT-4o and Gemini-1.5-Flash on case- and ECG-based cardiology questions relevant to emergency practice. Having recently evaluated a multimodal large language model (LLM) in a related setting, we would like to share our findings. Despite differences in domain and task, they converge with several of the authors’ observations and interpretations. It is also encouraging to see this line of research developing at our institution.

Anahtar Kelimeler

• Artificial intelligence
• medical education
• anatomy
• assessment

Kaynakça

1. 1. Günay-Polatkan Ş, Sığırlı D, Durak VA, Alak Ç, İris Kan İ. Performance of generative AI models on cardiology practice in emergency service: a pilot evaluation of GPT-4.o and Gemini-1.5-Flash. Uludağ Üniversitesi Tıp Fakültesi Dergisi. 2025;51(2):239-246. doi:10.32708/uutfd.1718121
2. 2. Günay S, Öztürk A, Yiğit Y. The accuracy of Gemini, GPT-4, and GPT-4o in ECG analysis: a comparison with cardiologists and emergency medicine specialists. Am J Emerg Med. 2024;84:68-73. doi:10.1016/j.ajem.2024.07.043
3. 3. Bhayana R, Krishna S, Bleakney RR. Performance of ChatGPT on a radiology board-style examination: insights into current strengths and limitations. Radiology. 2023;307(5):e230582. doi:10.1148/radiol.230582
4. 4. Teckwani SH, Wong AH, Luke NV, Low ICC. Accuracy and reliability of large language models in assessing learning outcomes achievement across cognitive domains. Adv Physiol Educ. 2024;48(4):904-914. doi:10.1152/advan.00137.2024
5. 5. Hassanein FEA, Hussein RR, Ahmed Y, El-Guindy J, Ahmed DE, Abou-Bakr A. Calibration of AI large language models with human subject matter experts for grading of clinical short-answer responses in dental education. BMC Oral Health. 2026;26(1):286. doi:10.1186/s12903-026-07665-4
6. 6. Grévisse C. LLM-based automatic short answer grading in undergraduate medical education. BMC Med Educ. 2024;24(1):1060. doi:10.1186/s12909-024-06026-5