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

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.