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

Healthcare is one of the many industries where large language models (LLMs) are making steady progress. Similar to a personal assistant, artificial intelligence (AI) is a potent and time-saving healthcare aid, but it is essentially unable to take the place of human clinicians' crucial decision-making. The development of multimodal transformers offers enormous promise by concurrently analyzing text, pictures, and structured data.