WangLab at MEDIQA-M3G 2024: Multimodal Medical Answer Generation using Large Language Models
This work addresses medical visual question answering for healthcare AI applications, but it is incremental as it applies existing methods (LLM APIs and CLIP-style embeddings) to a specific competition task.
The paper tackled medical visual question answering by submitting two solutions to the MEDIQA-M3G 2024 shared task: a multi-stage LLM approach using Claude 3 Opus API and a CLIP-style image classification method, which placed 1st and 2nd respectively, substantially outperforming other entries.
This paper outlines our submission to the MEDIQA2024 Multilingual and Multimodal Medical Answer Generation (M3G) shared task. We report results for two standalone solutions under the English category of the task, the first involving two consecutive API calls to the Claude 3 Opus API and the second involving training an image-disease label joint embedding in the style of CLIP for image classification. These two solutions scored 1st and 2nd place respectively on the competition leaderboard, substantially outperforming the next best solution. Additionally, we discuss insights gained from post-competition experiments. While the performance of these two solutions have significant room for improvement due to the difficulty of the shared task and the challenging nature of medical visual question answering in general, we identify the multi-stage LLM approach and the CLIP image classification approach as promising avenues for further investigation.