Assessing the performance of zero-shot visual question answering in multimodal large language models for 12-lead ECG image interpretation

Large Language Models (LLM) are increasingly multimodal, and Zero-Shot Visual Question Answering (VQA) shows promise for image interpretation. If zero-shot VQA can be applied to a 12-lead electrocardiogram (ECG), a prevalent diagnostic tool in the medical field, the potential benefits to the field would be substantial. This study evaluated the diagnostic performance of zero-shot VQA with multimodal LLMs on 12-lead ECG images. The results revealed that multimodal LLM tended to make more errors in extracting and verbalizing image features than in describing preconditions and making logical inferences. Even when the answers were correct, erroneous descriptions of image features were common. These findings suggest a need for improved control over image hallucination and indicate that performance evaluation using the percentage of correct answers to multiple-choice questions may not be sufficient for performance assessment in VQA tasks.