OpenAI's latest large vision-language model (LVLM), GPT-4V(ision), has piqued considerable interest for its potential in medical applications. Despite its promise, recent studies and internal reviews highlight its underperformance in specialized medical tasks. This paper explores the boundary of GPT-4V's capabilities in medicine, particularly in processing complex imaging data from endoscopies, CT scans, and MRIs etc. Leveraging open-source datasets, we assessed its foundational competencies, identifying substantial areas for enhancement. Our research emphasizes prompt engineering, an often-underutilized strategy for improving AI responsiveness. Through iterative testing, we refined the model's prompts, significantly improving its interpretative accuracy and relevance in medical imaging. From our comprehensive evaluations, we distilled 10 effective prompt engineering techniques, each fortifying GPT-4V's medical acumen. These methodical enhancements facilitate more reliable, precise, and clinically valuable insights from GPT-4V, advancing its operability in critical healthcare environments. Our findings are pivotal for those employing AI in medicine, providing clear, actionable guidance on harnessing GPT-4V's full diagnostic potential.

翻译：OpenAI最新的多模态大型视觉语言模型GPT-4V(ision)因其在医疗应用领域的潜力而引发了广泛关注。尽管前景可期，但近期研究与内部评估表明，该模型在专业医疗任务中表现欠佳。本文探索了GPT-4V在医学领域的性能边界，特别是处理内窥镜、CT扫描及MRI等复杂影像数据的能力。通过利用开源数据集，我们评估了其基础能力，识别出关键的提升空间。研究聚焦于提示工程这一常被忽视的AI响应优化策略。经过迭代测试，我们优化了模型的提示指令，显著提升了其在医学影像解读中的准确性与相关性。基于系统评估，我们提炼出10项有效的提示工程技术，每项技术均增强了GPT-4V的医学认知能力。这些方法论改进使GPT-4V能提供更可靠、精准且具有临床价值的洞察，推动其在关键医疗环境中的适用性。本研究为在医学领域应用人工智能的人员提供了关键发现，通过清晰可行的指导方案，助力充分发挥GPT-4V的诊断潜能。