Large language models (LLMs), such as ChatGPT, have received substantial attention due to their impressive human language understanding and generation capabilities. Therefore, the application of LLMs in medicine to assist physicians and patient care emerges as a promising research direction in both artificial intelligence and clinical medicine. To reflect this trend, this survey provides a comprehensive overview of the principles, applications, and challenges faced by LLMs in medicine. Specifically, we aim to address the following questions: 1) How can medical LLMs be built? 2) What are the downstream performances of medical LLMs? 3) How can medical LLMs be utilized in real-world clinical practice? 4) What challenges arise from the use of medical LLMs? and 5) How can we better construct and utilize medical LLMs? As a result, this survey aims to provide insights into the opportunities and challenges of LLMs in medicine and serve as a valuable resource for constructing practical and effective medical LLMs. A regularly updated list of practical guides on medical LLMs can be found at https://github.com/AI-in-Health/MedLLMsPracticalGuide.

翻译：大型语言模型（LLMs），如ChatGPT，因其出色的人类语言理解与生成能力而受到广泛关注。因此，将LLMs应用于医学领域以辅助医生及患者护理，成为人工智能与临床医学中的一个极具前景的研究方向。为反映这一趋势，本综述全面概述了LLMs在医学领域中的原理、应用及面临的挑战。具体而言，我们旨在解答以下问题：1）如何构建医学LLMs？2）医学LLMs的下游性能如何？3）如何在真实临床实践中应用医学LLMs？4）使用医学LLMs会引发哪些挑战？5）如何更优地构建与利用医学LLMs？由此，本综述旨在揭示LLMs在医学中的机遇与挑战，并为构建实用且高效的医学LLMs提供宝贵资源。关于医学LLMs实践指南的定期更新列表可查阅https://github.com/AI-in-Health/MedLLMsPracticalGuide。