Rouzrokh Pouria, Khosravi Bardia, Faghani Shahriar, Moassefi Mana, Shariatnia M Moein, Rouzrokh Parsa, Erickson Bradley
Mayo Clinic AI Laboratory, Mayo Clinic, Rochester, MN, USA.
Radiology Informatics Laboratory, Department of Radiology, Mayo Clinic, Rochester, MN, USA.
Curr Rev Musculoskelet Med. 2025 Apr 30. doi: 10.1007/s12178-025-09961-y.
This review aims to offer a foundational overview of Generative Artificial Intelligence (AI) for healthcare professionals without an engineering background. It seeks to aid their understanding of Generative AI's current capabilities, applications, and limitations within the medical field.
Generative AI models, distinct from discriminative models, are designed to create novel synthetic data. Key model families discussed include diffusion models for generating images and videos, Large Language Models (LLMs) for text, and Large Multimodal Models (LMMs) capable of processing multiple data types. Recent applications in healthcare are diverse, encompassing general uses like generating synthetic medical images, automating clinical documentation, and creating synthetic audio/video for training. More specialized applications include leveraging Generative AI models as backbones for diagnostic aids, enhancing information retrieval through Retrieval-Augmented Generation (RAG) pipelines, and coordinating multiple AI agents in complex workflows. Generative AI holds significant transformative potential in medicine, enhancing capabilities across imaging, documentation, education, and decision support. However, its integration faces substantial challenges, including models' knowledge limitations, the risk of generating incorrect or uncertain "hallucinated" outputs, inherent biases from training data, difficulty in interpreting model reasoning ("black box" nature), and navigating complex regulatory and ethical issues. This review offers a balanced perspective, acknowledging both the promise and the hurdles. While Generative AI is unlikely to fully replace physicians, understanding and leveraging these technologies will be crucial for medical professionals navigating the evolving healthcare landscape.
本综述旨在为没有工程背景的医疗保健专业人员提供生成式人工智能（AI）的基础概述。它旨在帮助他们了解生成式AI在医学领域的当前能力、应用和局限性。
生成式AI模型与判别式模型不同，旨在创建新颖的合成数据。讨论的关键模型家族包括用于生成图像和视频的扩散模型、用于文本的大语言模型（LLM）以及能够处理多种数据类型的大型多模态模型（LMM）。医疗保健领域的最新应用多种多样，包括生成合成医学图像、自动化临床文档以及创建用于训练的合成音频/视频等一般用途。更专业的应用包括将生成式AI模型用作诊断辅助工具的主干、通过检索增强生成（RAG）管道增强信息检索以及在复杂工作流程中协调多个AI智能体。生成式AI在医学领域具有重大的变革潜力，可增强成像、文档、教育和决策支持等方面的能力。然而，其整合面临重大挑战，包括模型的知识局限性、生成不正确或不确定的“幻觉”输出的风险、训练数据中的固有偏差、难以解释模型推理（“黑箱”性质）以及应对复杂的监管和伦理问题。本综述提供了一个平衡的观点，既承认其前景，也认识到障碍。虽然生成式AI不太可能完全取代医生，但对于在不断发展的医疗保健领域中前行的医疗专业人员来说，理解和利用这些技术将至关重要。
Zotero 插件