Department of Electrical Engineering and Information Systems, Graduate School of Engineering, The University of Tokyo, Tokyo, 113-8656, Japan.
Department of Orthopaedics, Qilu Hospital of Shandong University, Jinan, 250012, People's Republic of China.
Ann Biomed Eng. 2024 Feb;52(2):125-129. doi: 10.1007/s10439-023-03288-w. Epub 2023 Jun 18.
Recently, Chatbot Generative Pre-trained Transformer (ChatGPT) is recognized as a promising clinical decision support system (CDSS) in the medical field owing to its advanced text analysis capabilities and interactive design. However, ChatGPT primarily focuses on learning text semantics rather than learning complex data structures and conducting real-time data analysis, which typically necessitate the development of intelligent CDSS employing specialized machine learning algorithms. Although ChatGPT cannot directly execute specific algorithms, it aids in algorithm design for intelligent CDSS at the textual level. In this study, besides discussing the types of CDSS and their relationship with ChatGPT, we mainly investigate the benefits and drawbacks of employing ChatGPT as an auxiliary design tool for intelligent CDSS. Our findings indicate that by collaborating with human expertise, ChatGPT has the potential to revolutionize the development of robust and effective intelligent CDSS.
最近，聊天机器人生成式预训练转换器（ChatGPT）因其先进的文本分析能力和交互设计，被认为是医学领域有前途的临床决策支持系统（CDSS）。然而，ChatGPT 主要侧重于学习文本语义，而不是学习复杂的数据结构和进行实时数据分析，这通常需要开发采用专门机器学习算法的智能 CDSS。虽然 ChatGPT 不能直接执行特定算法，但它可以在文本层面上帮助设计智能 CDSS 的算法。在这项研究中，除了讨论 CDSS 的类型及其与 ChatGPT 的关系外，我们主要研究了将 ChatGPT 用作智能 CDSS 的辅助设计工具的优缺点。我们的研究结果表明，通过与人类专业知识合作，ChatGPT 有可能彻底改变强大而有效的智能 CDSS 的开发。
