Nguyen Y, Costedoat-Chalumeau N
Service de médecine interne, hôpital Cochin, AP-HP centre, Université Paris cité, 75014 Paris, France; Centre de recherche en épidémiologie et statistiques (CRESS), unité Inserm 1153, Université de Paris cité, Paris, France.
Service de médecine interne, hôpital Cochin, AP-HP centre, Université Paris cité, 75014 Paris, France; Centre de recherche en épidémiologie et statistiques (CRESS), unité Inserm 1153, Université de Paris cité, Paris, France.
Rev Med Interne. 2023 May;44(5):218-226. doi: 10.1016/j.revmed.2023.03.017. Epub 2023 Apr 14.
Artificial intelligence (AI) using deep learning is revolutionizing several fields, including medicine, with a wide range of applications. Available since the end of 2022, ChatGPT is a conversational AI or "chatbot", using artificial intelligence to dialogue with its users in all fields. Through the example of hydroxychloroquine (HCQ), we discuss its use for patients, clinicians, or researchers, and discuss its performance and limitations, particularly in relation to algorithmic bias. If AI tools using deep learning do not dispense with the expertise and experience of a clinician (at least, for the moment), they have a potential to improve or simplify our daily practice.
使用深度学习的人工智能(AI)正在彻底改变包括医学在内的多个领域,有着广泛的应用。ChatGPT自2022年底推出以来,是一种对话式AI或“聊天机器人”,利用人工智能在各个领域与用户进行对话。通过羟氯喹(HCQ)的例子,我们讨论了它在患者、临床医生或研究人员中的应用,并讨论了其性能和局限性,特别是与算法偏差相关的方面。如果使用深度学习的AI工具不能取代临床医生的专业知识和经验(至少目前如此),那么它们有潜力改善或简化我们的日常实践。