PDF(Pubmed)
Abstract：
UNASSIGNED: Patients access relevant information concerning their orthopaedic surgery resources through multiple information channels before presenting for clinical treatment. Recently, artificial intelligence (AI)-powered chatbots have become another source of information for patients. The currently developed AI chat technology ChatGPT (OpenAI LP) is an application for such purposes and it has been rapidly gaining popularity, including for patient education. This study sought to evaluate whether ChatGPT can correctly answer frequently asked questions (FAQ) regarding periprosthetic joint infection (PJI).
UNASSIGNED: Twelve FAQs about PJI after hip and knee arthroplasty were identified from the websites of fifteen international clinical expert centres. ChatGPT was confronted with these questions and its responses were analysed for their accuracy using an evidence-based approach by a multidisciplinary team. Responses were categorised in four groups: (1) Excellent response that did not require additional improvement; (2) Satisfactory responses that required a small amount of improvement; (3) Satisfactory responses that required moderate improvement; and (4) Unsatisfactory responses that required a large amount of improvement.
UNASSIGNED: From the analysis of the responses given by the chatbot, no reply received an \'unsatisfactory\' rating; one did not require any correction; and the majority of the responses required low (7 out of 12) or moderate (4 out of 12) clarification. Although a few responses required minimal clarification, the chatbot responses were generally unbiased and evidence-based, even when asked controversial questions.
UNASSIGNED: The AI-chatbot ChatGPT was able to effectively answer the FAQs of patients seeking information around PJI diagnosis and treatment. The given information was also written in a manner that can be assumed to be understandable by patients. The chatbot could be a valuable clinical tool for patient education and understanding around PJI treatment in the future. Further studies should evaluate its use and acceptance by patients with PJI.
UNASSIGNED: Twelve FAQs about PJI after hip and knee arthroplasty were identified from the websites of fifteen international clinical expert centres. ChatGPT was confronted with these questions and its responses were analysed for their accuracy using an evidence-based approach by a multidisciplinary team. Responses were categorised in four groups: (1) Excellent response that did not require additional improvement; (2) Satisfactory responses that required a small amount of improvement; (3) Satisfactory responses that required moderate improvement; and (4) Unsatisfactory responses that required a large amount of improvement.
UNASSIGNED: From the analysis of the responses given by the chatbot, no reply received an \'unsatisfactory\' rating; one did not require any correction; and the majority of the responses required low (7 out of 12) or moderate (4 out of 12) clarification. Although a few responses required minimal clarification, the chatbot responses were generally unbiased and evidence-based, even when asked controversial questions.
UNASSIGNED: The AI-chatbot ChatGPT was able to effectively answer the FAQs of patients seeking information around PJI diagnosis and treatment. The given information was also written in a manner that can be assumed to be understandable by patients. The chatbot could be a valuable clinical tool for patient education and understanding around PJI treatment in the future. Further studies should evaluate its use and acceptance by patients with PJI.
摘要：
■患者在临床治疗前通过多种信息渠道获取有关其骨科手术资源的相关信息。最近,人工智能（AI）驱动的聊天机器人已经成为患者的另一个信息来源。当前开发的AI聊天技术ChatGPT（OpenAILP）是用于此类目的的应用程序，并且已迅速普及，包括患者教育。这项研究旨在评估ChatGPT是否可以正确回答有关假体周围感染（PJI）的常见问题（FAQ）。
■在15个国际临床专家中心的网站上发现了12个关于髋关节和膝关节置换术后PJI的常见问题。ChatGPT面临这些问题，一个多学科团队使用基于证据的方法分析了其回答的准确性。反应分为四组：（1）不需要额外改善的出色反应；（2）需要少量改善的满意反应；（3）需要适度改善的满意反应；（4）需要大量改善的不满意反应。
■通过对聊天机器人给出的响应的分析，没有答复收到“不满意”评级；一个不需要任何更正；大多数答复要求低（12个中的7个）或中等（12个中的4个）澄清。尽管一些答复需要最少的澄清，聊天机器人的反应通常是公正的，以证据为基础的，即使被问到有争议的问题。
■AI聊天机器人ChatGPT能够有效地回答寻求PJI诊断和治疗信息的患者的常见问题。给定的信息也以可以被认为是患者可理解的方式编写。聊天机器人可能是未来患者教育和理解PJI治疗的宝贵临床工具。进一步的研究应评估其使用和接受PJI患者。
■在15个国际临床专家中心的网站上发现了12个关于髋关节和膝关节置换术后PJI的常见问题。ChatGPT面临这些问题，一个多学科团队使用基于证据的方法分析了其回答的准确性。反应分为四组：（1）不需要额外改善的出色反应；（2）需要少量改善的满意反应；（3）需要适度改善的满意反应；（4）需要大量改善的不满意反应。
■通过对聊天机器人给出的响应的分析，没有答复收到“不满意”评级；一个不需要任何更正；大多数答复要求低（12个中的7个）或中等（12个中的4个）澄清。尽管一些答复需要最少的澄清，聊天机器人的反应通常是公正的，以证据为基础的，即使被问到有争议的问题。
■AI聊天机器人ChatGPT能够有效地回答寻求PJI诊断和治疗信息的患者的常见问题。给定的信息也以可以被认为是患者可理解的方式编写。聊天机器人可能是未来患者教育和理解PJI治疗的宝贵临床工具。进一步的研究应评估其使用和接受PJI患者。
