摘要
由一名新闻记者-机器人与机器学习的工作人员新闻编辑每日新闻-人工智能的新数据在一份新的报告中呈现。根据NewsRx记者在华盛顿西雅图的新闻报道，研究表明：“人工智能(AI)的进步导致了大型语言模型(LLMs)的产生，比如聊天生成预训练变形器(ChatGPT)和巴德，它们分析在线资源，综合对用户查询的回答。尽管它们很受欢迎，但LLM对医疗问题的回答的准确性仍然未知。”新闻记者从瓦辛顿大学的研究中获得了一句话，本研究旨在将ChatGPT和Bard在髋关节和膝关节骨性关节炎治疗方面的反应与美国矫形外科医师学会(AAOS)循证临床实践指南(CPGs)建议进行比较。ChatGPT(Open AI)和Bard(Google)都被问及AOS CPGs的20个TRE(髋关节10个，膝关节骨性关节炎10个)。2名评审员将反应归类为与AAOS CPG的“一致性”、“不一致性”或“不一致性”。Cohen’s Kappa系数被用于评估者之间的可靠性，Chi-squared分析被用于比较LLM之间的响应。总的来说，ChatGPT和Bard分别提供了16（80%）和12（60%）项与AOS CPG一致的响应。值得注意ChatGPT和Bard分别在30%和60%的询问中鼓励使用不推荐的治疗。在联合或推荐治疗与非推荐治疗的评估中，性能没有差异。在6个Bard回答中，有6个（30%）的研究被引用，没有（0%）的ChatGPT回答被引用。在6个Bard回答中，只有1个（16.7%）的研究被识别。2个（33.3%）回复引用了不存在的期刊上的研究，2个（33.3%）引用了与所提供的信息无法找到的研究，1个（16.7%）提供了与未相关研究的链接。ChatGPT和Bard都没有一致地提供与AAOS CPG相同的回复。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Fresh data on Artificial Intelligence are presented in a new report. According to news reporting originating in Seattl e, Washington, by NewsRx journalists, research stated, "Advancements in artifici al intelligence (AI) have led to the creation of large language models (LLMs), s uch as Chat Generative Pretrained Transformer (ChatGPT) and Bard, that analyze o nline resources to synthesize responses to user queries. Despite their popularit y, the accuracy of LLM responses to medical questions remains unknown." The news reporters obtained a quote from the research from the University of Was hington, "This study aimed to compare the responses of ChatGPT and Bard regardin g treatments for hip and knee osteoarthritis with the American Academy of Orthop aedic Surgeons (AAOS) Evidence-Based Clinical Practice Guidelines (CPGs) recomme ndations. Both ChatGPT (Open AI) and Bard (Google) were queried regarding 20 tre atments (10 for hip and 10 for knee osteoarthritis) from the AAOS CPGs. Response s were classified by 2 reviewers as being in ‘Concordance, ‘ ‘Discordance, ‘ or ‘No Concordance ‘ with AAOS CPGs. A Cohen ‘s Kappa coefficient was used to asses s inter -rater reliability, and Chi -squared analyses were used to compare respo nses between LLMs. Overall, ChatGPT and Bard provided responses that were concor dant with the AAOS CPGs for 16 (80%) and 12 (60%) trea tments, respectively. Notably, ChatGPT and Bard encouraged the use of nonrecomme nded treatments in 30% and 60% of queries, respectiv ely. There were no differences in performance when evaluating by joint or by rec ommended versus non-recommended treatments. Studies were referenced in 6 (30% ) of the Bard responses and none (0%) of the ChatGPT responses. Of the 6 Bard responses, studies could only be identified for 1 (16.7% ). Of the remaining, 2 (33.3%) responses cited studies in journals that did not exist, 2 (33.3%) cited studies that could not be found with the information given, and 1 (16.7%) provided links to unrela ted studies. Both ChatGPT and Bard do not consistently provide responses that al ign with the AAOS CPGs."
NETL
NSTL