Department of Physical Medicine and Rehabilitation, Etlik City Hospital, Ankara, Turkey.
Int J Rheum Dis. 2023 Jul;26(7):1343-1349. doi: 10.1111/1756-185X.14749. Epub 2023 May 23.
It is inevitable that artificial intelligence applications will be used as a source of information in the field of health in the near future. For this reason, we aimed to evaluate whether ChatGPT, a new Large Language Model, can be used to obtain information about common rheumatic diseases.
Common rheumatic diseases were identified using the American College of Rheumatology and European League against Rheumatism guidelines. Osteoarthritis (OA), rheumatoid arthritis, ankylosing spondylitis (AS), systemic lupus erythematosus, psoriatic arthritis, fibromyalgia syndrome, and gout were identified by using Google trends for the four most frequently searched keywords on Google. The responses were evaluated with seven-point Likert-type reliability and usefulness scales developed by us.
The highest score in terms of reliability was OA (mean ± standard deviation 5.62 ± 1.17), whereas the highest score in terms of usefulness was AS (mean 5.87 ± 0.17). There was no significant difference in the reliability and usefulness of the answers given by the ChatGPT (p = .423 and p = .387, respectively). All scores ranged between 4 and 7.
Although ChatGPT is reliable and useful for patients to obtain information about rheumatic diseases, it should be kept in mind that it may give false and misleading answers.
人工智能应用在不久的将来必将被用作健康领域的信息源。基于此，我们旨在评估新的大型语言模型 ChatGPT 是否可用于获取常见风湿病的信息。
使用美国风湿病学会和欧洲抗风湿病联盟的指南确定常见风湿病。通过 Google 趋势确定骨关节炎（OA）、类风湿关节炎、强直性脊柱炎（AS）、系统性红斑狼疮、银屑病关节炎、纤维肌痛综合征和痛风这四种在 Google 上搜索最多的关键词。我们通过七点李克特量表对回答进行了评估，制定了可靠性和有用性量表。
在可靠性方面，OA 的得分最高（均值±标准差为 5.62±1.17），而在有用性方面，AS 的得分最高（均值为 5.87±0.17）。ChatGPT 给出的答案在可靠性和有用性方面没有显著差异（p=0.423 和 p=0.387）。所有评分均在 4 到 7 之间。
虽然 ChatGPT 对患者获取有关风湿病的信息是可靠且有用的，但应记住它可能会给出错误和误导性的答案。
