ABSTRACT
BACKGROUND: Advancements in artificial intelligence (AI) have led to the creation of large language models (LLMs), such as Chat Generative Pretrained Transformer (ChatGPT) and Bard, that analyze online resources to synthesize responses to user queries. Despite their popularity, the accuracy of LLM responses to medical questions remains unknown. This study aimed to compare the responses of ChatGPT and Bard regarding treatments for hip and knee osteoarthritis with the American Academy of Orthopaedic Surgeons (AAOS) Evidence-Based Clinical Practice Guidelines (CPGs) recommendations. METHODS: Both ChatGPT (Open AI) and Bard (Google) were queried regarding 20 treatments (10 for hip and 10 for knee osteoarthritis) from the AAOS CPGs. Responses were classified by 2 reviewers as being in "Concordance," "Discordance," or "No Concordance" with AAOS CPGs. A Cohen's Kappa coefficient was used to assess inter-rater reliability, and Chi-squared analyses were used to compare responses between LLMs. RESULTS: Overall, ChatGPT and Bard provided responses that were concordant with the AAOS CPGs for 16 (80%) and 12 (60%) treatments, respectively. Notably, ChatGPT and Bard encouraged the use of non-recommended treatments in 30% and 60% of queries, respectively. There were no differences in performance when evaluating by joint or by recommended 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 unrelated studies. CONCLUSIONS: Both ChatGPT and Bard do not consistently provide responses that align with the AAOS CPGs. Consequently, physicians and patients should temper expectations on the guidance AI platforms can currently provide.
Subject(s)
Osteoarthritis, Hip , Osteoarthritis, Knee , Humans , Osteoarthritis, Knee/therapy , Artificial Intelligence , Osteoarthritis, Hip/therapy , Reproducibility of Results , LanguageABSTRACT
ABSTRACT: Data are equivocal on the consequences of COVID-19 pandemic on pain and well-being for individuals with chronic pain. Furthermore, little is known regarding its impact on the health of young adults with chronic pain. We conducted a longitudinal study to compare pain, psychological functioning, and substance use before and during the pandemic of 196 young adults with chronic pain. Participants aged 18 to 24 years (M = 21.1 years; 79.6% females) reported on pain, anxiety, depression, and substance use before (October 2018-August 2019) and during the pandemic (October 2020-November 2020), in addition to the assessment of COVID-19 exposure and its impact. Before the pandemic, young adults experienced mild-to-moderate pain intensity (M = 3.75, SD = 2.33) and pain interference (M = 3.44, SD = 2.69). Findings were that pain intensity, pain interference, and depression symptoms remained stable during the pandemic. In contrast, anxiety symptoms increased significantly (M = 8.21, SD = 5.84 vs M = 8.89, SD = 5.95, P = 0.04). Tobacco, alcohol, and cannabis use were unchanged. Mixed linear models revealed that COVID-19 exposure and impact were not associated with changes in pain intensity or interference, with female sex associated with increased pain intensity (ß = 0.86, P = 0.02) and pain interference (ß = 0.87, P = 0.02). Our findings indicated relative stability of pain symptoms experienced by young adults with chronic pain. However, the increases in anxiety highlight the need to facilitate treatment access for mental health services to mitigate downstream impact.