Background: Since OpenAI released ChatGPT, with its strong capability in handling natural tasks and its user-friendly interface, it has garnered significant attention. Objective: A prospective analysis is required to evaluate the accuracy and appropriateness of medication consultation responses generated by ChatGPT. Methods: A prospective cross-sectional study was conducted by the pharmacy department of a medical center in Taiwan. The test data set comprised retrospective medication consultation questions collected from February 1, 2023, to February 28, 2023, along with common questions about drug-herb interactions. Two distinct sets of questions were tested: real-world medication consultation questions and common questions about interactions between traditional Chinese and Western medicines. We used the conventional double-review mechanism. The appropriateness of each response from ChatGPT was assessed by 2 experienced pharmacists. In the event of a discrepancy between the assessments, a third pharmacist stepped in to make the final decision. Results: Of 293 real-world medication consultation questions, a random selection of 80 was used to evaluate ChatGPT’s performance. ChatGPT exhibited a higher appropriateness rate in responding to public medication consultation questions compared to those asked by health care providers in a hospital setting (31/51, 61% vs 20/51, 39%; P=.01). Conclusions: The findings from this study suggest that ChatGPT could potentially be used for answering basic medication consultation questions. Our analysis of the erroneous information allowed us to identify potential medical risks associated with certain questions; this problem deserves our close attention.
The seeds of Cuscuta chinensis Lam. and C. campestris Yuncker have been commonly used as Chinese medical material for preventing aging. Our previous studies have found that C. chinensis and C. campestris possess anti-inflammatory activities in rodents. However, their other biological activities, such as memory-improving properties, have not yet been explored. In the present study, we examined the memory-improving effects of the extracts of C. chinensis and C. campestris on scopolamine (SCOP)-induced memory deficit and explored their underlying mechanism in mice. Both Cuscuta species improved SCOP-induced memory deficits in the passive avoidance test, elevated plus-maze, and spatial performance test of the Morris water maze in mice. In addition, compared with mice injected with SCOP, mice pretreated with both Cuscuta species stayed for a longer time on the platform for the probe test of the Morris water maze. Moreover, both Cuscuta species reduced brain acetylcholinesterase activity and malondialdehyde levels that were increased by SCOP, and the species restored the activities of antioxidant enzymes (superoxide dismutase and catalase) and the levels of glutathione that were decreased by SCOP in the brains of mice. Both Cuscuta species further decreased brain interleukin-1β and tumor necrosis factor-α levels that were elevated by SCOP. We demonstrated that both Cuscuta species exhibited a protective activity against SCOP-induced memory deficit, cholinergic dysfunction, oxidative damage, and neuroinflammation in mice, and C. campestris has better potential than C. chinensis. In addition, we provided evidence that the seeds of C. campestris can be used as Cuscutae Semen in Traditional Chinese Medicine.
1 January 1994 in Chemical and Pharmaceutical Bulletin