| Popis: |
BACKGROUND With a strong ability in performing natural tasks and an easy-to-use interface, ChatGPT received a lot of attention since OpenAI released it to the public. OBJECTIVE A prospective analysis is needed to examine the accuracy and appropriateness of the 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 dataset included the retrospective collection of medication consultation questions from February 1, 2023, to February 28, 2023, as well as common questions regarding drug-herb interactions. Two different sets of questions were tested: real-world medication consultation questions and common questions about interactions between traditional Chinese and Western medicines. For each ChatGPT response, the appropriateness was evaluated by two experienced pharmacists. In cases where the opinions of the two pharmacists were inconsistent, a third pharmacist would make the final determination. RESULTS From 293 real-world medication consultation questions, a random selection of 80 was used to compare ChatGPT's performance. ChatGPT demonstrated a higher appropriateness rate for answering public medication consultation questions compared to questions presented to healthcare providers in a hospital setting (61% vs 39%, p=.011). CONCLUSIONS The results of this study suggest that ChatGPT may be used to answer basic medication consultation questions. We analyzed the erroneous information and identified potential medical harms associated with certain questions, which is worthy of our attention. |
