TY - JOUR AU - Yu, Deahan AU - Vydiswaran, V G Vinod PY - 2022 DA - 2022/9/28 TI -基于自然语言处理的社交媒体药物不良事件提及评估:模型开发和分析乔-地中海JMIR通知SP - e38140六世- 10 - 9千瓦-自然语言处理KW -机器学习KW -药物不良事件KW -药物警戒KW -社会媒体KW -药物KW -临床KW -公共卫生KW -健康监测KW -监视KW -药物影响KW -药品安全AB -背景:药物不良反应吸引重要的问题在临床实践和公共卫生监测。已采取多项措施，加强对药物不良反应的上市后监测，并提高药物安全性。这些措施包括实施自发报告系统和开发基于电子健康记录和社交媒体数据的自动化自然语言处理系统，以收集可作为可能的不良反应进一步调查的药物不良事件证据。目的:虽然使用社交媒体收集药物不良事件的证据有潜力，但尚不清楚社交媒体是否是这一信息的可靠来源。我们的工作旨在(1)开发自然语言处理方法来识别社交媒体上的药物不良事件;(2)评估社交媒体数据的可靠性以识别药物不良事件。方法:我们提出了一个配置的长短期记忆网络模型，由预训练的模型生成注意池和聚合上下文表示。我们将该模型应用于大规模Twitter数据，以识别与不良药物事件相关的推文。我们对这些推文进行了定性内容分析，以验证社交媒体数据作为收集此类信息的手段的可靠性。结果:该模型在验证和评估阶段都优于没有上下文表示的变体。 Through the content analysis of adverse drug event tweets, we observed that adverse drug event–related discussions had 7 themes. Mental health–related, sleep-related, and pain-related adverse drug event discussions were most frequent. We also contrast known adverse drug reactions to those mentioned in tweets. Conclusions: We observed a distinct improvement in the model when it used contextual information. However, our results reveal weak generalizability of the current systems to unseen data. Additional research is needed to fully utilize social media data and improve the robustness and reliability of natural language processing systems. The content analysis, on the other hand, showed that Twitter covered a sufficiently wide range of adverse drug events, as well as known adverse reactions, for the drugs mentioned in tweets. Our work demonstrates that social media can be a reliable data source for collecting adverse drug event mentions. SN - 2291-9694 UR - https://medinform.www.mybigtv.com/2022/9/e38140 UR - https://doi.org/10.2196/38140 UR - http://www.ncbi.nlm.nih.gov/pubmed/36170004 DO - 10.2196/38140 ID - info:doi/10.2196/38140 ER -