基于自然语言处理的社交媒体上药物不良事件提及评价卡塔尔世界杯8强波胆分析模型开发与分析%A Yu, dehan %A Vydiswaran,V G Vinod %+密歇根大学医学院学习健康科学系，1161F NIB, 300 N Ingalls St, Ann Arbor, MI, 48109, usa, 1734 647 1207，vgvinodv@umich.edu %K自然语言处理%K机器学习%K药物不良事件%K药物警戒%K社交媒体%K药物%K临床%K公共卫生%K健康监测%K监测%K药物效应%K药物安全%D 2022 %7 28.9.2022 %9原论文%J JMIR Med Inform %G英文%X背景:药物不良反应在临床实践和公共卫生监测中都受到广泛关注。已经采取了多种措施来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具有潜力，但尚不清楚社交媒体是否是该信息的可靠来源。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:我们提出了一个并置的长短期记忆网络模型，该模型具有细心池和由预训练模型生成的聚合上下文表示。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的内容分析，以验证社交媒体数据作为收集这些信息的手段的可靠性。 Results: The model outperformed a variant without contextual representation during both the validation and evaluation phases. 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. %M 36170004 %R 10.2196/38140 %U https://medinform.www.mybigtv.com/2022/9/e38140 %U https://doi.org/10.2196/38140 %U http://www.ncbi.nlm.nih.gov/pubmed/36170004