Division of Pharmacovigilance, Office of Surveillance and Epidemiology, Center for Drug Evaluation and Research, US Food and Drug Administration, Silver Spring, MD 20993, United States.
Department of Health Services Administration, School of Health Professions, The University of Alabama at Birmingham, Birmingham, AL 35233, United States.
J Am Med Inform Assoc. 2023 Dec 22;31(1):70-78. doi: 10.1093/jamia/ocad197.
Apply natural language processing (NLP) to Amazon consumer reviews to identify adverse events (AEs) associated with unapproved over the counter (OTC) homeopathic drugs and compare findings with reports to the US Food and Drug Administration Adverse Event Reporting System (FAERS).
Data were extracted from publicly available Amazon reviews and analyzed using JMP 16 Pro Text Explorer. Topic modeling identified themes. Sentiment analysis (SA) explored consumer perceptions. A machine learning model optimized prediction of AEs in reviews. Reports for the same time interval and product class were obtained from the FAERS public dashboard and analyzed.
Homeopathic cough/cold products were the largest category common to both data sources (Amazon = 616, FAERS = 445) and were analyzed further. Oral symptoms and unpleasant taste were described in both datasets. Amazon reviews describing an AE had lower Amazon ratings (X2 = 224.28, P < .0001). The optimal model for predicting AEs was Neural Boosted 5-fold combining topic modeling and Amazon ratings as predictors (mean AUC = 0.927).
Topic modeling and SA of Amazon reviews provided information about consumers' perceptions and opinions of homeopathic OTC cough and cold products. Amazon ratings appear to be a good indicator of the presence or absence of AEs, and identified events were similar to FAERS.
Amazon reviews may complement traditional data sources to identify AEs associated with unapproved OTC homeopathic products. This study is the first to use NLP in this context and lays the groundwork for future larger scale efforts.
应用自然语言处理（NLP）技术分析亚马逊消费者评论，以识别与未经批准的非处方（OTC）顺势疗法药物相关的不良事件（AE），并将结果与美国食品和药物管理局不良事件报告系统（FAERS）的报告进行比较。
从公开的亚马逊评论中提取数据，并使用 JMP 16 Pro Text Explorer 进行分析。主题建模确定主题。情感分析（SA）探索消费者的看法。机器学习模型优化了评论中 AE 的预测。从 FAERS 公共仪表板获取同一时间区间和产品类别报告，并进行分析。
顺势疗法咳嗽/感冒产品是两个数据源（亚马逊=616，FAERS=445）中最常见的类别，并进一步进行了分析。两个数据集均描述了口腔症状和不愉快的味道。描述 AE 的亚马逊评论的亚马逊评分较低（X2=224.28，P<0.0001）。预测 AE 的最佳模型是结合主题建模和亚马逊评分作为预测因子的神经增强 5 倍（平均 AUC=0.927）。
亚马逊评论的主题建模和 SA 提供了有关消费者对顺势疗法 OTC 咳嗽和感冒产品的看法和意见的信息。亚马逊评分似乎是 AE 存在与否的良好指标，并且识别出的事件与 FAERS 相似。
亚马逊评论可能补充传统数据源，以识别与未经批准的 OTC 顺势疗法产品相关的 AE。本研究首次在这种情况下使用 NLP，并为未来更大规模的努力奠定了基础。
