Using natural language processing to characterize and predict homeopathic product-associated adverse events in consumer reviews: comparison to reports to FDA Adverse Event Reporting System (FAERS).

OBJECTIVE: 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). MATERIALS AND METHODS: 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. RESULTS: 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). DISCUSSION: 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. CONCLUSION: 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.

Serious Skin Injuries Following Exposure to Unapproved Mole and Skin Tag Removers.

Objective: We sought to describe skin injuries associated with unapproved topical mole and skin tag removers containing concentrated salicylic acid, Sanguinaria canadensis, or other caustic agents. Methods: We identified skin injuries associated with unapproved non-device topical mole and skin tag removers reported to the US Food and Drug Administration (FDA) through October 30, 2021 or described in Amazon consumer product reviews between 2019 and 2021. Results: We identified 38 cases, including 30 from Amazon consumer product reviews and eight reported to the FDA. Twenty-eight were from 2021. The most common reason for use was for mole and/or skin tag removal. Listed ingredients included salicylic acid, Sanguinaria canadensis, botanicals (includes homeopathic products), and calcium oxide. Seven cases involved products without ingredients listed. Adverse events included burns, pain, and ulceration, some resulting in permanent scarring and disfigurement. There were 14 facial injuries, including four adjacent to the eye. Reported treatments included antibiotics, hospital care, wound care, and dermatology advice to have a skin graft. Limitations: Limitations include underreporting of adverse events to the FDA, limited clinical details and potential bias in consumer reviews, and poor replicability of review searches due to the dynamic nature of the Amazon website. Conclusion: Unapproved, non-device topical mole and skin tag removers are associated with serious skin injuries. We found Amazon consumer reviews to be a novel and useful data source for safety surveillance of these types of skin products. When dermatologists are consulted about skin injuries, exposure to these products should be considered in the differential diagnosis.