Annotation of Adverse Drug Reactions in Patients’ Weblogs

Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pages 6769–6776 Marseille, 11–16 May 2020 c⃝ European Language Resources Association (ELRA), licensed under CC-BY-NC 6769 Annotation of Adverse Drug Reactions in Patients’ Weblogs Yuki Arase†, Tomoyuki Kajiwara‡, Chenhui Chu‡ †Graduate School of Information Science and Technology, Osaka University Yamada-oka 1-5, Suita, Osaka, Japan ‡Institute for Datability Science, Osaka University Yamada-oka 2-8, Suita, Osaka, Japan arase@ist.osaka-u.ac.jp, kajiwara@ids.osaka-u.ac.jp, chu@ids.osaka-u.ac.jp Abstract Adverse drug reactions are a severe problem that significantly degrade quality of life, or even threaten the life of patients. Patient- generated texts available on the web have been gaining attention as a promising source of information in this regard. While previous studies annotated such patient-generated content, they only reported on limited information, such as whether a text described an adverse drug reaction or not. Further, they only annotated short texts of a few sentences crawled from online forums and social networking services. The dataset we present in this paper is unique for the richness of annotated information, including detailed descriptions of drug reactions with full context. We crawled patient’s weblog articles shared on an online patient-networking platform and annotated the effects of drugs therein reported. We identified spans describing drug reactions and assigned labels for related drug names, standard codes for the symptoms of the reactions, and types of effects. As a first dataset, we annotated 677 drug reactions with these detailed labels based on 169 weblog articles by Japanese lung cancer patients. Our annotation dataset is made publicly available for further research on the detection of adverse drug reactions and more broadly, on patient-generated text processing. Keywords: Patient-generated text, effect of drugs, adverse drug reaction 1. Introduction Drugs are one of the primary treatment options, and can have both therapeutic and side effects. Among these side effects, those causing undesired and harmful reactions are called adverse effects. Such adverse effects are a severe problem for patients, since they significantly degrade their quality of life and make the therapeutic approach unaccept- able. They are particularly painful for patients who need long-term treatment, such as cancer patients. Therefore, in- formation on adverse drug reactions is essential for medical practitioners to prescribe drugs that maximise the therapeu- tic effects while minimising the adverse drug reactions as much as possible. Moreover, it is also crucial for pharma- ceutical science to understand the mechanisms that cause adverse drug reactions and develop new drugs. There have been two primary sources of information for adverse drug reactions: reports of clinical trials and post- marketing surveillance. Reports of clinical trials provide detailed information of adverse drug reactions observed un- der a carefully controlled setting. SIDER (Kuhn et al., 2015)1 is a database of drugs and their adverse effects, which was created by processing these reports of clinical trials. Post-marketing surveillance, on the other hand, is managed by governments to collect information of adverse drug reactions from the public to monitor for new adverse events that could not be observed during clinical trials. At- tendance to …

Content truncated to 500 words