Mining Adverse Drug Reactions in Social Media with Named Entity Recognition and Semantic Methods

摘要：

　　Suspected adverse drug reactions (ADR) reported by patients through social media can be a complementary source to current pharmacovigilance systems. However, the performance of text mining tools applied to social media text data to discover ADRs needs to be evaluated. In this paper, we introduce the approach developed to mine ADR from French social media. A protocol of evaluation is highlighted, which includes a detailed sample size determination and evaluation corpus constitution. Our text mining approach provided very encouraging preliminary results with F-measures of 0.94 and 0.81 for recognition of drugs and symptoms respectively, and with F-measure of 0.70 for ADR detection. Therefore, this approach is promising for downstream pharmacovigilance analysis.

关键词： Social Media Pharmacovigilance Data Mining

作者: Xiaoyi Chen Myrtille Deldossi Rim Aboukhamis Carole Faviez Badisse Dahamna Pierre Karapetiantz Armelle Guenegou-Arnoux Yannick Girardeau Sylvie Guillemin-Lanne Agnès Lillo-Le-Lou(e)t Nathalie Texier Anita Burgun Sandrine Katsahian

作者单位: INSERM,UMRS1138,équipe 22,Centre de Recherche des Cordeliers,Paris,France Expert System,75012 Paris,France Centre Régional de Pharmacovigilance,H(o)pital Européen Georges-Pompidou,AP-HP,Paris,France Kappa Santé,75002 Paris,France Service dInformatique Biomédicale,CHU de Rouen,France;LITIS-TIBS EA 4108,76031 Rouen Cedex,France;I Université Paris Descartes,Sorbonne Paris Cité,UMRS1138,Centre de Recherche de Cordeliers,Paris,Fran INSERM,UMRS1138,équipe 22,Centre de Recherche des Cordeliers,Paris,France;Université Paris Descartes

会议类型: 国际会议

会议名称: 第十六届世界医药健康信息学大会((MEDINFO2017)、第二届世界医药健康信息学华语论坛(WCHIS 2017)、第15届全国医药信息学大会(CMIA 2017)

会议地点: 苏州

会议语种:英文

页码: 322-326

在线出版日期: 2017-08-21（万方平台首次上网日期，不代表论文的发表时间）