Chen Xiaoyi, Deldossi Myrtille, Aboukhamis Rim, Faviez Carole, Dahamna Badisse, Karapetiantz Pierre, Guenegou-Arnoux Armelle, Girardeau Yannick, Guillemin-Lanne Sylvie, Lillo-Le-Louët Agnès, Texier Nathalie, Burgun Anita, Katsahian Sandrine
INSERM, UMRS1138, équipe 22, Centre de Recherche des Cordeliers, Paris, France.
Expert System, 75012 Paris, France.
Stud Health Technol Inform. 2017;245:322-326.
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.
患者通过社交媒体报告的疑似药物不良反应（ADR）可以成为当前药物警戒系统的补充来源。然而，应用于社交媒体文本数据以发现ADR的文本挖掘工具的性能需要评估。在本文中，我们介绍了从法国社交媒体挖掘ADR所开发的方法。突出了一个评估方案，其中包括详细的样本量确定和评估语料库构建。我们的文本挖掘方法提供了非常令人鼓舞的初步结果，识别药物和症状的F值分别为0.94和0.81，ADR检测的F值为0.70。因此，这种方法对下游药物警戒分析很有前景。
