| Autor: |
Karapetiantz P; Sorbonne Université, Inserm, université Paris 13, Laboratoire d'informatique médicale et d'ingénierie des connaissances en e-santé, LIMICS, F-75006 Paris, France., Audeh B; Sorbonne Université, Inserm, université Paris 13, Laboratoire d'informatique médicale et d'ingénierie des connaissances en e-santé, LIMICS, F-75006 Paris, France., Faille J; Sorbonne Université, Inserm, université Paris 13, Laboratoire d'informatique médicale et d'ingénierie des connaissances en e-santé, LIMICS, F-75006 Paris, France., Lillo-Le Louët A; Centre régional de pharmacovigilance HEGP, AP-HP Paris, France., Bousquet C; Sorbonne Université, Inserm, université Paris 13, Laboratoire d'informatique médicale et d'ingénierie des connaissances en e-santé, LIMICS, F-75006 Paris, France. |
| Abstrakt: |
Social media are proposed as a complementary data source for detection and characterisation of adverse drug reactions. While signal detection algorithms were implemented for generating signals in pharmacovigilance databases, the implementation of a graphical user interface supporting the selection and display of algorithms' results is not documented in the medical literature. Although collecting information on the chronology and the impact of adverse drug reactions is desirable to enable causality and quality assessment of potential signals detected in patients' posts, no tool has been proposed yet to consider such data. We describe here two approaches, and the corresponding tools we implemented for: (1) quantitative approach based on signal detection algorithms, and (2) qualitative approach based on expert review of patient's posts. Future work will focus on implementing other statistical methods, exploring the complementarity of both approaches on a larger scale, and prioritizing the posts to manually evaluate after applying appropriate signal detection methods. |
