The Adverse Drug Reactions from Patient Reports in Social Media Project: Five Major Challenges to Overcome to Operationalize Analysis and Efficiently Support Pharmacovigilance Process

Cédric Bousquet (1) , Badisse Dahamna (2, 3) , Sylvie Guillemin-Lanne (4) , Stefan J. Darmoni (2, 3, 1) , Carole Faviez (5) , Charles Huot (6) , Sandrine Katsahian , Vincent Leroux , Suzanne Pereira , Christophe C. Richard , Stéphane Schuck (5) , Julien Souvignet (1) , Agnès Lillo-Le Louet (7) , Nathalie Texier (5)

1 LIMICS - Laboratoire d'Informatique Médicale et Ingénierie des Connaissances en e-Santé
2 LITIS - Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes
3 TIBS - LITIS - Equipe Traitement de l'information en Biologie Santé
4 Temis
5 Kappa
6 IBM - IBM France
7 CRPV - Centre Régional de Pharmacovigilance

Adverse drug reactions (ADRs) are an important cause of morbidity and mortality. Classical Pharmacovigilance process is limited by underreporting which justifies the current interest in new knowledge sources such as social media. The Adverse Drug Reactions from Patient Reports in Social Media (ADR-PRISM) project aims to extract ADRs reported by patients in these media. We identified 5 major challenges to overcome to operationalize the analysis of patient posts: (1) variable quality of information on social media, (2) guarantee of data privacy, (3) response to pharmacovigilance expert expectations, (4) identification of relevant information within Web pages, and (5) robust and evolutive architecture.

Mots clés: big data; medical terminology; natural language processing; pharmacovigilance; social media

Domaines: Informatique [cs]

Cédric Bousquet, Badisse Dahamna, Sylvie Guillemin-Lanne, Stefan J. Darmoni, Carole Faviez, et al.. The Adverse Drug Reactions from Patient Reports in Social Media Project: Five Major Challenges to Overcome to Operationalize Analysis and Efficiently Support Pharmacovigilance Process. JMIR Research Protocols, 2017, 6 (9), pp.e179. ⟨10.2196/resprot.6463⟩. ⟨hal-02109409⟩