LiSA: an assisted literature search pipeline for detecting serious adverse drug events with deep learning.

Journal: BMC medical informatics and decision making
Published Date:

Abstract

INTRODUCTION: Detecting safety signals attributed to a drug in scientific literature is a fundamental issue in pharmacovigilance. The constant increase in the volume of publications requires the automation of this tedious task, in order to find and extract relevant articles from the pack. This task is critical, as serious Adverse Drug Reactions (ADRs) still account for a large number of hospital admissions each year.

Authors

  • Vincent Martenot
    Quinten, 8 rue Vernier, 75017, Paris, France. v.martenot@quinten-france.com.
  • Valentin Masdeu
    Quinten, 8 rue Vernier, 75017, Paris, France.
  • Jean Cupe
    Quinten, 8 rue Vernier, 75017, Paris, France.
  • Faustine Gehin
    Quinten, 8 rue Vernier, 75017, Paris, France.
  • Margot Blanchon
    Quinten, 8 rue Vernier, 75017, Paris, France.
  • Julien Dauriat
    Quinten, 8 rue Vernier, 75017, Paris, France.
  • Alexander Horst
    Swiss Agency for Therapeutic Products, Swissmedic, Hallerstrasse 7, 3012, Bern, Switzerland.
  • Michael Renaudin
    Swiss Agency for Therapeutic Products, Swissmedic, Hallerstrasse 7, 3012, Bern, Switzerland.
  • Philippe Girard
    Swiss Agency for Therapeutic Products, Swissmedic, Hallerstrasse 7, 3012, Bern, Switzerland.
  • Jean-Daniel Zucker
    Integromics, Institute of Cardiometabolism and Nutrition, ICAN, Assistance Publique Hôpitaux de Paris, Pitié-Salpêtrière Hospital, Paris, 75013, France. jean-daniel.zucker@ird.fr.