Format

Send to

Choose Destination
Stud Health Technol Inform. 2019 Aug 21;264:60-64. doi: 10.3233/SHTI190183.

Initial Experiments for Pharmacovigilance Analysis in Social Media Using Summaries of Product Characteristics.

Author information

1
LIMSI, CNRS, Université Paris-Saclay, F-91405 Orsay, France.
2
CRPV Paris-HEGP, Hôpital Européen George Pompidou, 20 rue Leblanc, 75015 Paris, France.

Abstract

We report initial experiments for analyzing social media through an NLP annotation tool on web posts about medications of current interests (baclofen, levothyroxine and vaccines) and summaries of product characteristics (SPCs). We conducted supervised experiments on a subset of messages annotated by experts according to positive or negative misuse; results ranged from 0.62 to 0.91 of F-score. We also annotated both SPCs and another set of posts to compare MedDRA annotations in each source. A pharmacovigilance expert checked the output and confirmed that entities not found in SCPs might express drug misuse or unknown ADRs.

KEYWORDS:

Natural Language Processing; Pharmacovigilance; Social media

PMID:
31437885
DOI:
10.3233/SHTI190183
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for IOS Press
Loading ...
Support Center