JMIR Publications

ABSTRACT

Background:

Spontaneous Pharmacovigilance (PV) reporting systems are the main data source for signal detection for vaccines. However, there is a large time-lag between the occurrence of an adverse event (AE) and availability for analysis. With global mass COVID-19 vaccination campaigns, social media and web content, there is an opportunity for real-time, faster monitoring of AEs potentially related to COVID-19 vaccine use.

Objective:

To monitor AEs shared in social media and online using medical context aware Natural Language Processing (NLP) Large Language Models (LLM).

Methods:

We developed an LLM-based web-app to analyze social media, patient blogs and forums (from 190 countries in 61 languages) around COVID-19 vaccine related keywords. Following machine translation to English, lay language safety terms (i.e. AEs) were observed using PubmedBERT based named-entity recognition model (precision = .76, recall = .82) and mapped to the Medical Dictionary for Regulatory Activities (MedDRA) terms using knowledge graphs (MedDRA® terminology is developed and registered under the auspices of the International Council for Harmonization of Technical Requirements for Pharmaceuticals for Human Use). Weekly and cumulative aggregated AE counts, proportions and ratios were displayed via visual analytics such as word clouds.

Results:

Most AEs were identified in 2021, with fewer in 2022. AEs observed using the web-app were consistent with AEs communicated by Health Authorities shortly before or within the same period.

Conclusions:

Monitoring web and social media provides opportunities to observe AEs that may be related to the use of COVID-19 vaccines. The presented analysis demonstrates the ability to use web content and social media as a data source which could contribute to the early observation of AEs. It could help to adjust signal detection strategies and communication with external stakeholders, contributing to increased confidence in vaccine safety monitoring.