COVID-19 vaccine evidence monitoring assisted by artificial Intelligence: An emergency system implemented by the Public Health Agency of Canada to capture and describe the trajectory of evolving pandemic vaccine literature

Abstract

Background

The COVID-19 pandemic resulted in a rapid accumulation of novel vaccine research evidence. As a means to monitor this evidence, the Public Health Agency of Canada (PHAC) created the Evidence eXtraction Team for Research Analysis (EXTRA), which contributed to situational awareness in Canada through a bibliographic repository used to support decision-making by the National Advisory Committee on Immunization. We describe the process by which this literature was identified and catalogued, and provide an overview of characteristics in the identified literature.

Methods

To expedite the process, PHAC leveraged an artificial intelligence (AI) tool to assist in the screening and selection of relevant articles. Literature search results were initially screened by AI, then manually reviewed for relevance. Relevant articles were tagged using controlled vocabulary and stored in a bibliographic repository. This repository was analyzed to identify trends in vaccine research over time according to several key characteristics.

Results

As of December 31, 2023, EXTRA’s repository contained 19,050 articles relevant to PHAC’s immunization mandate. The majority of these articles (63.9 %) were identified between August 2021 and January 2023, with an average of 20 relevant articles added daily during this period. Nearly 14,000 articles reported on mRNA vaccines. Safety outcomes were most frequently reported (n = 8,289), followed by immunogenicity (n = 7,269) and efficacy/effectiveness (n = 3,246). COVID-19 vaccine literature output started to decrease in mid-2023, two years after the initial dramatic increase in mid-2021.

Conclusions

This hybrid (AI and human) approach was critical for PHAC situational awareness and the development of timely vaccine guidance in Canada during the COVID-19 pandemic. Given the volume of data and analyses required, the AI-augmented processes made this massive undertaking manageable. Analysis of COVID-19 vaccine research patterns supports projections of research volume, type, and rate that will help predict resourcing and information needs to plan future emergency vaccine guidance activities.