# Use of Artificial Intelligence in Public Health Education for Pandemic Preparedness and Response

## TL;DR

This paper reviews how artificial intelligence is used in public health education during pandemics, highlighting its potential for personalized learning and communication while identifying gaps in research and governance.

## Contribution

The study maps AI-based educational strategies in pandemic preparedness and response, revealing key gaps in scalability, equity, and governance.

## Key findings

- Conversational AI and machine learning tools are widely used for health literacy and misinformation management.
- Most AI interventions focus on the response phase of pandemics, with limited applications for preparedness.
- Human oversight is crucial for ensuring safety and reliability of AI-based educational tools.

## Abstract

Background: The rapid evolution of artificial intelligence (AI) has enabled new approaches for health education, particularly during public health emergencies. However, evidence remains fragmented on how AI-based educational strategies support preparedness, response, and recovery phases of pandemics and epidemics.

Objective: To map the use of AI-based technologies in health education strategies addressing preparedness, response, and recovery during public health emergencies, identifying target populations, intervention characteristics, outcomes, scalability, and knowledge gaps.

Methods: This scoping review followed Joanna Briggs Institute methodology and PRISMA-ScR guidelines. Searches were conducted in PubMed/MEDLINE, Scopus, Web of Science, Embase, IEEE Xplore, and LILACS, complemented by gray literature from Google Scholar. Studies published from 2010 onward in English, Portuguese, or Spanish were included. Eligible designs comprised primary studies, methodological or implementation research, and reviews with explicit educational components. Data extraction covered context, populations, AI modalities, educational purposes, delivery channels, supervision requirements, pandemic-cycle phase, scalability, outcomes, and evidence gaps.

Results: Forty-one studies met the inclusion criteria. Conversational AI (chatbots and large language models) and algorithmic curation tools using machine learning and natural language processing predominated. Most interventions supported health literacy, risk communication, and misinformation management; others addressed personalized learning, microtraining, and clinical simulation for students and health professionals. Delivery channels included mobile applications, messaging platforms, websites/YouTube, and clinical AI systems. Human oversight (expert validation and curation) was consistently reported as essential for safety and reliability. Interventions mainly targeted the response phase, with emerging applications for preparedness. Major gaps included standardized learning measures, cost-effectiveness evaluations, equity analyses, and governance frameworks ensuring privacy, transparency, and bias control.

Conclusions: AI-enabled educational technologies can strengthen rapid, scalable, and personalized learning during health emergencies. Future research should prioritize multicenter studies using standardized indicators, economic and equity assessments, and robust governance frameworks to ensure ethical, safe, and inclusive adoption.