The evolving landscape of artificial intelligence in patient education: A bibliometric knowledge mapping study

Area of Science:

• Digital Health
• Artificial Intelligence
• Bibliometrics

Background:

• AI offers solutions for patient education barriers like low readability and high personalization costs.
• The rapid integration of Large Language Models (LLMs) requires understanding the AI research landscape for effective implementation.

Purpose of the Study:

• To systematically map the global research landscape of AI in patient education.
• To identify knowledge structure, research hotspots, key contributors, and evolutionary trends.

Main Methods:

• Bibliometric analysis of 837 documents from 2016-2025 (Web of Science).
• Analysis using CiteSpace and RStudio for publication trends, collaborations, co-citation networks, and keyword evolution.

Main Results:

• Exponential publication increase since 2021, coinciding with LLM advent.
• USA and China lead research; Harvard University leads institutions.
• Hotspots evolved from machine learning to health literacy, readability, and adherence.

Conclusions:

• AI is transforming patient education towards patient-centered outcomes.
• LLMs show potential but face challenges in accuracy, ethics, and integration.
• Future work needs validation frameworks and international collaboration for digital health equity.