Generative Artificial Intelligence In Health Informatics Education: A Comprehensive Bibliometric Assessment Of Cognitive Outcome Research (2019–2025)

Abstract

This study provides a comprehensive bibliometric assessment of generative artificial intelligence (GenAI) research in health informatics education, with particular emphasis on cognitive outcomes. A total of 264 PubMed-indexed publications (2019–2025) were analyzed using Bibliometrix (R) and VOSviewer to evaluate annual scientific output, core journals, authorship patterns, institutional and country productivity, conceptual trends, and collaboration networks. Results show an exceptional rise in publication volume beginning in 2023, coinciding with the widespread introduction of large language models such as ChatGPT. The intellectual structure of the field is dominated by themes related to artificial intelligence, machine learning, large language models, and digital health applications. Two major clusters of application were identified: clinical and patient-centered communication, and educational processes involving competence development and assessment. Ethical themes, including bias and transparency, emerged rapidly in 2024–2025. Research output is highly concentrated in the United States and China, whereas collaboration patterns remain fragmented with multiple small author clusters. Most studies relied on cross-sectional designs, with limited experimental or longitudinal evaluation of learning outcomes. The findings highlight a methodological gap between technical GenAI development and established educational or cognitive frameworks. The study recommends integrating cognitive theory, improving methodological rigor, and expanding interdisciplinary and international collaboration. This bibliometric mapping offers an evidence-oriented foundation for guiding future work on GenAI-enhanced teaching, learning, curriculum design, and evaluation in health informatics education.