Artificial Intelligence and Machine Learning in Connected Health: A Bibliometric Analysis of Evolving Trends within Society 5.0

Abstract

The objective of this study is to provide a bibliometric analysis of research in the field of connected health, focusing on the increasing role of Artificial Intelligence (AI) and Machine Learning (ML) in the era of Society 5.0. This analysis aims to identify dominant publications and themes, as well as the connections between these technologies and their healthcare applications, to better understand how they are poised to revolutionize clinical practices and decision-making processes. A corpus of 1866 articles, published between 2014 and 2024 and sourced from the Scopus database, was meticulously analyzed. Document selection was based on specific criteria, including keywords such as "artificial intelligence", "machine learning" and "smart healthcare" in titles, abstracts, and keywords, with publications limited to English-language articles. The bibliometric indicators employed include citation counts, the most influential journals, and keyword co-occurrence analyses. The choice of the Shiny App for Bibliometrix was strategically made to visualize co-occurrence networks and identify major thematic clusters effectively. The keyword co-occurrence analysis revealed several major thematic clusters, with primary clusters centered on terms like "artificial intelligence", "machine learning" and "health care". These clusters highlight the interconnection of themes and reveal closely related research areas, particularly the use of AI for health monitoring, intelligent diagnostics, and healthcare service optimization.