Research on the correlation between artificial intelligence and depression: A bibliometric analysis from 2000 to 2024

This study aims to systematically assess the research productivity of artificial intelligence (AI) technologies and depression using bibliometric methods, while also exploring the trends and prospects of AI applications in the diagnosis, prediction, and treatment of depression. This study employs bibliometric analysis, using the Web of Science database to collect relevant literature on depression and AI from 2000 to 2024. By analyzing indicators such as changes in the number of publications, keyword co-occurrence, author collaboration networks, and academic impact evaluation, the study comprehensively assesses the research dynamics and key topics in this field. The literature data are analyzed using visualization tools to identify core research themes and future development trends. From 2000 to 2024, the number of studies combining depression and AI showed steady growth. This study identified a total of 1437 papers published in 766 academic journals. Keyword analysis revealed that machine learning, deep learning, natural language processing, chatbots, and neuromorphic computing are the primary technological approaches used in this research. Regarding application domains, publications were categorized into screening (173 articles), diagnosis (279 articles), and treatment (944 articles), with a smaller group covering other aspects (41 articles). Additionally, international collaborative research has increased year by year, with particularly prominent scientific activities observed in the United States, China, and the United Kingdom. AI technology has demonstrated significant potential in the research and application of depression, particularly in precise diagnosis, personalized treatment, and early intervention. Nevertheless, key research gaps persist; long-term efficacy evidence is scarce, lack of standardized validation, and cross-disciplinary integration remains insufficient. This study employs bibliometrics analysis to map the field's evolution, identifying these critical areas requiring focused research and collaboration to fully harness AI's potential against depression.