A Scientometrics Analytics on Immune system-related conditions and AI-driven computational methods: Trend and Exploration

In the previous decade, there has been a concerning rise in both prevalence and incidence rates of autoimmune diseases. According to recent studies, these illnesses affect about 10% of the population, with a significantly higher frequency in women than in men. A comprehensive study conducted in the UK has underscored this trend, revealing significant socioeconomic, seasonal, and geographical variations in the manifestation of these diseases. Furthermore, evidence indicates that individuals diagnosed with one autoimmune condition are at an elevated risk of developing additional autoimmune disorders, although this correlation is not uniform across all conditions. The principal purpose of this research is to highlight and carefully review the corpus of existing material that explores the use of ML technique in the framework of autoimmune diseases. This includes an assessment of the present level of understanding as well as an all embracing and impartial review of recent advancements, areas requiring improvement, concerns, and potential future research directions. Utilizing R programming and bibliometrix codes, a descriptive bibliometric analysis was conducted, resulting in a matrix that encompasses all relevant documents. Data was sourced from the WOS database, During the time frame from 2002 to 2025, specifically concentrating on the terms “Immune system-related conditions” and “AI-driven computational methods.” The final dataset comprised 419 publications, revealing a connection between autoimmune diseases and machine learning. Key themes identified include “Rheumatoid Arthritis,” “Pathogenesis,” and “Inflammation.” In the current research landscape, topics such as systems, consensus, and cell death have gained significant adhesion. This paper provides a comprehensive overview of the bibliometric measure linking autoimmune diseases and machine learning, thereby contributing to the advancement of scientific research in this domain.