Abstract Background Systemic lupus erythematosus (SLE) is a severe autoimmune disease that imposes substantial burdens on individuals and healthcare systems. Machine learning (ML) offers significant potential to advance the diagnosis, prognosis, and precision medicine of SLE. However, no bibliometric evaluation has yet focused specifically on this intersection. This study addresses that gap by conducting a comprehensive bibliometric and visual analysis of publications from the past decade on ML applications in SLE. These findings are intended to offer valuable insights for researchers, clinicians, and policymakers, thereby supporting their efforts to understand and advance this promising interdisciplinary field. Methods A scientometric analysis was conducted on English-language publications concerning ML applications in SLE. The literature dataset, comprising research and review articles published between 2015 and 2025, was retrieved from the Web of Science Core Collection. Using CiteSpace software (Version 6.3.R2), this study systematically investigated publication trends over time, collaborative networks among institutions, and the evolution of thematic research foci within the field. Results Analysis of included publications revealed that the People’s Republic of China contributed the most studies, and the University of California System was the leading institution. The most prolific individual investigators were Lipsky, Peter E and Grammer, Amrie C. The reference by Aringer M (2019) received the highest number of citations (30). Co-citation analysis identified key research domains, including disease classification, prediction models, lupus nephritis, and biomarker discovery. Emerging keyword trends highlighted growing interest in disease activity, type I interferon, prediction tools, and pathogenesis. Conclusions This study maps the intellectual landscape of ML applications in SLE research, outlining three core thematic clusters: disease classification and diagnosis, prediction of disease activity and outcomes, and pathogenesis and biomarker discovery. The findings help clarify the evolution of the field and suggest priorities for future interdisciplinary research, while underscoring the role of bibliometrics in guiding scientific inquiry.
Fu et al. (Mon,) studied this question.