Exploring machine learning applications in Meningioma Research (2004–2023)

Abstract

Objective: This study aims to examine the trends in machine learning application to meningiomas between 2004 and 2023. Methods: Publication data were extracted from the Science Citation Index Expanded (SCI-E) within the Web of Science Core Collection (WOSCC). Using CiteSpace 6.2.R6, a comprehensive analysis of publications, authors, cited authors, countries, institutions, cited journals, references, and keywords was conducted on December 1, 2023. Results: The analysis included a total of 342 articles. Prior to 2007, no publications existed in this field, and the number remained modest until 2017. A significant increase occurred in publications from 2018 onwards. The majority of the top 10 authors hailed from Germany and China, with the USA also exerting substantial international influence, particularly in academic institutions. Journals from the IEEE series contributed significantly to the publications. ''Deep learning,'' ''brain tumor,'' and ''classification'' emerged as the primary keywords of focus among researchers. The developmental pattern in this field primarily involved a combination of interdisciplinary integration and the refinement of major disciplinary branches. Conclusion: Machine learning has demonstrated significant value in predicting early meningiomas and tailoring treatment plans. Key research focuses involve optimizing detection indicators and selecting superior machine learning algorithms. Future efforts should aim to develop high-performance algorithms to drive further innovation in this field.

Keywords

• Machine learning
• Meningiomas
• Bibliometric analysis