Machine learning applied to epilepsy: bibliometric and visual analysis from 2004 to 2023

Area of Science:

• Neurology
• Artificial Intelligence
• Biomedical Informatics

Background:

• Epilepsy is a common neurological disorder with significant individual and societal impact.
• Machine learning (ML) integration in epilepsy research is increasing for clinical diagnosis, prediction, and precision medicine.
• A bibliometric assessment was needed to evaluate scientific progress in ML applications for epilepsy.

Approach:

• A comprehensive search of the Web of Science Core Collection database (2004-2023) was conducted.
• Bibliometric analyses and visualizations were performed using VOSviewer, CiteSpace, and Bibliometrix (R-Tool).
• A total of 1,284 papers were analyzed to identify trends, key contributors, and research hotspots.

Key Points:

• Research output on ML in epilepsy shows a consistent year-on-year increase.
• The United States and China are leading contributors, with 1,957 organizations and 87 countries involved.
• Key research areas include seizure prediction, epilepsy management, and epilepsy neuroimaging.

Conclusions:

• This study provides the first bibliometric visualization of ML applications in epilepsy research.
• It identifies current trends and frontiers, offering valuable references for researchers in the field.
• The findings highlight the growing importance of ML in advancing epilepsy diagnosis and treatment.