A brief review and scientometric analysis on ensemble learning methods for handling COVID-19

Area of Science:

• Artificial Intelligence
• Medical Informatics
• Computational Biology

Background:

• The COVID-19 pandemic spurred extensive global research, including the application of machine learning and deep learning techniques.
• Ensemble learning methods have shown promise for COVID-19 detection, yet a comprehensive scientometric analysis was lacking.

Purpose of the Study:

• To conduct a scientometric analysis and brief review of research utilizing ensemble learning for COVID-19 detection.
• To identify trends, key algorithms, and prominent research contributions in this field.

Main Methods:

• A two-step approach combining a concise literature review with scientometric and bibliometric analyses.
• Data retrieval from the Scopus database for relevant published articles.

Main Results:

• Convolutional Neural Network (CNN) emerged as the most frequently utilized algorithm.
• Support Vector Machine (SVM), Random Forest, Resnet, DenseNet, and VGG were also commonly employed ensemble learning methods.
• China demonstrated a significant presence in top-ranking research categories.

Conclusions:

• The study provides valuable insights into the landscape of ensemble learning for COVID-19 detection.
• Identified trends and dominant algorithms offer a foundation for future research and development in AI-driven diagnostics.