Ensemble learning for multi-class COVID-19 detection from big data.

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Data Science

Background:

• Coronavirus disease (COVID-19) presents pneumonia-like symptoms and rapid spread, necessitating advanced detection strategies.
• Chest X-rays are a cost-effective initial diagnostic tool for COVID-19.
• Existing detection methods require improved efficiency in training and execution times.

Purpose of the Study:

• To introduce an advanced architecture for COVID-19 detection from chest X-ray images using ensemble learning.
• To enhance the efficiency of COVID-19 detection models by reducing training and execution times.
• To validate the model's efficacy and compare its performance against state-of-the-art methods.

Main Methods:

• Developed an advanced architecture integrating ensemble learning with big data analytics.
• Utilized a parallel and distributed framework to facilitate parallel processing.
• Evaluated model performance using accuracy, precision, recall, and F-measure metrics.

Main Results:

• The proposed ensemble learning model demonstrated enhanced execution and training times.
• The model's efficacy was validated through comprehensive analysis of predicted and actual values.
• Performance metrics indicated a robust detection capability for COVID-19 from chest X-rays.

Conclusions:

• Ensemble learning, integrated with big data analytics and parallel processing, offers an effective approach for COVID-19 detection.
• The proposed model significantly improves efficiency in training and execution times for medical image analysis.
• This work highlights the potential of ensemble learning techniques in advancing healthcare diagnostics and disease management.