Detection of COVID-19 Using Deep Learning Techniques and Cost Effectiveness Evaluation: A Survey

Area of Science:

• Radiology and Medical Imaging
• Artificial Intelligence in Medicine
• Epidemiology

Background:

• Pandemics necessitate efficient diagnostic tools.
• Radiographic imaging, including Chest X-rays (CXR) and CT scans, plays a crucial role in identifying infectious diseases.
• Deep learning has emerged as a powerful tool for analyzing complex medical imaging data.

Purpose of the Study:

• To comprehensively analyze deep learning methodologies for COVID-19 detection.
• To evaluate the cost-effectiveness and financial implications of AI-driven diagnostic methods.
• To identify the most affordable and reliable imaging techniques for pandemic virus detection.

Main Methods:

• Literature review and analysis of deep learning techniques applied to radiographic images (CXR, CT scans) for COVID-19 detection.
• Comparative analysis of different imaging modalities based on cost-effectiveness and diagnostic accuracy.
• Examination of financial aspects, including insurance claim settlements.

Main Results:

• Deep learning models demonstrate high potential in recognizing patterns indicative of COVID-19 in radiographic images.
• AI can enhance image characteristics for improved diagnostic accuracy.
• The study identifies cost-effective and trustworthy imaging methods for pandemic virus detection.

Conclusions:

• Deep learning offers a practical, affordable, and reliable modality for COVID-19 diagnosis.
• AI-enhanced medical imaging presents a valuable approach for pandemic response.
• The cost-effectiveness of these methods has significant financial implications, particularly for insurance claim settlements.