Authors: Kavian Khanjani, Seyed Rasoul Hosseini, Shahrzad Shashaani, Mohammad Teshnehlab

Published on: April 02, 2024

Impact Score: 8.0

Arxiv code: Arxiv:2404.02348

Summary

• What is new: This study introduces an innovative use of self-categorizing classifiers for differentiating COVID-19 patients from others using blood test samples and radiography images, utilizing an Ensemble method that combines neural networks and machine learning methods.
• Why this is important: The need for early and accurate detection of COVID-19 to control its rapid global spread and manage treatment effectively.
• What the research proposes: Employing a combination of AI techniques, including machine learning, neural networks, and deep learning, to classify diseases and differentiate COVID-19 patients through blood tests and radiography images.
• Results: Achieved a 94.09% accuracy in classifying COVID-19 from blood test samples and a 91.1% accuracy from radiography images, proving to be both cost-effective and faster than other methods.

Technical Details

Technological frameworks used: Ensemble method combining neural networks with machine learning

Models used: Neural networks, machine learning methods, deep learning

Data used: Blood test samples, radiography images

Potential Impact

Healthcare providers, diagnostic centers, AI-driven diagnostic tool developers, and medical imaging companies could benefit through improved detection methods, potentially disrupting current diagnostic markets.

Want to implement this idea in a business?

We have generated a startup concept here: ViraDetect.