Classification of COVID-19 and Influenza Patients Using Deep Learning

Area of Science:

• Medical Imaging
• Artificial Intelligence in Medicine
• Infectious Disease Diagnosis

Background:

• Coronavirus (COVID-19) presents early flu-like symptoms, complicating diagnosis.
• Accurate and timely detection of COVID-19 is crucial for global health.
• Distinguishing COVID-19 from influenza in early stages poses a diagnostic challenge.

Purpose of the Study:

• To develop and evaluate deep learning models for classifying COVID-19, influenza, and normal cases.
• To compare the performance of different deep learning architectures for respiratory illness detection.
• To leverage chest X-ray imaging for automated disease diagnosis.

Main Methods:

• Utilized a publicly available dataset of chest X-ray images.
• Developed tailored deep learning models, including Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN).
• Trained and evaluated models for the classification of normal, influenza, and COVID-19 cases.

Main Results:

• Deep learning models demonstrated high accuracy in diagnosing normal, influenza, and COVID-19.
• The proposed Long Short-Term Memory (LSTM) model achieved 98% accuracy.
• LSTM outperformed the Convolutional Neural Network (CNN) model in the evaluation.

Conclusions:

• Deep learning, particularly LSTM, is effective for accurate COVID-19 and influenza diagnosis from chest X-rays.
• Automated detection systems can aid clinicians in differentiating between respiratory viral infections.
• Further research into AI-driven diagnostic tools is warranted for infectious diseases.