Ensemble Deep Learning and Internet of Things-Based Automated COVID-19 Diagnosis Framework

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Infectious Diseases

Background:

• Coronavirus disease (COVID-19), caused by SARS-CoV-2, necessitates rapid and accurate diagnostic methods.
• Computed tomography (CT) scans are valuable for early COVID-19 detection.
• Deep learning models show promise for automated screening of COVID-19 cases.

Purpose of the Study:

• To propose an ensemble deep learning and Internet of Things (IoT) framework for efficient screening of COVID-19 suspected cases.
• To leverage pretrained deep learning models and medical IoT devices for automated diagnosis.

Main Methods:

• Ensembling three well-known pretrained deep learning models.
• Utilizing medical IoT devices for collecting CT scans.
• Performing automated diagnoses on IoT servers.

Main Results:

• The proposed framework achieved 98.98% accuracy in diagnosing COVID-19.
• The model demonstrated superior performance with 98.56% precision, 98.58% recall, 98.75% F-score, and 98.57% AUC.
• The framework outperformed thirteen competitive models on a four-class dataset.

Conclusions:

• The developed ensemble deep learning and IoT framework significantly accelerates COVID-19 diagnosis.
• This approach offers a robust and accurate solution for automated screening of suspected COVID-19 cases.