Deep learning-based COVID-19 diagnosis using CT scans with laboratory and physiological parameters

The global economy has been dramatically impacted by COVID-19, which has spread to be a pandemic. COVID-19 virus affects the respiratory system, causing difficulty breathing in the patient. It is crucial to identify and treat infections as soon as possible. Traditional diagnostic reverse transcription-polymerase chain reaction (RT-PCR) methods require more time to find the infection. A high infection rate, slow laboratory analysis, and delayed test results caused the widespread and uncontrolled spread of the disease. This study aims to diagnose the COVID-19 epidemic by leveraging a modified convolutional neural network (CNN) to quickly and safely predict the disease's appearance from computed tomography (CT) scan images and a laboratory and physiological parameters dataset. A dataset representing 500 patients was used to train, test, and validate the CNN model with results in detecting COVID-19 having an accuracy, sensitivity, specificity, and F1-score of 99.33%, 99.09%, 99.52%, and 99.24%, respectively. These experimental results suggest that our strategy performs better than previously published approaches.

Hybridization of particle swarm optimization algorithm with neural network for COVID-19 using computerized tomography scan and clinical parameters

The 2019 coronavirus disease began in Wuhan, China, and spread worldwide. This pandemic was concerning, given its significant and worrying impact on human health. Strategies to manage the disease begin with diagnosing the infection, often using the real-time reverse transcription polymerase chain reaction (RT-PCR) assay. However, this process is time intensive. Therefore, alternative rapid methods to diagnose the coronavirus with high accuracy are needed. X-ray and computerized tomography (CT) scans are reasonable solutions for rapid coronavirus diagnosis. The dataset of 500 patients was tested, including 286 uninfected patients and 214 infected with COVID-19. Clinical parameters, including heart rate (HR), temperature (T), blood oxygen level, D-dimer, and CT scan, including red-green-blue (RGB) pixel values of the left and right lungs, were collected from 500 patients and used to train an artificial neural network (ANN) to diagnose coronavirus. The ANN was hybridized with a particle swarm optimization (PSO) algorithm to improve diagnosis accuracy. The results show that the proposed PSO-ANN method significantly improved diagnosis accuracy (98.93%), sensitivity (100%), and specificity (98.13%). The effectiveness of the proposed method was confirmed by comparing the findings with those of previous studies.