Prediction of COVID-19 Using Genetic Deep Learning Convolutional Neural Network (GDCNN)

Abstract

Rapid spread of Coronavirus disease COVID-19 leads to severe pneumonia and it is estimated to create a high impact on the healthcare system. An urgent need for early diagnosis is required for precise treatment, which in turn reduces the pressure in the health care system. Some of the standard image diagnosis available is Computed Tomography (CT) scan and Chest X-Ray (CXR). Even though a CT scan is considered a gold standard in diagnosis, CXR is most widely used due to widespread, faster, and cheaper. This study aims to provide a solution for identifying pneumonia due to COVID-19 and healthy lungs (normal person) using CXR images. One of the remarkable methods used for extracting a high dimensional feature from medical images is the Deep learning method. In this research, the state-of-the-art techniques used is Genetic Deep Learning Convolutional Neural Network (GDCNN). It is trained from the scratch for extracting features for classifying them between COVID-19 and normal images. A dataset consisting of more than 5000 CXR image samples is used for classifying pneumonia, normal and other pneumonia diseases. Training a GDCNN from scratch proves that, the proposed method performs better compared to other transfer learning techniques. Classification accuracy of 98.84%, the precision of 93%, the sensitivity of 100%, and specificity of 97.0% in COVID-19 prediction is achieved. Top classification accuracy obtained in this research reveals the best nominal rate in the identification of COVID-19 disease prediction in an unbalanced environment. The novel model proposed for classification proves to be better than the existing models such as ReseNet18, ReseNet50, Squeezenet, DenseNet-121, and Visual Geometry Group (VGG16).

Artificial intelligence in clinical care amidst COVID-19 pandemic: A systematic review

“…val. Acc 92.5, SEN 92 U U U H H Babukarthik et al [74] , Early diagnosis 102 GDCNN Imaging features unclear Acc 98.84, SEN 100, SPE 97.0 H H H H H Minaee et al [20] , Diagnosis unclear CNN Raw images without feature extraction TTS SEN 98, SPE 92 U U U H H Yan et al [94] , China, Diagnosis 206 CNN Imaging features TTS SEN 99.5 (95%CI: 99.3–99.7), SPE 95.6 (95%CI: 94.9–96.2) L H H H H Lokwani et al [95] , India, Diagnosis 55 NN Imaging features TTS SEN 96.4 (95% CI: 88–100), SPE 88.4 (95% CI: 82–94) U U H H H Jin et al [96] , China, Screening (early detection) 751 DL, DNN Imaging features TTS AUC 0.97, SEN 90.19, SPE 95.76 H U U H H Ko et al [29] , South Korea, Diagnosis 20 2D DL Imaging features TTS, ext.val. Acc 99.87, SEN 99.58, SPE 100.00 U U U H H Ezzat et al [34] , Diagnostic imaging 99 Hybrid CNN Not applicable TTS Acc 98 H U …”

Predicting COVID-19 Disease Progression and Patient Outcomes based on Temporal Deep Learning

“…In addition to the basic information of patients, the vital signs, diagnoses and other lab tests are all time series. Existing many works [28][29][30][31][32][33][34][35][36][37][38][39][40][41][42]45] Besides, we have found that the time series of COVID-19 patients is irregularly sampled -Different time intervals exist in adjacent observations. Every possible test is not regularly measured during an admission.…”

“…Deep learning methods can train the parameters with complex nonlinearity to learn the data structures and have achieved state-of-the-art in many medical prediction tasks [19,20,47]. Thus, many current works apply deep learning methods for COVID-19 prediction tasks [28][29][30][31][32][33][34][35][36]. However, these methods either use the simple multi-layer perceptron for predicting or use the convolutional structures for image classification.…”

Development and Validation of a Machine Learning Approach for Automated Severity Assessment of COVID-19 Based on Clinical and Imaging Data: Retrospective Study

“…Previous studies have focused on mortality predictions [ 9 ], diagnosis (identifying COVID-19 cases and differentiating them from other pulmonary diseases or no disease) [ 10 - 15 , 19 , 22 - 25 ], and severity assessment and disease progression [ 16 - 18 , 23 ]. Most current approaches have used deep learning methods and imaging features from CT scans [ 10 - 15 , 19 , 22 - 24 ] and X-ray imaging [ 18 , 20 , 21 ] with popular architectures including ResNet [ 10 , 12 , 14 , 23 ], U-Net [ 11 , 17 ], Inception [ 15 , 22 ], Darknet [ 20 ], and other convolutional neural networks (NNs) [ 18 , 21 , 26 , 27 ]. Recent reviews provide more details regarding these architectures [ 1 , 28 - 32 ].…”