Eliminating Indefiniteness of Clinical Spectrum for Better Screening COVID-19

Abstract

The coronavirus disease 2019 (COVID-19) has swept all over the world in the last few months. Due to the limited detection facilities and medical resources, especially in developing countries, a large number of suspected cases can only receive common clinical diagnosis rather than more effective detections like Reverse Transcription Polymerase Chain Reaction (RT-PCR) tests or CT scans. This motivates us to develop a quick screening method on suspected patients via common clinical diagnosis results. However, the diagnostic items of different patients may vary greatly and there is a huge variation in the dimension of the diagnosis data among different suspected patients, which makes it hard to process these indefinite dimension data via classical classification algorithms. To resolve this problem, we propose an Indefiniteness Elimination Network (IE-Net) to eliminate the influence of the varied dimensions and make predictions about the COVID-19 cases. The IE-Net is in an encoder-decoder framework fashion and an indefiniteness elimination operation is proposed to transfer the indefinite dimension feature into a fixed dimension feature. Comprehensive experiments were conducted on the public available COVID-19 Clinical Spectrum dataset. Experimental results show that the proposed indefiniteness elimination operation greatly improves the classification performance and the IE-Net achieves 94.80% accuracy, 92.79% recall, 92.97% precision and 94.93% AUC for distinguishing COVID-19 cases from non-COVID-19 cases with only common clinical diagnose data. We further compared our methods with 3 classical classification algorithms: random forest, gradient boosting and multi-layer perceptron (MLP). Compared with traditional classification methods, the proposed IE-Net can bring at least 9.40% accuracy gains, 12.17% recall gains, 3.66% precision and 9.71% AUC gains. To explore the specificity of each clinical test item, we further analyzed the possible relationship between each clinical test item and COVID-19. In general, we proposed a novel image complementary method for COVID-19 screen-

A Study on a Neural Network Risk Simulation Model Construction for Avian Influenza A (H7N9) Outbreaks in Humans in China during 2013–2017

“…Some researchers have compared and analyzed artificial neural network with random forest and other classification models. For example, in terms of epidemic research, Wang et al [ 29 ], Guo et al [ 30 ], and Oliveira et al [ 31 ] compared the efficiency of neural network, random forest and support vector machine models in the auxiliary diagnosis of AIDS and COVID-19, and results showed that the accuracy of the neural network model is higher than that of other models. In studies on other diseases, Yu et al [ 32 ], Choi et al [ 33 ], Lai et al [ 34 ], Shh et al [ 35 ] all made a comprehensive comparison among neural network, random forest and support vector machine in their respective studies, and concluded that the neural network model was more accurate than random forest and support vector machine models.…”

Covid-19 Hastalarında Başvuru Şikayetleri

“…An attempt is made to develop a rapid screening method with common clinical diagnosis results on suspicious patients. However, the differences in the diagnostic research characteristics of the patients make it difficult for these efforts to yield results (27).…”

Convolutional neural network based CT scan classification method for COVID-19 test validation

“…Extensive experiments have demonstrated that GANs can effectively deal with the problem of too few samples in datasets. For example, author ( Gomathi et al, 2020 ) used GAN to generate synthetic medical images to improve the accuracy of classification performance; author ( Guo et al, 2021 ) proposed a GAN-based architecture for limited training data scenarios, and the result was a model capable of Diversity is achieved in the generated samples. Author ( Niu et al, 2021 ) also used GAN as a data augmentation method to show that it can improve performance in tumor segmentation.…”