Application of intelligence-based computational techniques for classification and early differential diagnosis of COVID-19 disease

Abstract

Clinical methods are used for diagnosing COVID-19 infected patients, but reports posit that, several people who were initially tested positive of COVID-19, and who had some underlying diseases, turned out having negative results, after further tests. Therefore, the performance of clinical methods is not always guaranteed. Moreover, chest X-ray image data of COVID-19 infected patients are mostly used in the computational models for COVI-19 diagnosis while the use of common symptoms such as “ Fever, Cough, Fatigue, Muscle aches, Headache etc ”, in computational models is not yet reported. In this study, we employ seven classification algorithms to empirically test and verify their efficacy when applied to diagnose COVID-19 using the aforementioned symptoms. We experimented with logistic regression (LR), support vector machine (SVM), naïve Byes (NB), decision tree (DT), multilayer perceptron (MLP), fuzzy cognitive map (FCM) and Deep neural network (DNN) algorithms. The techniques were subjected to random under-sampling and over-sampling. Our results showed that with class imbalance, MLP and DNN outperform others but without class imbalance MLP, FCM and DNN outperform others with the use of random under-sampling but DNN has the best performance with the use random oversampling. This study identified MLP, FCM and DNN as better classifiers over LR, NB, DT and SVM, that healthcare software system developers can adopt to develop intelligence-based expert systems which both medical personnel and patients can use for differential diagnosis of COVID-19 based on the aforementioned symptoms however, the test of performance must not be limited to the traditional performance metrics.

A Critical Historic Overview of Artificial Intelligence: Issues, Challenges, Opportunities, and Threats

“…The experts use methods of cognitive science and fuzzy logic. This approach has been used to address difficult problems with very useful results: in energy (Kyriakarakos et al, 2012;Mahboub et al, 2019;Pereira et al, 2020), in health (Amirkhani et al, 2017;Apostolopoulos & Groumpos, 2020;Bevilacqua et al, 2012;Bhatia & Kumar, 2015;Bhatia et al, 2014;de Moraes Lopes et al, 2013;Janmenjoy et al, 2015;Oye & Thomas, 2019;Papageorgiou, 2012;Savage, 2019), in business and economics (Lopez & Ishizaka, 2019;Paes de Faria et al, 2020;Groumpos, 2015;Neocleous & Schizas, 2012), in social and international affairs (Groumpos, , 2019Cole & Persichitte, 2000;Mago et al, 2013;Wang et al, 2022), on COVID-19 (Akinnuwesi et al, 2021;Goswami et al, 2021;Groumpos, 2020Groumpos, , 2021, in agriculture (Christen et al, 2015;Correa et al, 2012;Groumpos et al, 2016), and in renewable energy sources (Çoban & Onar, 2017;Jetter & Schweinfort, 2011;Karlis et al, 2007). Reviews of FCMs for several applications are provided in Papageorgiou and Salmeron (2013) and Janmenjoy et al (2015).…”

Effect of vitamin energy drinks on relieving exercise-induced fatigue in muscle group by ultrasonic bioimaging data analysis

“…With the wide application of artificial intelligence in various fields, including long shortterm memory (LSTM) neural network and support vector machine (SVM) [14][15][16]. Ashraf et al (2023) [17] adopted a new denoising algorithm based on variational mode decomposition, and used SOFT iterative interval threshold to process surface and intramuscular electromyography.…”

Predicting HIV Status among Men Who Have Sex with Men in Bulawayo & Harare, Zimbabwe Using Bio-Behavioural Data, Recurrent Neural Networks, and Machine Learning Techniques

“…The SVM is a binary classification algorithm that classifies data and separates the two classes by constructing an operating separating hyperplane [22]. The support vectors are the data points closest to the hyperplane, while the hyperplane is a decision space divided between a set of objects with different classes [23]. All parameters for SVM in sklearn were left on default.…”