Data Mining Techniques for Extraction and Analysis of Covid-19 Data

Artificial intelligence has played a crucial role in medical disease diagnosis. In this research, data mining techniques that included deep learning with different scenarios are presented for extraction and analysis of covid-19 data. The energy of the features is implemented and calculated from the CT scan images. A modified meta-heuristic algorithm is introduced and then used in the suggested way to determine the best and most useful features, which are based on how ants behave. Different patients with different problems are investigated and analyzed. Also, the results are compared with other studies. The results of the proposed method show that the proposed method has higher accuracy than other methods. It is concluded from the results that the most crucial features can be concentrated on during feature selection, which lowers the error rate when separating sick from healthy individuals. © 2022 IEEE.

Modeling The Effect of Contaminated Object, Vaccination and Treatment on The Diseases Epidemiology

In this paper, the effect of contaminated objects on a SIRS Model with vaccination and hospitalization compartments is modeled. Positivity and boundedness properties of the solutions of model are proved, basic reproduction number of the model is founded through criteria which make the eigenvalues of the Jacobean matrix at the disease-free equilibrium point, negative. Globally stability analysis of the disease-free equilibrium point is proved when the basic reproduction number is less than unity. The existence, uniqueness of the endemic equilibrium point is investigated when the basic reproduction number is greater than unity. Parameter values regarding to spreading covid-19 in Kurdistan region are estimated. Finally, sensitivity analysis of the reproduction number is carried out. © 2022 Production by the University of Garmian. This is an open access article under the LICENSE.

INSIGHT OF PANDEMIC COVID-19: DEVELOPMENTS AND CHALLENGES

This review focuses on the characteristics of coronavirus disease-19 (COVID-19) including virus structure, ecoepidemiology and pathophysiology, signs and symptoms in infected people, and data on virus pathogenicity, severity, and survivability in COVID-19 infected patients. The emphasis is on immunological reactions, diagnosis, prophylactic methods, and the zoonotic significance of COVID-19. The authors feel that the review's contents will be valuable to epidemiologists, virologists, public health officials, diagnosticians, laboratory workers, environmentalists, and socioeconomic experts. It has information on the many types of coronavirus variants, the disease situation in Pakistan and the WHO criteria for COVID-19 prevention is given. Moreover, lessons learned from the COVID-19 pandemic are also outlined.

Effects of some biological factors on Coronavirus

This research was been adopted to study the relationship between Covid and some necessary biological factors in human body and how these factors affected, This studying included three stages (Sever - Moderate - Mild) it was studied 20 patient for every stage and monitor the biological factors during infection and after infection.Copyright © 2023, Codon Publications. All rights reserved.

Global e-Commerce (GeC) theory by intuitionistic fuzzy Γ-submodule

Intuitionistic fuzzy set (IFS) theory can be applied for multi-aspect systems due to its capability to address uncertainty and incomplete information in terms of membership and non-membership degrees. Unfortunately, classical Γ-structures cannot handle fuzzy and imprecise information in real problems. In fact, there is no rigorous base to practically express the effectiveness of multi-attribute systems in IFS environment. Here, we develop a generalized IFS with the notion of Γ-module called intuitionistic fuzzy Γ-submodule (IFΓM) to establish a novel "Global electronic (e)-Commerce (GeC) Theory”. To simplify the analysis of parameters, (α,β)-cut representation is proposed in terms of comprehensive distribution of fuzzy number for the classification of components. On the other hand, Cartesian product is implemented to correspond the elements. Substantial properties of IFΓM including (α,β)-cut, Cartesian product and t-intuitionistic fuzzy Γ-submodule (t-IFΓM) are characterized with illustrative examples to extend the framework of IFΓM, where (α,β)-cut and support t-IFΓM are verified to be Γ-submodules based on the properties of IFΓM. Through Γ-module homomorphism, image and inverse image, the parametric connections between (α,β)-cuts are systematically investigated. In addition, a mathematical relationship between the Cartesian product and (α,β)-cut is determined. The overlapping intersection of a collection of t-IFΓM is proved to be t-IFΓM, and the image and inverse image are preserved under Γ-module homomorphism. As global e-trades are increasingly expanding after the recent coronavirus disease 2019 (COVID-19) hit, with the growth of 26.7-trillion dollars, businesses are required to transform their traditional functional natures to online (or blended) strategies for cost efficiency and self-survival in the present competitive environment. Therefore, compared to recent studies on IFS in the context of Γ-structures, the main contribution of this study is to provide a theoretical basis for the establishment of a new GeC Theory through the developed IFΓM method and Γ-module M which targets the purchasing rate of customers through e-commerce companies. In the end, the performance of the proposed method in terms of upper and lower cut, t-intuitionistic fuzzy set, support and IFΓM model, is analyzed in the developed GeC Theory. The proposed GeC Theory is validated using real datasets of e-commerce mega companies, i.e., Amazon, Alibaba, eBay, Shopify. They are characterized based on the amount of online shopping by samples (individuals). Compared to the existing methods, the GeC approach is an effective IFS-based method for complex systems with uncertainty. © 2023 Elsevier Ltd

Associations between IL-17A G/A-rs2275913 and IL 23R A/G-rs11209026 gene polymorphisms and severe coronavirus disease 2019 (COVID-19).

Severe COVID-19 disease was linked to a severe proinflammatory response and cytokine storm interleukin 17 (IL-17) is one of these cytokines, was associated with severe acute lung injury and multiorgan dysfunction. Single nucleotide polymorphisms (SNPs) in genes coding IL-17 can affect level of IL-17 hence its role in diseases. Also, SNPs in IL-23 R which control IL-23 is the main activator of IL-17 production. This study aimed to determine whether the IL-17A (G/A-rs2275913), IL-23R (A/G rs11209026) SNPs and serum levels of IL-17 were related to the risk of severe COVID-19. This case-control study included 120 confirmed COVID-19 patients, divided into two categories according to the severity of the disease and 74 normal subjects as controls. COVID-19 patients were SARS-CoV-2 positive by a reverse transcription-polymerase chain reaction and subjected to full clinical examinations, routine laboratory tests, and radiographic evaluations. The IL-17 levels were assessed using ELISA method, and genotyping of IL-17A (197 A/G; rs2275913) and IL-23R rs11209026 (A/G) was performed by the TaqMan Genotyping Assay. There were no differences in the distribution of IL-17A or IL-23R genotypes between COVID-19 groups and the control group (p=0.93 and p=0.84, respectively). Severe COVID-19 patients had significantly higher IL-17 serum levels than non-severe COVID-19 (p=0.0001). The GG genotypes of IL-17A were significantly higher in severe COVID-19 patients (p=0.004). Multivariate logistic regression analysis revealed that AG, GG genotypes of IL-17 and IL-17A were independent predictors of COVID-19 disease severity (p < 0.0001, p=0.06 and p=0.04, respectively). ROC curve analysis for IL-17, as predictor of severe COVID-19 disease revealed a sensitivity of 87.9% and specificity of 66.1% at a cutoff point of 114 pg/ml with AUC = 0.799. In conclusion, these findings indicated that IL-17 may be considered a marker of severe COVID-19. IL-17A SNPs may have a role in COVID-19 severity. IL-23R SNPs had no role in COVID-19.

The influence of dietary Salvia and lavender powders on productive performance, some physiological parameters, and immunity of broiler under stocking density stress

The purpose of this experiment was to increase poultry meat production by increasing the number of chickens reared in the same area and managing it by using medicinal herbs Salvia officinalis L and Lavandula angustifolia L. in the broiler chicken diet. 705 one-day-old chicks were randomly distributed into to7 treatments with three replicates for an area of two m2 floor system in each replicate for each treatment, during 35 days of the study. T0 negative control 75 chicks, 25 chicks for each replicate 12-13 chicks per m2 fed standard diet. T1 positive control (stocking density without supplementation)105 chicks, 35 each replicate chicks 17-18 per m2 fed standard diet. The same stocking density for T2, T3, T4, T5, and T6 have been given standard feed with supplemented herbals, salvia 0.7%, 0.9%, lavender0.7%, 0.9%, and mixed 0.7% respectively. Depending on the results, chickens reared in stress stocking density with supplementations led to higher improvement of body weight, meat production, body weight gain (BWG), feed conversion ratio(FCR g feed/g weight), production index PI, carcass weight (g) and dressing percentage, RBCs 106cells/mm3, lymphocyte%, of increasing activity of thyroid hormones T3, T4 (nmol/L) boost antibody titers of ND and IBV when compared with positive control. However, heterophil%, stress indicator H/L ratio, glucose mg/ dL and cholesterol mg/ dL significantly reduced. The results showed that adding sage and lavender plants to broiler feed is effective in improving productivity, immunity, and resistance characteristics in reducing the adverse effects of stress caused by increasing the intensity of broiler rearing in the same area.

Variants of SARS-CoV-2: Influences on the Vaccines' Effectiveness and Possible Strategies to Overcome Their Consequences.

The immune response elicited by the current COVID-19 vaccinations declines with time, especially among the immunocompromised population. Furthermore, the emergence of novel SARS-CoV-2 variants, particularly the Omicron variant, has raised serious concerns about the efficacy of currently available vaccines in protecting the most vulnerable people. Several studies have reported that vaccinated people get breakthrough infections amid COVID-19 cases. So far, five variants of concern (VOCs) have been reported, resulting in successive waves of infection. These variants have shown a variable amount of resistance towards the neutralising antibodies (nAbs) elicited either through natural infection or the vaccination. The spike (S) protein, membrane (M) protein, and envelope (E) protein on the viral surface envelope and the N-nucleocapsid protein in the core of the ribonucleoprotein are the major structural vaccine target proteins against COVID-19. Among these targets, S Protein has been extensively exploited to generate effective vaccines against COVID-19. Hence, amid the emergence of novel variants of SARS-CoV-2, we have discussed their impact on currently available vaccines. We have also discussed the potential roles of S Protein in the development of novel vaccination approaches to contain the negative consequences of the variants' emergence and acquisition of mutations in the S Protein of SARS-CoV-2. Moreover, the implications of SARS-CoV-2's structural proteins were also discussed in terms of their variable potential to elicit an effective amount of immune response.

Regulatory T Cells (Tregs) and COVID-19: Unveiling the Mechanisms, and Therapeutic Potentialities with a Special Focus on Long COVID.

The COVID-19 pandemic has caused havoc all around the world. The causative agent of COVID-19 is the novel form of the coronavirus (CoV) named SARS-CoV-2, which results in immune system disruption, increased inflammation, and acute respiratory distress syndrome (ARDS). T cells have been important components of the immune system, which decide the fate of the COVID-19 disease. Recent studies have reported an important subset of T cells known as regulatory T cells (Tregs), which possess immunosuppressive and immunoregulatory properties and play a crucial role in the prognosis of COVID-19 disease. Recent studies have shown that COVID-19 patients have considerably fewer Tregs than the general population. Such a decrement may have an impact on COVID-19 patients in a number of ways, including diminishing the effect of inflammatory inhibition, creating an inequality in the Treg/Th17 percentage, and raising the chance of respiratory failure. Having fewer Tregs may enhance the likelihood of long COVID development in addition to contributing to the disease's poor prognosis. Additionally, tissue-resident Tregs provide tissue repair in addition to immunosuppressive and immunoregulatory activities, which may aid in the recovery of COVID-19 patients. The severity of the illness is also linked to abnormalities in the Tregs' phenotype, such as reduced expression of FoxP3 and other immunosuppressive cytokines, including IL-10 and TGF-beta. Hence, in this review, we summarize the immunosuppressive mechanisms and their possible roles in the prognosis of COVID-19 disease. Furthermore, the perturbations in Tregs have been associated with disease severity. The roles of Tregs are also explained in the long COVID. This review also discusses the potential therapeutic roles of Tregs in the management of patients with COVID-19.

Public nutritional Knowledge toward the COVID-19 among Palestinian Population: A Cross- Sectional Study

Background: COVID-19 is an emerging infectious disease that affected multiple countries and sustained person-to-person transmission making it a concerning and serious public health threat. This pandemic has emphasized that good nutrition and a healthy life is the key to strengthening immunity. Aim of the study: To assess knowledge of nutrition toward the COVID-19 among the Palestinian population. Methods: A cross-sectional online survey was launched at West Bank and Gaza Strip. A total number of 554 participants have shared the completion of this survey and the response rate was 90.2%. Results: The mean level of knowledge among participants was 65.38% and the study indicated that 55.8% behaving healthy nutritional habits. The analysis revealed that the mean score of knowledge increased by 1.61 comparing the oldest age groups (>30 years) against the youngest group. As the same as, the knowledge mean score increased by 2.46 among the obese individuals according to BMI classification (>30). Whereas, the knowledge mean score was increased significantly among those who work in medical sectors compared to others unemployed individuals. As well, the knowledge score increased by 2.04 among individuals with comorbidity than healthy ones. Conclusion: Nutritional knowledge score during COVID-19 was 67.03% and the knowledge about the body immunity system and the protective measures against COVID-19, scored a weighted mean of 76.21%. The level of knowledge among all participants did not reflect a satisfactory level of knowledge among the public regard COVID-19 while the level of behaving healthy nutritional habits illustrated that nearly 45% of the participants were practicing unhealthy nutritional behaviors.

Epigenetic Targets and Pathways Linked to SARS-CoV-2 Infection and Pathology.

The scale at which the SARS-CoV-2/COVID-19 pandemic has spread remains enormous. Provided the genetic makeup of the virus and humans is readily available, the quest for knowing the mechanism and epidemiology continues to prevail across the entire scientific community. Several aspects, including immunology, molecular biology, and host-pathogen interaction, are continuously being dug into for preparing the human race for future pandemics. The exact reasons for vast differences in symptoms, pathophysiological implications of COVID-infections, and mortality differences remain elusive. Hence, researchers are also looking beyond traditional genomics, proteomics, and transcriptomics approach, especially entrusting the environmental regulation of the genetic landscape of COVID-human interactions. In line with these questions lies a critical process called epigenetics. The epigenetic perturbations in both host and parasites are a matter of great interest to unravel the disparities in COVID-19 mortalities and pathology. This review provides a deeper insight into current research on the epigenetic landscape of SARS-CoV-2 infection in humans and potential targets for augmenting the ongoing investigation. It also explores the potential targets, pathways, and networks associated with the epigenetic regulation of processes involved in SARS-CoV-2 pathology.

Sugar price behavior and price relationships at the market level before and during COVID-19 pandemic

An efficient commodity market creates a price relationship between two or more markets. This study provides an overview of the behavior of premium granulated sugar prices and the price relationship between market levels. Time series data for the period January 2018-March 2022, are used in this study. Graphical trend analysis;and cointegration analysis with Vector Autoregression (VAR) approach to find research objectives. The research found that the price behavior of premium quality granulated sugar in the traditional market and the modern market is more dynamic than the price at the wholesaler level. The highest price spike occurred in the early period of covid-19, and several months later it returned to stability. Price behavior in traditional markets does not follow movements at other market levels simultaneously but takes some time to reach equilibrium. There is a long-term rionship (cointegration) between prices at the level of traditional markets, modern markets, and wholesalers, which contribute to the balance in the market. Market players need to take a strategic role in maintaining price balance at every level of the market in order to create an efficient and fair market.

Seroprevalence of community-acquired atypical bacterial pneumonia among adult COVID-19 patients from a single center in Al Madinah Al Munawarah, Saudi Arabia: A retrospective cohort study.

OBJECTIVES: To investigate the seroprevalence of the community-acquired bacterial that causes atypical pneumonia among confirmed severe acute respiratory syndrome coronavirus 2 (SARS-COV-2) patients. METHODS: In this cohort study, we retrospectively investigated the seroprevalence of Chlamydia pneumoniae, Mycoplasma pneumoniae, and Legionella pneumophila among randomly selected 189 confirmed COVID-19 patients at their time of hospital presentation via commercial immunoglobulin M (IgM) antibodies against these bacteria. We also carried out quantitative measurements of procalcitonin in patients' serum. RESULTS: The seropositivity for L. pneumophila was 12.6%, with significant distribution among patientsolder than 50 years (χ2 test, p=0.009), while those of M. pneumoniae was 6.3% and C. pneumoniae was 2.1%, indicating an overall co-infection rate of 21% among COVID-19 patients. No significant difference (χ2 test, p=0.628) in the distribution of bacterial co-infections existed between male and female patients. Procalcitonin positivity was confirmed amongst 5% of co-infected patients. CONCLUSION: Our study documented the seroprevalence of community-acquired bacteria co-infection among COVID-19 patients. In this study, procalcitonin was an inconclusive biomarker for non-severe bacterial co-infections among COVID-19 patients. Consideration and proper detection of community-acquired bacterial co-infection may minimize misdiagnosis during the current pandemic and positively reflect disease management and prognosis.

Social anxiety in E-Learning: Scale validation and socio-demographic correlation study.

During the ongoing coronavirus disease 2019 pandemic, over 1.5 billion students worldwide have been deprived of access to traditional learning. This situation has necessitated the use of social distancing-based educational methods; consequently, a tremendous shift towards e-learning has been observed. This study assesses medical students' social anxiety levels in e-learning environments. The study was conducted in two phases. In the first phase, the original Turkish Social Anxiety Scale for E-Learning Environments (SASE) was adapted in English and tested for validity and reliability. This instrument has two subscales: social anxiety in learner-learner interaction and in learner-instructor interaction. In the second stage, we explored the associations of gender, age, and perceived academic performance with medical students' social anxiety levels in e-learning environments. A total of 325 responses were analysed. Consistent with the original version, the adapted scale is a reliable and valid measure of social anxiety in e-learning. Social anxiety in e-learning was related to gender (p = 0.008) and age (p = 0.013). Social anxiety levels were higher in students with lower perceived performance during e-learning compared to students with enhanced performance, but the difference was not significant. The SASE is a useful instrument for evaluating social anxiety in e-learning environments across English educational frameworks. Considering the shift in social interaction environments, efforts are required to reduce medical students' social anxiety levels and enhance learning.

THE IMPACT OF COVID-19 ON CONSUMER BEHAVIOUR AND ONLINE SHOPPING: THE CASE STUDY IN THE DEVELOPING COUNTRY

The main purpose of this study is to assess the impact of the pandemic on online shopping in the case of Kosovo. Cunningham (2019) states that online shopping is an e-commerce activity that involves buying items on a seller’s website through a credit or debit card and delivering the item to your home with online shopping, customers buy items from anywhere in the world through a digital platform. The data used are primary, collected through the online questionnaire and it was distributed using social media Facebook, Instagram, and Gmail to a random sample of 500 respondents from Kosovo. We have concluded that the COVID-19 pandemic has had a positive impact on online shopping because, based on the results we have obtained, online shopping has increased during this period. Online shopping clearly shows that consumers’ attitudes and behaviors have changed rapidly, but the pandemic had not increased their confidence in online shopping. This is especially true for developed countries, where every store has its website from which to buy, and India seems to have adopted this trend very fast compared to Pakistan (Bashir, Mehboob, & Bhatti, 2015). The most demanded products besides food, and hygiene, there was a great demand for clothing, electronic and technological equipment, books, and others. Regardless of how many advantages we can have from online shopping, traditional shopping is still what Kosovar consumers prefer to practice. The paper also suggests some recommendations regarding online shopping in Kosovo. © 2022 The Authors.

Using Machine Learning Approaches to Distinguish COVID-19 from Other Upper Respiratory Tract Infections

COVID-19 has made its first debut in early December 2019 in Wuhan, China. The COVID-19 main symptoms are fever, sore throat, tiredness, and cough, which are quite similar to flu, cold, and allergic rhinitis symptoms. COVID, flu, allergic rhinitis, and cold are all caused by respiratory attacking viruses, and they transmit in the same way by droplets and contacting surfaces and bodies. Thereby, it becomes an urgent need for physicians and healthcare providers to differentiate between each case of the four diseases of cold, flu, allergic rhinitis, and COVID-19. Making an accurate diagnosis in a timely manner, maintain that the patient has the best chance to get to the best clinical outcome. Thus, to meet this aim, the current paper used a publicly available symptoms dataset and applied the Apriori algorithms to extract the most important rules between the symptoms. Furthermore, six classifying algorithms were used to predict the type of disease from its' symptoms, these algorithms namely;Bagging, Random Forest, Extra Trees, Ada Boost, Stochastic gradient boosting, and voting ensemble. The experiments show that the voting ensemble algorithm achieved the highest classification testing accuracy (about 96.22%). As a conclusion, we conclude by demonstrating that using an ensemble technique may greatly increase classification accuracy and make COVID-19 easier to distinguish from other similar diseases. For the medical sector and the healthcare business, our results have significant theoretical and practical consequences. © 2022 IEEE.

A Case Study on Design of Covid-19 Detection and Alerting System Using Machine Learning Techniques

Coronavirus or 2019-nCoV is not, at this point, pandemic but instead endemic, with in excess of 14 million complete cases all throughout the planet getting the infection. At present, there is no particular treatment or solution for Coronavirus, and hence living with the sickness and its manifestations is unavoidable. The connection coefficient examination between different needy and free highlights was done to decide a strength connection between every reliant element and autonomous component of the dataset before building up the models. The database is divided into two parts, 80% of the database is used for model training and the remaining 20% is used for model testing and evaluation. In 2019, early Coronavirus predictions is useful to reduce colossal weight on medical service panels through the diagnosis of coronavirus patients. In the proposed work in this paper, Naive Bayes, Decision tree, Support Vector Machine (SVM) and Artificial neural network (ANN) models are used for forecasting COVID-19 prediction and occurrences.

Being a Mother under the COVID-19 Pandemic Lockdown: Evaluation of Perinatal Anxiety, Prenatal Attachment, and Maternal-Infant Attachment.

OBJECTIVES: The novel coronavirus disease 2019 (COVID-19) pandemic has caused both physical and emotional stress throughout the population due to its worldwide impact. The unknowns about the disease, social isolation, pregnant women's concerns regarding exposure to the COVID-19, inaccessibility to necessary care, and the possibility of harm to their fetus may cause increased psychological distress during the perinatal period. We aimed to evaluate the association between perinatal anxiety, prenatal attachment, and maternal-infant attachment status among women with those who delivered their child in a tertiary-care center with rigid hospital restrictions. STUDY DESIGN: Term pregnant women who experienced the last trimester of their pregnancy during COVID-19 curfews between December 2020 and May 2021 were asked specifically about their concerns during the COVID-19 pandemic and they filled out the Perinatal Anxiety Screening Scale (PASS) and the Prenatal Attachment Inventory (PAI). Those who continued the follow-up within a month of period following the delivery were invited to fill out the Maternal Attachment Inventory (MAI). RESULTS: A total of 600 women completed the survey. While the evaluation of the relationship between participants' mean PAI and MAI scores showed a statistically significant positive correlation between scales (r = 0.124, p = 0.002), mean PAI and PASS scores showed a statistically significant negative correlation between scale scores (r = - 0.137, p = 0.001). CONCLUSION: Examining the factors, affecting the attachment process of pregnant and puerperal women, will guide the improvement of the quality of health services in the COVID-19 pandemic. KEY POINTS: · COVID-19 caused psychological distress, with increased anxiety among perinatal women.. · Elevated levels of anxiety about COVID-19 during pregnancy may lead to insecure attachment.. · Insecure attachment in the prenatal period will negatively contribute to mother - infant attachment..

Identifying key critical model parameters in spreading of COVID-19 pandemic

The spreading of COVID-19 has been considered a worldwide issue, and many global efforts have been suggested. Suggested control strategies to minimize the impact of the disease have effectively worked with computational simulations and mathematical models. Model critical transmissions and sensitivities are also key elements to study this pandemic more widely. This work reviews and discusses susceptible-exposed-infected-recovered (SEIR) model to predict the spreading of this disease. Accordingly, the basic reproduction number and its parameter elasticity are considered at the equilibrium points. Furthermore, the real data of confirmed cases in the Kurdistan region of Iraq are used in estimating model parameters and model validating. Computational model results provide some important model improvements and suggest control strategies. Firstly, the model population states have different model dynamics using the estimated parameters and the initial values. Another result is that almost all model states are sensitive to the model parameters at different levels. Interestingly, contact rate, transition rate from exposed class to the infected class and natural recovery rate are the most important controllable parameters to reduce the basic reproduction number R o , and they become the model critical parameters. More interestingly, computational results for the real data provide that the basic reproduction number in the Kurdistan Region was about 1.28, which is greater than unity. This means that the new coronavirus still has a high potential to spread among individuals, and it will require more interventions and new strategies to control this disease further.

Classifying the Mortality of People with Underlying Health Conditions Affected by COVID-19 Using Machine Learning Techniques

The COVID-19 pandemic has greatly affected populations worldwide and has posed a significant challenge to medical systems. With the constant increase in the number of severe COVID-19 infections, an essential area of research has been directed towards predicting the mortality rate of these patients, in order to make informed medical decisions about the necessary healthcare priorities. Although a large amount of research has attempted to predict the mortality rate of COVID-19 patients, the association between the mortality rate of COVID-19 patients and their underlying health conditions has been given significantly less attention. Meanwhile, patients with underlying conditions often face a worse COVID-19 prognosis. Therefore, the goal of this study was to classify the mortality rate of patients diagnosed with COVID-19, who also suffer from underlying health conditions or comorbidities. To achieve our goal, we applied machine learning (ML) models on a new publicly available dataset, not investigated by any existing literature. The dataset provides detailed information on 582 COVID-19 patients and facilitates a robust forecasting model of the mortality rate. The dataset was analysed using seven ML classifiers, namely, Bagging, J48, logistic regression (LR), random forest (RF), support vector machine (SVM), naïve Bayes (NB), and threshold selector. A comparative analysis was performed across the seven ML techniques, and their performance was assessed based on evaluation parameters including classification accuracy, true-positive rate, and false-positive rate. The best performance was demonstrated by the Bagging algorithm with an accuracy of 83.55% when using all the dataset features. The findings are intended to assist researchers and physicians in the early identification of at-risk COVID-19 patients and to make the appropriate intensive care decisions.