Risk factors associated with SARS-CoV-2 transmission, outbreak duration, and mortality in Fraser Health acute-care settings

Background: Transmission of SARS-CoV-2 in acute-care settings affects patients, healthcare workers, and the already-burdened healthcare system. An analysis of risk factors associated with outbreak severity was conducted to inform prevention strategies. Methods: This study was a cross-sectional analysis of COVID-19 outbreaks at Fraser Health (FH) acute-care sites between March 2020 and March 2021. Outbreak severity measures included COVID-19 attack rate, outbreak duration, and 30-day case mortality. Covariates at patient, outbreak, unit level, and facility level were included (Table 1). Generalized linear models with generalized estimation equations were used for all outcome measures, with outbreak duration and 30-day case mortality using multivariate negative binomial distributions, and attack rate using Gaussian distribution. A P value of .05 indicated statistical significance. Analyseswere performed using SAS version 3.8 software, R version 4.1.0 software, and Stata version 16.0 software. Results: Between March 2020 and March 2021, 54 COVID-19 outbreaks were declared in FH acute-care sites involving 455 SARS-CoV-2–positive patients. The average outbreak duration was 23 days, the average attack rate was 28%, and the average 30-day all-cause mortality per outbreak was 2 deaths. The results of the full models are shown in Table 1. Discussion: We identified an inverse relationship between increased hand hygiene compliance during outbreaks and all 3 severity measures. Paradoxically, hand hygiene rates in the year prior to the pandemic were positively associated with duration and mortality. Increased unit age was also associated with increases in each of the severity measures. Comorbidity total factor was correlated with outbreak attack rate and duration, demonstrating the importance of individual patient characteristics in an outbreak. Conclusions: Our findings highlight the importance of hand hygiene practices during an outbreak. Additionally, it is important to understand the difficulties faced by older facilities, many of which face infrastructural challenges. This study reinforces the need to incorporate infection control standards into healthcare planning and construction.Funding: NoneDisclosures: None

Evaluation of primary care during the COVID-19 pandemic in a Peruvian región

Introducción: La atención primaria es el pilar fundamental de un sistema de salud efectivo;el incumplimiento de los atributos esenciales podría contribuir al colapso de los sistemas de salud en eventuales pandemias. Objetivo: Evaluar el cumplimiento de los atributos de la atención primaria y sus factores asociados, según perspectiva del usuario externo en el contexto de la pandemia por COVID-19, en una región del Perú. Método: Estudio transversal, que incluyó 1064 usuarios externos, seleccionados aleatoriamente. Utilizando la Encuesta se recogieron características sociodemográficas y de salud. El cumplimiento de los atributos de la atención primaria fue valorado con la versión modificada del instrumento PCAT-A10. Se realizó un análisis descriptivo y multivariado mediante modelos lineales generalizados de la familia Poisson para evaluar ciertos factores asociados al incumplimiento de los atributos de la atención primaria. Resultados: De los participantes, el 76,6% perciben que los atributos básicos esenciales se incumplen;asimismo, en el primer contacto (74,7%), continuidad (87,8%), coordinación (95,7%), globalidad (88,3%) y competencia cultural (75,9%). La condición de estudiante (p<0,001), autopercepción de salud regular (p=0,010), adulto de 30 a 59 años (p<0,001) y la condición de usuarios del centro de salud Subtanjalla (p=0,001), Parcona (p<0,001) y Guadalupe (p<0,001), se encuentran asociados a mayor percepción de incumplimiento de los atributos de la atención primaria. Conclusiones: Desde la perspectiva de los usuarios externos los atributos esenciales son incumplidos en los centros de atención primaria;existen factores asociados a mayor probabilidad de percibir que estos atribuidos son incumplidos.Alternate :Introduction: Primary care attention is the fundamental pillar of an effective health system;a failure to comply with its essential attributes could contribute to the collapse of the health systems in the event of pandemics. Objective: To evaluate the compliance of the primary attention's attributes and its associated factors, according to the external user's perspective in the context of the COVID-19 pandemic in a Peruvian region. Method: Cross-sectional study, which included 1064 randomly selected external users. Also, the sociodemographic and health characteristics were collected using the survey. And the compliance of the primary care attributes was valued using the modified version of the PCAT-A10 instrument. Finally, a descriptive and multivariate analysis was performed using generalized linear models of the Poisson family to evaluate certain factors associated with noncompliance with the attributes of primary care. Results: 76.6% of the participants perceive that the essential basic attributes are not met;likewise, in the first contact (74.7%), continuity (87.7%), coordination (95.7%), globality (88.3%) and cultural competence (75.9%). The student condition (p<0,001), self-perception of regular health (p=0.010), adult from 30 to 59 years old (p<0.001), and the condition of users of Subtanjalla (p=0.001), Parcona (p<0.001) and Guadalupe (p<0.001) health centers were associated with a greater perception of noncompliance with the attributes of primary health care. Conclusions: From the external user's perspective the essential attributes are met in primary care centers;there are factors associated with a greater probability of perceiving that these attributes are not met.

Within- and between-person changes in work practice and experiences due to COVID-19: Lessons learned from employees working from home, hybrid working, and working at the office.

Introduction: In response to the requirement of keeping social distance during the COVID-19 outbreak a lot of employees needed to change from a regular office to a home-office at short notice. The aim of the present study is to explore these employees' experiences and evaluate changes in their work situation during the pandemic. Method: A mixed-method design was used with panel data collected twice in an insurance company in Norway. The first dataset was collected in December 2020 (Time 1; N = 558), with a follow up in March 2021 (Time 2; N = 601). Results: Our study indicated that employees' main reasons for working from home were to keep social distance, avoid contagion and protect their loved ones. Flexibility, timesaving and more time with family and friends were also motivators. Most employees reported that they had the necessary technical equipment to work from home and wanted more opportunity to use their home office in the future. General Linear Models (GLM) indicated that work-family balance and workload were the same across age, gender, and worksites. Women and employees working from home reported more fear of being infected by COVID-19 at work. Younger employees reported experiencing less social contact with colleagues than normal during the pandemic, compared to the older employees. Overall, employees working at home were more positive toward digital solutions and digital meetings than those at the office. Repeated measures MANOVA showed that the work motivation and digital competence decreased over time for all worksites. Productivity increased for home-office employees but decreased for the hybrid and work-office employees. Discussion: This paper contributes to knowledge of employees' experiences with different worksite solutions, which will be useful for anticipating employees experience in the future with more hybrid work.

COVID-19 transmission in Africa: estimating the role of meteorological factors.

Climate variables play a critical role in COVID-19's spread. Therefore, this research aims to analyze the effect of average temperature and relative humidity on the propagation of COVID-19 in Africa's first four affected countries (South Africa, Morocco, Tunisia, and Ethiopia). As a result, policymakers should develop effective COVID-19 spread control strategies. For each country, using daily data of confirmed cases and weather variables from May 1, 2020, to April 30, 2021, generalized linear models (Poisson regression) and general linear models were estimated. According to the findings, the rising average temperature causes COVID-19 daily new cases to increase in South Africa and Ethiopia while decreasing in Morocco and Tunisia. However, in Tunisia, the relative humidity and daily new cases of COVID-19 are positively correlated, while in the other three countries, they are negatively associated.

ESG Controversies: A Quantitative and Qualitative Analysis for the Sociopolitical Determinants in EU Firms

Environmental, Social, and Governance (ESG) criteria are novel and exciting tools of corporate disclosure for decision making. Using quantitative and qualitative analyses, the present study examined the key characteristics and trends of ESG controversies in the European market. At the same time, it identified the controversies’ determinants. A bibliometric analysis was the qualitative method employed on the data derived from Scopus using Biblioshiny software, an R package. The quantitative analysis involved an international sample of 2278 companies headquartered in Europe from 2017–2019 being studied using a Generalized Linear Model. The findings of this research highlighted the role of the “S” and the “G” dimensions of the ESG controversies as the most crucial in affecting controversies. Women are under-represented in the business hierarchy, but their natural characteristics such as friendliness and peaceability lead to a low level of illegal business practices. However, independent of gender, executives have personal gains that they want to satisfy. Thus, executives may become involved in unethical practices and harm their colleagues and the business’s reputation. On the other hand, democracy emerged as one of the most disputed factors. Democracy gives people the voice to express themselves and publicly support their ideas without restrictions. Although, the regression results showed that democracy is not always operated as the “pipe of peace” and can affect, to some extent, controversies.

Relaciones entre actividad física y calidad de vida relacionada con la salud en niños y adolescentes durante la distancia social COVID-19

Este estudio tuvo como objetivo verificar la relación entre la actividad física (AF) y los dominios de la calidad de vida relacionada con la salud (QVRS) en niños y jóvenes durante la distancia social COVID-19. Se aplicó un estudio transversal y analítico con enfoque cuantitativo en una muestra de 119 niñas y 121 niños. Se aplicaron cuestionarios y métodos estadísticos. La correlación entre AF y HQOL fue más fuerte en los niños (46,9%) que en las niñas (14,5%), lo que puede explicarse porque existe una relación considerable y más fuerte entre la edad y el grado escolar con HQOL en las niñas. En conclusión, la actividad física se asoció con la QVRS de los niños y adolescentes durante la distancia social COVID-19. Estos hallazgos muestran la importancia de que esta población se mantenga físicamente activa para que los parámetros de salud no se vean afectados durante este período.Alternate :This study aimed to verify the relationship between physical activity (PA) with health-related quality (HQOL) of life domains in children and adolescents during COVID-19 social distancing. A Cross-sectional and analytical study with a quantitative approach in a sample of 119 girls and 121 boys. Questionnaires and statistical methods were applied. The correlation between PA and HQOL was stronger in boys (46.9%) than girls (14.5%), which may be explained because there is a considerable and stronger relationship between age, and the school grade with HQOL in girls. In conclusion, physical activity was associated with the quality of life of children and adolescents during social distance due to the COVID-19. These findings show the importance of this population to remain physically active so that health parameters are not affected during this period.Alternate :Este estudo teve como objetivo verificar a relação da atividade física (AF) com domínios da qualidade de vida relacionada à saúde (QVRS) em crianças e jovens durante o distanciamento social COVID-19. Foi aplicado um estudo transversal e analítico com abordagem quantitativa em uma amostra de 119 meninas e 121 meninos. Questionários e métodos estatísticos foram aplicados. A correlação entre AF e QVRS foi mais forte nos meninos (46,9%) do que nas meninas (14,5%). Isso foi explicado porque há uma relação considerável e mais forte entre idade e ano escolar com QVRS em meninas. Em conclusão, a atividade física se associou à qualidade de vida de crianças e adolescentes durante o distanciamento social COVID-19. Esses achados mostram a importância dessa população se manter fisicamente ativa para que os parâmetros de saúde não sejam afetados nesse período.

Prenatal Telehealth During the Pandemic: Sociodemographic and Clinical Associations

Objectives: Like other areas of care affected by the COVID-19 pandemic, telehealth (both audio and video) was rapidly adopted in the obstetric setting. We performed a retrospective analysis of electronic health record (EHR) data to characterize the sociodemographic and clinical factors associated with telehealth utilization among patients who received prenatal care. Materials and Methods: The study period covered March 23rd, 2020 to July 2nd, 2020, during which time 2,521 patients received prenatal care at a large academic medical center. We applied a generalized logistic regression to measure the relationship between the patients’ sociodemographic factors (in terms of age, race, ethnicity, urbanization level, and insurance type), pregnancy complications (namely, type 2 diabetes, chronic hypertension, and fetal growth restriction), and telehealth usage, as documented in the EHR. Results: During the study period, 2,521 patients had 16,516 prenatal care visits. 938 (37.2%) of the patients participated in at least one of 1,934 virtual prenatal care visits. Prenatal visits were more likely to be conducted through telehealth for patients who were older than 25 years old and lived in rural areas. In addition, patients who were with type 2 diabetes were more likely to use telehealth in their prenatal care (adjusted Odds Ratio (aOR) 7.247 [95% Confidence Interval (95% CI) 4.244 – 12.933]). By contrast, patients from racial and ethnic minority groups were less likely to have a telehealth encounter compared to white or non-Hispanic patients (aOR 0.603 [95% CI 0.465 – 0.778] and aOR 0.663 [95% CI 0.471 – 0.927], respectively). Additionally, patients who were on state-level Medicaid were less likely to use telehealth (aOR 0.495 [95% CI 0.402 – 0.608]). Discussion: Disparities in telehealth use for prenatal care suggest further investigations into access barriers. Hispanic patients who had low English language proficiency may not willing to see doctors via virtual care. Availability of high-speed internet and/or hardware may hold these patients who were insured through state-level Medicaid back due to poverty. Future work is advised to minimize access barriers to telehealth in its implementation. Conclusions: While telehealth expanded prenatal care access for childbearing women during the COVID-19 pandemic, this study suggested that there were non-trivial differences in the demographics of patients who utilized such settings.

Unraveling the dynamic impacts of COVID-19 on metro ridership: An empirical analysis of Beijing and Shanghai, China.

The outbreak of coronavirus disease 2019 (COVID-19) has had severely disruptive impacts on transportation, particularly public transit. To understand metro ridership changes due to the COVID-19 pandemic, this study conducts an in-depth analysis of two Chinese megacities from January 1, 2020, to August 31, 2021. Generalized linear models are used to explore the impact of the COVID-19 pandemic on metro ridership. The dependent variable is the relative change in metro ridership, and the independent variables include COVID-19, socio-economic, and weather variables. The results suggested the following: (1) The COVID-19 pandemic has a significantly negative effect on the relative change in metro ridership, and the number of cumulative confirmed COVID-19 cases within 14 days performs better in regression models, which reflects the existence of the time lag effect of the COVID-19 pandemic. (2) Emergency responses are negatively associated with metro system usage according to severity and duration. (3) The marginal effects of the COVID-19 variables and emergency responses are larger on weekdays than on weekends. (4) The number of imported confirmed COVID-19 cases only significantly affects metro ridership in the weekend and new-normal-phase models for Beijing. In addition, the daily gross domestic product and weather variables are significantly associated with metro ridership. These findings can aid in understanding the usage of metro systems in the outbreak and new-normal phases and provide transit operators with guidance to adjust services.

Cost and Length of Stay for Department of Defense Hospitalizations Attributed to COVID-for Adults with Diabetes

Healthcare costs in 2020 increased 9.7% from the prior year reaching $4.1 trillion dollars. This increase is considered largely due to the COVID-pandemic. Since adults with diabetes were at increased risk of poor outcomes from COVID-19, the objective of this study was to investigate cost and length of stay for Department of Defense (DoD) hospitalizations attributed to COVID-for adults with diabetes. Data on hospitalizations within military facilities between 2020-2021 for patients with diabetes were investigated. 6,265 hospitalizations occurred at DoD facilities, of which 7.2% (n=458) were attributed to COVID-19. Generalized linear models using a gamma distribution for total cost and Poisson distribution for length of stay were run to investigate outcomes adjusting for age, sex, race/ethnicity, active duty status, service category (Army, Coast Guard, Marine, Air Force, or Navy) , and comorbidity count. In adults with diabetes hospitalized at military facilities, those with COVID-cost over $8,500 more than those without COVID- (8792.98, 95%CI 5850.38,11735.57) after adjustment. There were no significant differences by sex or race/ethnicity, however, active duty hospitalizations cost on average $2,200 more than not active duty (2239.26, 95%CI 738.72,3739.81) . Length of stay was over 2 days longer for COVID-hospitalizations (2.20, 95%CI 1.98,2.42) after adjustment. There were no differences by sex, however African Americans and Asian/Pacific Islanders had slightly longer lengths of stay (AA: 0.37, 95%CI 0.26,0.48;A/PI: 0.26, 95%CI 0.05,0.46) , as did those on active duty (0.24, 95%CI 0.08,0.40) . Total costs for hospitalizations attributed to COVID-were higher and length of stay longer for adults with diabetes at military facilities. Further work is needed to understand long term consequences of COVID-on cost and utilization for adults with diabetes.

ANALYZE THE SPATIAL DISTRIBUTION OF DELIVERY MOTORCYCLE CRASHES AND IDENTIFY THE RELATED FACTORS

During COVID-19, the suspension of the dine-in option at restaurants had significantly increased online food delivery crashes in Taiwan. Nevertheless, the majority of current studies remain focused on the common motorcycle, which has distinct driving habits and routes than a delivery motorcycle. Even though some recent studies identified the variables contributing to delivery motorcycle crashes, they still restricted in defining crash severity model and did not account for spatial dependences. In this study, two different models were used in this study: the generalized linear model (GLM), and the geographically weighted negative binomial model (GWNBR) to estimate crash frequency in a non-stationary pattern. In 2020, there were 2314 delivery motorcycle crashes in Taipei, according to the study area. Besides that, the point of interests data from 456 villages in Taipei city was considered as related crash factors for further analysis. According to the results, GWNBR showed the best performance in terms of log-likelihood, Akaike Information Criterion (AIC), and Root Mean Square Error (RMSE). Furthermore, this research reveals that commercial areas and bus stations had a significant impact on delivery motorcycle crashes. As per the coefficient distribution, the effect is exacerbated in rural areas where the traffic policy is still a major concern. As the popularity of delivery food services grows, this topic will become even more important in the future.

Influence of the sociodemographic profile of hunters on the knowledge and use of faunistic resources

Background Hunting wild animals is essential for nutrition, clothing, predator control and disease treatment. As part of a system based on food choices and uses, it is influenced by ecological, economic and sociocultural patterns. In this context, the aim is to identify the game fauna of interest in the Brazilian semiarid region;indicate the methods, uses, patterns of choices and cultural importance of the fauna and identify which sociodemographic variables influence the knowledge and use of faunal resources. Methods Information on hunting and fauna use was obtained through semi-structured interviews, complemented with free interviews and informal conversations. The cultural importance of the species was calculated through the current use value. The generalized linear model was created to verify whether the sociodemographic profile of hunters influences the knowledge and use of game species. Results The results showed a representativeness of 56 species. The group of birds was the most representative in terms of taxonomic richness (48.2%), followed by the group of mammals (26.8%), reptiles (21.4%) and amphibians (3.6%). The animals mentioned are used for food, trade, control hunting (slaughter of animals considered invaders of property or harmful to humans), pets, zootherapy and ornamentation. Sociodemographic variables shaped the knowledge of faunal resources, in which the age of hunters showed a negative correlation with the number of known species. Conclusions The meaning and forms of use attributed to each species depend on ecological, economic and sociocultural factors, which dictate the relationship between human communities and natural resources. Socioeconomic variables shape hunting patterns in all its aspects, whether in perception that hunters have of the resources, forms of use and utilization of hunting strategies.

Machine Learning in Healthcare Communication

DefinitionMachine learning (ML) is a study of computer algorithms for automation through experience. ML is a subset of artificial intelligence (AI) that develops computer systems, which are able to perform tasks generally having need of human intelligence. While healthcare communication is important in order to tactfully translate and disseminate information to support and educate patients and public, ML is proven applicable in healthcare with the ability for complex dialogue management and conversational flexibility. In this topical review, we will highlight how the application of ML/AI in healthcare communication is able to benefit humans. This includes chatbots for the COVID-19 health education, cancer therapy, and medical imaging.

Generalized Additive Models to Capture the Death Rates in Canada COVID-19

To capture the death rates and strong weekly, biweekly and probably monthly patterns in the Canada COVID-19, we utilize the generalized additive models in the absence of direct statistically based measurement of infection rates. By examining the death rates of Canada in general and Quebec, Ontario and Alberta in particular, that there are substantial overdispersion relative to the Poisson so that the negative binomial distribution is an appropriate choice for the analysis. Generalized additive models (GAMs) are one of the main modeling tools for data analysis. © 2022, Springer Nature Switzerland AG.

Solutions to problems of nonexistence of parameter estimates and sparse data bias in Poisson regression.

Poisson regression can be challenging with sparse data, in particular with certain data constellations where maximum likelihood estimates of regression coefficients do not exist. This paper provides a comprehensive evaluation of methods that give finite regression coefficients when maximum likelihood estimates do not exist, including Firth's general approach to bias reduction, exact conditional Poisson regression, and a Bayesian estimator using weakly informative priors that can be obtained via data augmentation. Furthermore, we include in our evaluation a new proposal for a modification of Firth's approach, improving its performance for predictions without compromising its attractive bias-correcting properties for regression coefficients. We illustrate the issue of the nonexistence of maximum likelihood estimates with a dataset arising from the recent outbreak of COVID-19 and an example from implant dentistry. All methods are evaluated in a comprehensive simulation study under a variety of realistic scenarios, evaluating their performance for prediction and estimation. To conclude, while exact conditional Poisson regression may be confined to small data sets only, both the modification of Firth's approach and the Bayesian estimator are universally applicable solutions with attractive properties for prediction and estimation. While the Bayesian method needs specification of prior variances for the regression coefficients, the modified Firth approach does not require any user input.

Modeling of daily confirmed Saudi COVID-19 cases using inverted exponential regression.

The coronavirus disease 2019 (COVID-19) pandemic caused by the coronavirus strain has had massive global impact, and has interrupted economic and social activity. The daily confirmed COVID-19 cases in Saudi Arabia are shown to be affected by some explanatory variables that are recorded daily: recovered COVID-19 cases, critical cases, daily active cases, tests per million, curfew hours, maximal temperatures, maximal relative humidity, maximal wind speed, and maximal pressure. Restrictions applied by the Saudi Arabia government due to the COVID-19 outbreak, from the suspension of Umrah and flights, and the lockdown of some cities with a curfew are based on information about COVID-15. The aim of the paper is to propose some predictive regression models similar to generalized linear models (GLMs) for fitting COVID-19 data in Saudi Arabia to analyze, forecast, and extract meaningful information that helps decision makers. In this direction, we propose some regression models on the basis of inverted exponential distribution (IE-Reg), Bayesian (BReg) and empirical Bayesian regression (EBReg) models for use in conjunction with inverted exponential distribution (IE-BReg and IE-EBReg). In all approaches, we use the logarithm (log) link function, gamma prior and two loss functions in the Bayesian approach, namely, the zero-one and LINEX loss functions. To deal with the outliers in the proposed models, we apply Huber and Tukey's bisquare (biweight) functions. In addition, we use the iteratively reweighted least squares (IRLS) algorithm to estimate Bayesian regression coefficients. Further, we compare IE-Reg, IE-BReg, and IE-EBReg using some criteria, such as Akaike's information criterion (AIC), Bayesian information criterion (BIC), deviance (D), and mean squared error (MSE). Finally, we apply the collected data of the daily confirmed from March 23 - June 21, 2020 with the corresponding explanatory variables to the theoretical findings. IE-EBReg shows good model for the COVID-19 cases in Saudi Arabia compared with the other models.

Generalized k -means in GLMs with applications to the outbreak of COVID-19 in the United States.

Generalized k -means can be combined with any similarity or dissimilarity measure for clustering. Using the well known likelihood ratio or F -statistic as the dissimilarity measure, a generalized k -means method is proposed to group generalized linear models (GLMs) for exponential family distributions. Given the number of clusters k , the proposed method is established by the uniform most powerful unbiased (UMPU) test statistic for the comparison between GLMs. If k is unknown, then the proposed method can be combined with generalized liformation criterion (GIC) to automatically select the best k for clustering. Both AIC and BIC are investigated as special cases of GIC. Theoretical and simulation results show that the number of clusters can be correctly identified by BIC but not AIC. The proposed method is applied to the state-level daily COVID-19 data in the United States, and it identifies 6 clusters. A further study shows that the models between clusters are significantly different from each other, which confirms the result with 6 clusters.

Explainable Machine Learning for Early Assessment of COVID-19 Risk Prediction in Emergency Departments.

Between January and October of 2020, the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus has infected more than 34 million persons in a worldwide pandemic leading to over one million deaths worldwide (data from the Johns Hopkins University). Since the virus begun to spread, emergency departments were busy with COVID-19 patients for whom a quick decision regarding in- or outpatient care was required. The virus can cause characteristic abnormalities in chest radiographs (CXR), but, due to the low sensitivity of CXR, additional variables and criteria are needed to accurately predict risk. Here, we describe a computerized system primarily aimed at extracting the most relevant radiological, clinical, and laboratory variables for improving patient risk prediction, and secondarily at presenting an explainable machine learning system, which may provide simple decision criteria to be used by clinicians as a support for assessing patient risk. To achieve robust and reliable variable selection, Boruta and Random Forest (RF) are combined in a 10-fold cross-validation scheme to produce a variable importance estimate not biased by the presence of surrogates. The most important variables are then selected to train a RF classifier, whose rules may be extracted, simplified, and pruned to finally build an associative tree, particularly appealing for its simplicity. Results show that the radiological score automatically computed through a neural network is highly correlated with the score computed by radiologists, and that laboratory variables, together with the number of comorbidities, aid risk prediction. The prediction performance of our approach was compared to that that of generalized linear models and shown to be effective and robust. The proposed machine learning-based computational system can be easily deployed and used in emergency departments for rapid and accurate risk prediction in COVID-19 patients.