Investigation on the risk factores for mortality of patients with COVID-19 and prioritization these factores using neural network in some southern cities of Iran

Background: The coronavirus disease 2019 (COVID-19 the seventh human coronavirus) was discovered in Wuhan, Hubei province of China, in January 2020. COVID-19 virus caused six million deads in the world to date and cussed infection of more than seven million of cases in Iran(1). This infectious disease caused by the SARS-CoV-2 virus. This virus was contagious and fast-spread. Despite the aquarantine politics, SARS-CoV-2 virus caused many permanent economic and health damages in most countries. Coronaviruses are positive-sense, single-stranded enveloped RNA viruses with helical capsids that infect a wide range of hosts including humans, bats, other mammals, and birds. Coronaviruses are within the Nidovirales order, Coronaviridae family, Coronovirinae subfamily and are further subclassified into four genera: alpha, beta, delta, and gamma coronaviruses(2, 3). Alpha and beta coronaviruses are known to infect humans. SARS-COV-2 virus abilities including: short incubation period, high number of mortality, widespread transmission methods, asymptomatic infection and affecting on most vital organs (heart, brain, lungs and …) have attracted the attention of the health systems and has caused health systems to neglect other diseases, especially chronic and non-communicable diseases. Therefore, the incidence and prevalence of diseases and their prioritization in countries may change in the future(4, 5). From the beginning of COVID-19 pandemic, some symptoms and risk-factors have been introduced to the world as the increase of morbidity and mortality. Studies have shown that having any kind of underlying diseases and risk factors will be effective in the COVID-19 disease severity and mortality. Some of these important risk factors are included: hypertension, chronic kidney disease, age, obesity, gender, diabetes, obstructive pulmonary diseases, lung diseases, cancer, cardiovascular diseases and liver disease. Also, each risk factors have different impact in different geographic areas (6-9). Some factors, such as different viral load kinetics in each individual person, epidemiological history, immune response and therapeutic or pharmacological effects have major impacts on the laboratory diagnostic results (10-13). Due to the successive mutations of the SARS-CoV-2 virus and the high incidence disease, it seems that the vaccination alone cannot prevent the COVID-19. Also, The WHO (World Health Organization) has warned about the application of vaccination as the only pandemic control protocol. Since the beginning of the COVID-19 epidemic and the vaccination, the prevalence of morbidity and mortality are still public health concerns in the world (14). Recognizing of the risk-factors and symptoms on COVID-19 in different geographic regions can be a useful tool to prevent the mortality. Understanding risk factors can help the world to control the pandemic period of coronaviruses and similar situations in the future. Therefore, the aim of this study was to determine the risk-factors of mortality of COVID_19 patients in three cities of Khuzestan province, Iran. Method: This research was an analytical cross-sectional study. Some details of 27963 of COVID-19 patients including individual characteristics, clinical symptoms and underlying diseases were gathered from hospitals in Abadan, Shadegan and Khorramshahr cities in Khuzestan province, Iran, from 20 February 2020 to November 2020. All under study population was previously investigated by the medical examinations and laboratory methods. This under study population was categorized into three groups including: outpatients, hospitalized and dead patients. Hospitalized patients were admitted in general or ICU (Intensive Care Unit) sector. Obtained database of COVID-19 patients was analyzed by SPSS (version 22) with regression, logistic model (univariable and multivariable logistic regression models) with 95 percent confidence level. Also, a neural network was used for prioritizing of significant risk factors for mortality. Multiple logistic regression model and neural network were evaluated for Goodness of Fit at the end of the analysis. In this study, the principle of anonymity and preservation of patient's personal information was considered. Result: The mean of age was 40 years. The sex ratio was higher for men. That ratio for dead patients were 63 years (62.7597-64.9854). The number of hospitalizations and deaths was ocured in May-July 2020 and the most number of deaths reports was belonged to Abadan city. The most prevalent symptoms were observed as fever, cough, hard breath and sickness which were observed more within dead patients. 4.8 percent of patients had no symptoms. Prevalent underlying diseases in under study population were diabetes, hypertension and blood diseases. Risk factors for mortality in the multivariable logistic regression model were age, diabetes, cardiovascular diseases, blood diseases, respiratory diseases, neurological diseases and cancers. Some variables such as gender, thyroid diseases and diseases related to blood lipid, were removed from the multivariable logistic regression model by univariable logistic regression model in 0.2 confidence level because they had no statistical significance for entering the multiple regression model. Age was most important risk factor for mortality, according to neural network analysis. Other important risk factors were neurological diseases, blood diseases, respiratory diseases, cardiovascular diseases, diabetes and cancers respectively. The odds ratio of mortality increases with increasing number of underlying diseases among COVID-19 patients and the presence of at least one risk factor increases the odds of mortality approximately 8.3 times. Some variables such as hypertension, kidney diseases, Immunodeficiency and obesity were not recognized as risk factors for mortality in the multivariable logistic regression model. Conclusion: This study investigated the effective risk factors for mortality among patients with COVID-19 in southern three cities including Abadan, Khorramshahr and Shadegan of Khuzestan province, Iran. According to risk factors of mortality and prioritizing in neural network, we recommend that after attention to age as the most important risk factor for mortality, COVID-19 patients with a history of neural diseases and blood diseases should receive public health care services more than the others till the end of COVID-19 pandemic period. Although, antigenic mutations of COVID-19 virus have reduced the effectiveness of recent vaccines. However, risk factors for mortality of patients with COVID-19 as the most important level of disease prevention need more attention from health politicians. Understanding risk factors of mortality, can useful for researchers in the future and any similar epidemic or pandemic of coronaviruses. This research was part of a project registered in Iran University of Medical Sciences under code number of IR.IUMS.REC.1399.1005 and collaborations with Abadan University of Medical Sciences and Health Services.