Identification Symptoms and Underlying Diseases Related to COVID-19 And Prediction of Death Status Using Artificial Neural Network and Logistic Regression: A Data Mining Approach.

Background and Objectives: Due to the high prevalence of COVID-19 disease and its high mortality rate, it is necessary to identify the symptoms, demographic information and underlying diseases that effectively predict COVID-19 death. Therefore, in this study, we aimed to predict the mortality behavior due to COVID-19 in Khorasan Razavi province. Method(s): This study collected data from 51, 460 patients admitted to the hospitals of Khorasan Razavi province from 25 March 2017 to 12 September 2014. Logistic regression and Neural network methods, including machine learning methods, were used to identify survivors and non-survivors caused by COVID-19. Result(s): Decreased consciousness, cough, PO2 level less than 93%, age, cancer, chronic kidney diseases, fever, headache, smoking status, and chronic blood diseases are the most important predictors of death. The accuracy of the artificial neural network model was 89.90% in the test phase. Also, the sensitivity, specificity and area under the rock curve in this model are equal to 76.14%, 91.99% and 77.65%, respectively. Conclusion(s): Our findings highlight the importance of some demographic information, underlying diseases, and clinical signs in predicting survivors and non-survivors of COVID-19. Also, the neural network model provided high accuracy in prediction. However, medical research in this field will lead to complementary results by using other methods of machine learning and their high power.Copyright © 2022 The Authors.

Evaluating the effect of gargling with hydrogen peroxide and povidone-iodine on salivary viral load of SARS-CoV-2: A pilot randomized clinical trial.

Background and Aim: This study evaluates the salivary viral load of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) in hospitalized patients and outpatients before and after gargling with 1% hydrogen peroxide and 0.25% povidone-iodine in comparison with normal saline. Patients and Methods: This clinical trial was conducted on 120 participants with laboratory-confirmed coronavirus disease 2019 (COVID-19) in two groups: outpatients (n = 60) and hospitalized patients (n = 60). In each group, the patients were randomly divided into three subgroups of 20 based on their given mouthwash for gargling (hydrogen peroxide, povidone-iodine, or normal saline). Two saliva samples were taken from each patient: the first one before gargling and the second one 10 minutes after gargling 10 ml of the respected mouthwashes for 30 seconds. The TaqMan real-time polymerase chain reaction (PCR) amplification of SARS-CoV-2 was used to measure the viral load. Results: Saliva samples from 46% of patients were positive for coronavirus before gargling the mouthwashes. The percentage of patients with an initial positive saliva sample was significantly higher in the outpatient group (83.3%) than in the hospitalized group (5.4%) (P = 0.01). According to the findings, gargling any mouthwash similar to saline did not reduce the viral load (P > 0.05). Conclusion: The saliva of COVID-19 patients in the initial stage of the disease was more likely to contain SARS-CoV-2 than the saliva of the hospitalized patients. Gargling hydrogen peroxide or povidone-iodine did not reduce the salivary SARS-CoV-2 viral load.

Identification Symptoms and Underlying Diseases Related to COVID-19 And Prediction of Death Status Using Artificial Neural Network and Logistic Regression: A Data Mining Approach

Background and Objectives: Due to the high prevalence of COVID-19 disease and its high mortality rate, it is necessary to identify the symptoms, demographic information and underlying diseases that effectively predict COVID-19 death. Therefore, in this study, we aimed to predict the mortality behavior due to COVID-19 in Khorasan Razavi province. Method(s): This study collected data from 51, 460 patients admitted to the hospitals of Khorasan Razavi province from 25 March 2017 to 12 September 2014. Logistic regression and Neural network methods, including machine learning methods, were used to identify survivors and non-survivors caused by COVID-19. Result(s): Decreased consciousness, cough, PO2 level less than 93%, age, cancer, chronic kidney diseases, fever, headache, smoking status, and chronic blood diseases are the most important predictors of death. The accuracy of the artificial neural network model was 89.90% in the test phase. Also, the sensitivity, specificity and area under the rock curve in this model are equal to 76.14%, 91.99% and 77.65%, respectively. Conclusion(s): Our findings highlight the importance of some demographic information, underlying diseases, and clinical signs in predicting survivors and non-survivors of COVID-19. Also, the neural network model provided high accuracy in prediction. However, medical research in this field will lead to complementary results by using other methods of machine learning and their high power.Copyright © 2022 The Authors.