Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 4 de 4
Filter
1.
Iranian Journal of Epidemiology ; 18(3):244-254, 2022.
Article in Persian | EMBASE | ID: covidwho-20243573

ABSTRACT

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.

2.
Iranian Journal of Epidemiology ; 18(3):244-254, 2022.
Article in Persian | EMBASE | ID: covidwho-2326574

ABSTRACT

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.

3.
Turkiye Klinikleri Journal of Medical Sciences ; 43(1):29-39, 2023.
Article in English | EMBASE | ID: covidwho-2280796

ABSTRACT

Objective: The coronavirus disease-2019 (COVID-19), caused by the novel severe acute respiratory syndrome coronavirus 2, started in Wuhan, China, and was recognized as a pandemic by the World Health Organization. In Iran, the first confirmed COVID-19 case was officially reported on February 19. The aim of this study was to investigate the epidemiological and clinical characteristics, and comorbid conditions, and determine risk factors for the mortality of COVID-19 patients as well as provide a comparison of the epidemiological features between the 3 waves of COVID-19 in the North-East of Iran from January 21, 2020, to March 20, 2021. Material(s) and Method(s): The current retrospective epidemiological population-based study was conducted on COVID-19 patients who were admitted to the hospitals affiliated to the Mashhad University of Medical Sciences in Razavi-Khorasan province, Iran. The data were extracted from the Medical Care Monitoring System of the Mashhad University of Medical Sciences. Result(s): In total, 43.6% of subjects had at least one coexisting underlying medical condition. The most common comorbidities were hypertension, diabetes, and cardiovascular diseases with the prevalence of 19.7, 15.1, and 13.3%;respectively. The overall case fatality rate was 15.0%, following a median of 4 days [interquartile range (IQR) 1-10] of hospitalization. The mean+/-SD and the median (IQR) of age in expired subjects were 67.40+/-18.27 and 70 (59-81) years;respectively. Conclusion(s): Our results demonstrated that age >60, male sex, loss of consciousness, respiratory distress, having at least one comorbidity, and diabetes were mortality risk factors among COVID-19 patients.Copyright © 2023 by Turkiye Klinikleri.

4.
Front Digit Health ; 4: 814248, 2022.
Article in English | MEDLINE | ID: covidwho-1809364

ABSTRACT

Nearly all young people use the internet daily. Many youth with mental health concerns, especially since the Covid-19 pandemic, are using this route to seek help, whether through digital mental health treatment, illness prevention tools, or supports for mental wellbeing. Videogames also have wide appeal among young people, including those who receive mental health services. This review identifies the literature on videogame interventions for young people, ages 12-29, and maps the data on game use by those with mental health and substance use problems, focusing on evidence for the capacity of games to support treatment in youth mental health services; how stakeholders are involved in developing or evaluating games; and any potential harms and ethical remedies identified. A systematic scoping review methodology was used to identify and assess relevant studies. A search of multiple databases identified a total of 8,733 articles. They were screened, and 49 studies testing 32 digital games retained. An adapted stepped care model, including four levels, or steps, based on illness manifestation and severity, was used as a conceptual framework for organizing target populations, mental health conditions and corresponding digital games, and study results. The 49 selected studies included: 10 studies (20.4%) on mental health promotion/prevention or education for undiagnosed youth (Step 0: 7 games); 6 studies (12.2%) on at-risk groups or suspected mental problems (Step 1: 5 games); 24 studies (49.0%) on mild to moderate mental conditions (Steps 2-3: 16 games); and 9 studies (18.4%) focused on severe and complex mental conditions (Step 4: 7 games). Two interventions were played by youth at more than one level of illness severity: the SPARX game (Steps 1, 2-3, 4) and Dojo (Steps 2-3 and 4), bringing the total game count to 35 with these repetitions. Findings support the potential integration of digital games in youth services based on study outcomes, user satisfaction, relatively high program retention rates and the potential usefulness of most games for mental health treatment or promotion/prevention. Most studies included stakeholder feedback, and involvement ratings were very high for seven games. Potential harms were not addressed in this body of research. This review provides an important initial repository and evaluation of videogames for use in clinical settings concerned with youth mental health.

SELECTION OF CITATIONS
SEARCH DETAIL