ABSTRACT
Background: The new coronavirus has been spreading since the beginning of 2020, and many efforts have been made to develop vaccines to help patients recover. It is now clear that the world needs a rapid solution to curb the spread of COVID-19 worldwide with non-clinical approaches such as artificial intelligence techniques. These approaches can be effective in reducing the burden on the health care system to provide the best possible way to diagnose the COVID-19 epidemic. This study was conducted to use Machine Learning (ML) algorithms for the early detection of COVID-19 in patients. Methods: This retrospective study used data from hospitals affiliated with Shiraz University of Medical Sciences in Iran. This dataset was collected in the period March to October 2020 andcontained 10055 cases with 63 features. We selected and compared six algorithms: C4.5, support vector machine (SVM), Naive Bayes, logistic Regression (LR), Random Forest, and K-Nearest Neighbor algorithm using Rapid Miner software. The performance of algorithms was measured using evaluation metrics, such as precision, recall, accuracy, and f-measure. Results: The results of the study show that among the various used classification methods in the diagnosis of coronavirus, SVM (93.41% accuracy) and C4.5 (91.87% accuracy) achieved the highest performance. According to the C4.5 decision tree, "contact with a person who has COVID-19" was considered the most important diagnostic criterion based on the Gini index. Conclusion: We found that ML approaches enable a reasonable level of accuracy in the diagnosis of COVID-19.
ABSTRACT
Background and Aims: The COVID-19 pandemic has changed people's lifestyles as well as the way healthcare services are delivered. Undoubtedly, the difficulties associated with COVID-19 infection and rehabilitation and those associated with quarantine and viral preventive efforts may exacerbate the need for virtual reality to be used as a part of a complete rehabilitation strategy for these individuals. Thus, the present research aimed to evaluate the potential uses of virtual reality for the rehabilitation of individuals suffering from COVID-19. Methods: From 2019 to March 1, 2022, a systematic search was conducted in PubMed, Cochran Library, Scopus, Science Direct, ProQuest, and Web of Science databases. The papers were selected based on search terms and those that discussed the use of virtual reality in the rehabilitation of COVID-19 patients were reviewed. Each step of the study was reviewed by two authors. Results: A total of 699 papers were found during the first search. Three papers were chosen for further investigation after a thorough evaluation of the publications' titles, abstracts, and full texts. Cross-sectional studies, randomized controlled clinical trials, and case reports comprised 33%, 33%, and 33% of the publications, respectively. Based on the results, people suffering from COVID-19 were the focus of two papers (66%) that employed immersion virtual reality for cognitive rehabilitation, whereas one study (33%) used non-immersive virtual reality for physical rehabilitation. In two papers (66%), virtual reality was also offered to patients in the form of a game. Conclusion: According to the results of the present research, virtual reality games may enhance functional and cognitive consequences, contentment levels among patients, and their ability to take charge of their own health care. In light of the obstacles faced by COVID-19 patients, alterations in the delivery of healthcare, and the significance of rehabilitation in this group during quarantine, new techniques have been considered for these patients to maintain treatment, return to regular life, and enhance their standard of life.
ABSTRACT
Background: The new coronavirus has been spreading since the beginning of 2020, and many efforts have been made to develop vaccines to help patients recover. It is now clear that the world needs a rapid solution to curb the spread of COVID-19 worldwide with non-clinical approaches such as artificial intelligence techniques. These approaches can be effective in reducing the burden on the health care system to provide the best possible way to diagnose the COVID-19 epidemic. This study was conducted to use Machine Learning (ML) algorithms for the early detection of COVID-19 in patients. Methods: This retrospective study used data from hospitals affiliated with Shiraz University of Medical Sciences in Iran. This dataset was collected in the period March to October 2020 andcontained 10055 cases with 63 features. We selected and compared six algorithms: C4.5, support vector machine (SVM), Naive Bayes, logistic Regression (LR), Random Forest, and K-Nearest Neighbor algorithm using Rapid Miner software. The performance of algorithms was measured using evaluation metrics, such as precision, recall, accuracy, and f-measure. Results: The results of the study show that among the various used classification methods in the diagnosis of coronavirus, SVM (93.41% accuracy) and C4.5 (91.87% accuracy) achieved the highest performance. According to the C4.5 decision tree, "contact with a person who has COVID-19" was considered the most important diagnostic criterion based on the Gini index. Conclusion: We found that ML approaches enable a reasonable level of accuracy in the diagnosis of COVID-19.
ABSTRACT
Background and Aim: Death certificate (DC) data provides a basis for public health policies and statistics and contributes to the evaluation of a pandemic's evolution. This study aimed to evaluate the quality of the COVID-19-related DC completion. Methods: A descriptive-analytical study was conducted to review a total of 339 medical records and DCs issued for COVID-19 cases from February 20 to September 21, 2020. A univariate analysis (χ 2 as an unadjusted analysis) was performed, and multiple logistic regression models (odd ratio [OR] and 95% confidence interval [CI] as adjusted analyses) were used to evaluate the associations between variables. Results: Errors in DCs were classified as major and minor. All of the 339 examined DCs were erroneous; more than half of DCs (57.8%) had at least one major error; all of them had at least one minor error. Improper sequencing (49.3%), unacceptable underlying causes of death (UCOD) (33.3%), recording more than one cause per line (20.1%), listing general conditions instead of specific terms (11.2%), illegible handwriting (8.3%), competing causes (6.2%), and mechanisms (3.8%) were most common major errors, respectively. Absence of time interval (100%), listing mechanism allying with UCOD (51.6%), using abbreviations (45.4%), missing major comorbidities (16.5%), and listing major comorbidities in part I (16.5%) were most common minor errors, respectively. Conclusion: The rate of both major and minor errors was high. Using automated tools for recording and selecting death cause(s), promoting certifiers' skills on DC completion, and applying quality control mechanisms in DC documentation can improve death data and statistics.
ABSTRACT
Background and Aim Death certificate (DC) data provides a basis for public health policies and statistics and contributes to the evaluation of a pandemic's evolution. This study aimed to evaluate the quality of the COVID‐19‐related DC completion. Methods A descriptive‐analytical study was conducted to review a total of 339 medical records and DCs issued for COVID‐19 cases from February 20 to September 21, 2020. A univariate analysis (χ2 as an unadjusted analysis) was performed, and multiple logistic regression models (odd ratio [OR] and 95% confidence interval [CI] as adjusted analyses) were used to evaluate the associations between variables. Results Errors in DCs were classified as major and minor. All of the 339 examined DCs were erroneous;more than half of DCs (57.8%) had at least one major error;all of them had at least one minor error. Improper sequencing (49.3%), unacceptable underlying causes of death (UCOD) (33.3%), recording more than one cause per line (20.1%), listing general conditions instead of specific terms (11.2%), illegible handwriting (8.3%), competing causes (6.2%), and mechanisms (3.8%) were most common major errors, respectively. Absence of time interval (100%), listing mechanism allying with UCOD (51.6%), using abbreviations (45.4%), missing major comorbidities (16.5%), and listing major comorbidities in part I (16.5%) were most common minor errors, respectively. Conclusion The rate of both major and minor errors was high. Using automated tools for recording and selecting death cause(s), promoting certifiers' skills on DC completion, and applying quality control mechanisms in DC documentation can improve death data and statistics.
ABSTRACT
The present study is conducted to determine the status of e-learning, student satisfaction and the relationship between these two variables in Zahedan University of Medical Sciences (ZAUMS). According to a descriptive study, there was just a significant difference between the mean score of e-Learning experience and student satisfaction, and a positive correlation between the education level and student satisfaction. Also, there was a positive correlation between all variables of e-learning and student satisfaction The findings showed that the more capable learners were outcome of better educational content, stronger e-learning infrastructure, better support and assessment of e-learning quality, which, in turn, resulted in the greater the students' satisfaction. As a result, the experiences from the evaluation of e-learning in the Covid-19 pandemic period may be regarded a good guide in improving the course during the Covid-19 pandemic, and also it can be considered a key factor in providing educations in the post-Covid-19 period.