Introduction: Needless to say that correct and real-time detection and effective prognosis of the COVID-19 are necessary to deliver the best possible care for patients and, accordingly, diminish the pressure on the healthcare industries. Hence our paper aims to present an intelligent algorithm for selecting the best features from the dataset and developing Machine Learning(ML) based models to predict the COVID-19 and finally opted for the best-performing algorithm. Methods: In this developmental study, the clinical data of 1703 COVID-19 and non-COVID-19 patients Using a single-center registry from February 9, 2020, to December 20, 2020, were used. The Minimum Redundancy Maximum Relevance (mRMR) feature selection algorithm identified the most relevant variables. Then, chosen features feed into the several data mining methods, including K-Nearest Neighbors, AdaBoost Classifier, Decision Tree, HistGradient Boosting Classifier, and Support Vector Machine. A 10-fold cross-validation method and six performance evaluation metrics were used to evaluate and compare these implemented algorithms, and finally, the best model was implemented. Results: Out of the 34 included features, 11 variables were selected as the essential features. The results of using ML algorithms indicated that the best performance belongs to the AdaBoost classifier with mean accuracy = 92.9%, mean specificity = 89.3%, mean sensitivity = 94.2%, mean F-measure = 91.6 %, mean KAPA = 94.3% and mean ROC = 92.1 %. Conclusion: The empirical results reveal that the Adaboost model yielded higher performance than other classification models and developed our Clinical Decision Support Systems (CDSS) interface to discriminate positive COVID-19 from negative cases.
Background: During the COVID-19 pandemic, the use of technology-based services has been incremental by the care providers for patients scheduling, regulatory considerations, resource allocation, thus enabling virus exposure prevention while maintaining effective patient care. This study aims to review the currently available evidence to identify available technology solutions in the era of COVID-19. Methods: A systematic review in July 2020 using the PubMed, Scopus, Embase, Science Direct, and Web of Science databases has been carried out. After evaluating the title and abstract to select the most relevant studies based on inclusion and exclusion criteria, the selected articles underwent quality assessment. The full text of selected articles was then thoroughly evaluated to extract the essential findings. Results: In this study, 20 technology-based approaches have been identified for provision of healthcare services to patients with COVID-19. These methods included telemedicine, virtual visits, e-consult, tele-consulting, video conference, virtual healthcare, mobile-based self-care, social media, tele ICU, 3D printing technology, telemonitoring, teleradiology, telesurgical, and cloud-based service. Conclusion: Due to the rapid spread of the coronavirus, the use of technology-based methods for the provision of remote healthcare services can help control the disease. The effectiveness of each of these approaches can be investigated in future research.
Background and aimThe picture archiving and communication system (PACS) is a healthcare system technology which manages medical images and integrates equipment through a network. There are some theories about the use and acceptance of technology by people to describe the behavior and attitudes of end users towards information technologies. We investigated the influential factors on users’ acceptance of PACS in the military hospitals of Tehran.MethodsIn this applied analytical and cross-sectional study, 151 healthcare employees of military hospitals who had experience in using the PACS system were investigated. Participants were selected by census. The following variables were considered: performance expectancy, efforts expectancy, social influence, facilitating conditions and behavioral intention. Data were gathered using a questionnaire. Its validity and reliability were approved by a panel of experts and was piloted with 30 hospital healthcare staff (Cronbach’s alpha =0.91). Spearman correlation coefficient and multiple linear regression analysis were used in analyzing the data.ResultsExpected performance, efforts expectancy, social impact and facilitating conditions had a significant relationship with behavioral intention. The multiple regression analysis indicated that only performance expectancy can predict the user’s behavioral intentions to use PACS technology.ConclusionPerformance and effort expectancies are quite influential in accepting the use of PACS in hospitals. All healthcare personnel should become aware that using such technology is necessary in a hospital. Knowing the influencing factors that affect the acceptance of using new technology can help in improving its use, especially in a healthcare system. This can improve the offered healthcare services’ quality.
Mobile Health applications have shown different usages in the COVID-19 pandemic, which consisted of empowering patient’s awareness, promoting patient’s self-care, and self-monitor behaviors. The purpose of this study is to identify key features and capabilities of a mobile-based application for self-care and self-management of people with COVID-19 disease. This study was a descriptive-analytical study that was conducted in two main phases in 2020. In the first phase, a literature review study was performed. In the second phase, using the information obtained from the review of similar articles, a questionnaire was designed to validate identified requirements. Based on the results of the first phase, 53 data elements and technical key features for mobile-based self-care application for people with COVID-19 were identified. According to the statistical population, 11 data elements for demographic requirements, 11 data elements for clinical requirements, 15 data elements for self-care specifications, and 16 features for the technical capability of this app were determined. Most of the items were selected by infectious and internal medicine specialists (94%). This study supports that the use of mobile-based applications can play an important role in the management of this disease. Software design and development could help manage and improve patients’ health status.
Background: Today, the COVID-19 pandemic is ever-increasingly challenging healthcare systems globally with many uncertainties and ambiguities regarding disease behavior and outcome prediction. Thus, machine learning (ML) algorithms could be potentially demanding to tackle these challenges. Objectives: The present study aimed to construct and compare two prediction models based on statistical and computational ML algorithms to predict mortality in COVID-19 hospitalized patients and, finally, adopt the best-performing algorithm, accordingly. Methods: Having considered a single-center registry, we scrutinized 482 records of laboratory-confirmed COVID-19 hospitalized patients admitted from February 9, 2020, to December 20, 2020. The most important clinical parameters for COVID-19 mortality prediction were identified using the Phi coefficient technique. In the next step, two statistical and computational ML models, ie, logistic regression (LR) and artificial neural network (ANN), were evaluated through the metrics derived from the confusion matrix. Results: Predictive models were trained using 16 validated features. The results indicated that the best performance pertained to the ANN classifier with a positive predictive value (PPV) of 0.96%, a negative predictive value (NPV) of 0.86%, the sensitivity of 0.94%, specificity of 0.94%, and accuracy of 0.93%. Conclusions: According to the results, ANN predicted mortality in hospitalized patients with COVID-19 with an acceptable level of accuracy. Therefore, it would be extremely reasonable to develop intelligent decision support systems to early detect high-risk patients, helping clinicians come up with proper interventions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.