RESUMO
Background: The rapid prevalence of coronavirus disease 2019 (COVID-19) has caused a pandemic worldwide and affected the lives of millions. The potential fatality of the disease has led to global public health concerns. Apart from clinical practice, artificial intelligence (AI) has provided a new model for the early diagnosis and prediction of disease based on machine learning (ML) algorithms. In this study, we aimed to make a prediction model for the prognosis of COVID-19 patients using data mining techniques. Methods: In this study, a data set was obtained from the intelligent management system repository of 19 hospitals at Shahid Beheshti University of Medical Sciences in Iran. All patients admitted had shown positive polymerase chain reaction (PCR) test results. They were hospitalized between February 19 and May 12 in 2020, which were investigated in this study. The extracted data set has 8621 data instances. The data include demographic information and results of 16 laboratory tests. In the first stage, preprocessing was performed on the data. Then, among 15 laboratory tests, four of them were selected. The models were created based on seven data mining algorithms, and finally, the performances of the models were compared with each other. Results: Based on our results, the Random Forest (RF) and Gradient Boosted Trees models were known as the most efficient methods, with the highest accuracy percentage of 86.45% and 84.80%, respectively. In contrast, the Decision Tree exhibited the least accuracy (75.43%) among the seven models. Conclusion: Data mining methods have the potential to be used for predicting outcomes of COVID-19 patients with the use of lab tests and demographic features. After validating these methods, they could be implemented in clinical decision support systems for better management and providing care to severe COVID-19 patients.
RESUMO
BACKGROUND With an increase in the prevalence and incidence of inflammatory bowel diseases (IBDs), they have become a global challenge. The IBD registry provides complete and timely data, thereby greatly contributing to the estimation of the burden of these diseases and development of control and prevention programs. We aimed to develop an IBD registry software. METHODS The present applied-developmental study had two main stages: determining user requirements, and developing the IBD registry software. The software was created using a Web-based software development technology called ASP.NET Core 2. The programming language in this framework was C#, and the SQL Server 2017 was employed to create a strong and integrated software databank in the relational form. RESULTS When determining user requirements, the data elements were classified into two main categories of patient information and visits and tests. Moreover, in this stage, registry functions, including case ascertainment, abstracting, follow-up, quality control, and reporting were identified. In the registry software development stage, the object-oriented conceptual model was designed with five use case diagrams and 59 classes. The user interface comprised the following main sections: add patient, find patient, complete source report, report, staff, and drugs. Precise user authentication and authorization were also employed to enhance the security of the developed software. CONCLUSION Development of an IBD registry which can precisely record patients and estimate the incidence, prevalence, and socioeconomic burden of these diseases can assist in planning for the control and prevention of IBD in healthcare systems.
RESUMO
BACKGROUND: Nurses' health is often accompanied by various dangers due to the nature of their career. Therefore, it is required to monitor their health. Based on designing any system, users' views should be investigated relative to the usefulness, necessity and acceptance of the system. Then, a designing and implementing process is conducted. OBJECTIVE: To investigate nurses' views on accepting the creation of a Nurses' Health Monitoring System. METHODS: This cross-sectional study was conducted in 2015. Sample size was 586 nurses of Shahid Beheshti University of Medical Sciences. Sampling was conducted using multi-stage random sampling method. Research tool was a two-section researcher-made questionnaire. In the first section, demographic data were studied and in the second section, a twelve-item questionnaire was presented based on technology acceptance model. Five-item questions were regulated on perceived usefulness (PU) and perceived ease of use (PEU) and views towards creating this system. Validity of the questionnaire was approved by content validity and content validity index and its reliability was approved by Cronbach's alpha. Data were analyzed using SPSS16 and descriptive statistics (frequency distribution, percentage, mean). RESULTS: The majority of participants (75.3%) were females between 25-35 years of age (44.4%) and (58.2%) were married. Mean work experience was 11.5±8.19. Mean perceived usefulness (PU) (17.36±2.66) and perceived ease of use (PEU) (16.75±2.65) and views towards using a Nurses' Health Monitoring System was (16.220±3.05). CONCLUSION: Over two-thirds of nurses demonstrated perceived usefulness and perceived ease of use as well as positive views towards creating a nurses' health monitoring system. It is recommended to design and implement a nurses' health monitoring system based on local culture of Iranian nurses using IT in the health sector.