INTRODUCTION: The 2019 coronavirus disease (COVID-19) is a major global health concern. Joint efforts for effective surveillance of COVID-19 require immediate transmission of reliable data. In this regard, a standardized and interoperable reporting framework is essential in a consistent and timely manner. Thus, this research aimed at to determine data requirements towards interoperability. MATERIALS AND METHODS: In this cross-sectional and descriptive study, a combination of literature study and expert consensus approach was used to design COVID-19 Minimum Data Set (MDS). A MDS checklist was extracted and validated. The definitive data elements of the MDS were determined by applying the Delphi technique. Then, the existing messaging and data standard templates (Health Level Seven-Clinical Document Architecture [HL7-CDA] and SNOMED-CT) were used to design the surveillance interoperable framework. RESULTS: The proposed MDS was divided into administrative and clinical sections with three and eight data classes and 29 and 40 data fields, respectively. Then, for each data field, structured data values along with SNOMED-CT codes were defined and structured according HL7-CDA standard. DISCUSSION AND CONCLUSION: The absence of effective and integrated system for COVID-19 surveillance can delay critical public health measures, leading to increased disease prevalence and mortality. The heterogeneity of reporting templates and lack of uniform data sets hamper the optimal information exchange among multiple systems. Thus, developing a unified and interoperable reporting framework is more effective to prompt reaction to the COVID-19 outbreak.
Background: The rapid coronavirus disease 2019 (COVID-19) outbreak has overwhelmed many healthcare systems worldwide and put them at the edge of collapsing. As the capacity of intensive care units (ICUs) is limited, deciding on the proper allocation of required resources is crucial. Objectives: This study aimed to create a machine learning (ML)-based predictive model of ICU admission among COVID-19 in-hospital patients at the initial presentation. Methods: This retrospective study was conducted on 1225 laboratory-confirmed COVID-19 hospitalized patients during January 9, 2020 - January 20, 2021. The top clinical parameters contributing to COVID-19 ICU admission were identified based on a correlation coefficient at P-value < 0.05. Next, the predictive models were constructed using five ML algorithms. Finally, to evaluate the performances of models, the metrics derived from the confusion matrix, classification error, and receiver operating characteristic were calculated. Results: Following feature selection, a total of 11 parameters were selected as the top predictors to build the prediction models. The results showed that the best performance belonged to the random forest (RF) algorithm with the mean accuracy of 99.5%, mean specificity of 99.7%, mean sensitivity of 99.4%, Kappa metric of 95.7%, and root mean squared error of 0.015. Conclusions: The ML algorithms, particularly RF, enable a reasonable level of accuracy and certainty in predicting disease progression and ICU admission for COVID-19 patients. The proposed models have the potential to inform frontline clinicians and health authorities with quantitative tools to assess illness severity and optimize resource allocation under time-sensitive and resource-constrained situations.
Introduction:The wide range of notifiable diseases and the need for immediate reporting complicate the management of these diseases. Developing a surveillance system using precise architectural principles could ease the management of these diseases. Aim: The present study reviews the data architecture of notifiable diseases surveillance systems to provide a basis for developing such systems. Methods: A systematic review was conducted on the literature focused on data architecture of notifiable diseases surveillance systems. The searches for relevant English language articles were conducted based on the paper keywords, as well as the words Mesh and EMTREE. Results: The findings were categorized into five groups, including organizations involved in the generation and monitoring of notifiable diseases' data. The databases in the present study were relational and used a centralized architecture for information sharing. The minimum dataset was determined in two information categories. The data standards were categorized into three main groups. The key approaches for data quality control included checking the completeness, timeliness, accuracy, consistency, adequacy, and validity of the data. Conclusion: Developing a notifiable diseases surveillance based on data architecture principles could lay the foundation for better management of such diseases through eliminating the obstacles experienced during data generation, data processing, and data sharing.
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.