Volume 5, Issue 3 (12-2022)
2022, 5(3): 0-0 |
Back to browse issues page
Ethics code: IR.MEDILAM.REC.1399.294
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Shanbehzadeh M, Kafashian M. Design and development of Computerized Decision Support System (CDSS) for COVID-19 diagnosis. Journal title 2022; 5 (3)
URL: http://newresearch.medilam.ac.ir/article-1-1252-en.html
URL: http://newresearch.medilam.ac.ir/article-1-1252-en.html
Department of Health Information Management, School of Allied Medical Sciences, Ilam University of Medical sciences, Ilam, Iran
Abstract: (1135 Views)
Coronavirus disease 2019 (COVID-19) has widely spread all over the world since December2019. This pandemic poses a great threat and challenge to global health and economy. The COVID-19 diagnosis and treatment is very complex, because of its unknown many characteristics. Thus it is crucial to have a framework for an early of its prediction. In this regard, Machines Learning (ML) could be the crucial to extracting high-quality predictive models and concealed patterns from mining of huge raw datasets.
Purpose: At this juncture, we aimed to apply different ML models to discover correlations in COVID-19 data that could help improving prediction rate. Additionally, their potential was evaluated to find the best classifier which gives better accuracy. Material and Methods: The dataset of Talleghani hospital, COVID-19 focal center affiliated to Abadan University of Medical Sciences have been taken into consideration. ML algorithms such as Naïve Bayesian (NB), Bayesian Net (BN), Random Forest (RF), Multilayer Perceptron ( MLP ), K-star, C4.5, and Support Vector Machine ( SVM ) were developed. Then the recital of selected ML models was assessed by comparison of some performance indices such as accuracy, sensitivity, specificity, precision, F-score, and Receiver Operating Characteristic (ROC).
Purpose: At this juncture, we aimed to apply different ML models to discover correlations in COVID-19 data that could help improving prediction rate. Additionally, their potential was evaluated to find the best classifier which gives better accuracy. Material and Methods: The dataset of Talleghani hospital, COVID-19 focal center affiliated to Abadan University of Medical Sciences have been taken into consideration. ML algorithms such as Naïve Bayesian (NB), Bayesian Net (BN), Random Forest (RF), Multilayer Perceptron ( MLP ), K-star, C4.5, and Support Vector Machine ( SVM ) were developed. Then the recital of selected ML models was assessed by comparison of some performance indices such as accuracy, sensitivity, specificity, precision, F-score, and Receiver Operating Characteristic (ROC).
Received: 2020/11/12 | Accepted: 2022/04/18 | Published: 2022/08/20
Send email to the proposal executer
| Rights and permissions | |
 | This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
