Please use this identifier to cite or link to this item: https://ir.swu.ac.th/jspui/handle/123456789/27593
Full metadata record
DC FieldValueLanguage
dc.contributor.authorAnupoomchaiya P.
dc.contributor.authorSukperm A.
dc.contributor.authorRojnuckarin P.
dc.contributor.authorSa-Ing V.
dc.date.accessioned2022-12-14T03:17:44Z-
dc.date.available2022-12-14T03:17:44Z-
dc.date.issued2022
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85133310679&doi=10.1109%2fECTI-CON54298.2022.9795612&partnerID=40&md5=315e31090a75e83bb76549d783cf056b
dc.identifier.urihttps://ir.swu.ac.th/jspui/handle/123456789/27593-
dc.description.abstractThrombosis is the main cause of blood clots that obstructs the flow of blood in an artery or venous thrombosis. Thus, venous thromboembolism (VTE) is the most serious cause of cardiovascular disease. Furthermore, this disease is a leading cause of death in Thailand because of a lack of understanding and caution. In this research, we propose an automatic diagnosis model by using effective machine learning to predict the important risk factors for VTE. The raw data were collected from the medical ward at King Chulalongkorn Memorial Hospital of Thailand. Before the analysis, this data consisted of 1,290 rows and 65 columns that were analyzed, solved, and transformed as prepared data. By resampling algorithms to import into each model, this research spits the prepared data into the training dataset and the testing dataset with a ratio of 80:20. In the experiments, our research compares the effectiveness of the three machine learning models that consist of Adaptive Boosting (AdaBoost), Random Forest (RF), and Extreme Gradient Boosting (XGBoost) to find the best diagnostic model. According to the experimental results, the Random Forest model was computed by the class weight and oversampled by the sampling strategy 0.25 technique is the most efficient model to represent the most prediction accuracy of 99.61 percent. Therefore, the Random Forest and our proposed setting will assist the medical doctors in determining the risk of symptomatic venous thromboembolism. In addition, our proposed model can be used to forecast the likelihood of VTE based on a combination of the important risk factors. © 2022 IEEE.
dc.languageen
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.subjectimbalanced data
dc.subjectmachine learning
dc.subjectresampling method
dc.subjectvenous thromboembolism
dc.titleAutomatic Diagnosis Model for Risk Factors of Symptomatic Venous Thromboembolism based on Machine Learning
dc.typeArticle
dc.rights.holderScopus
dc.identifier.bibliograpycitationPrimary Health Care Research and Development. Vol 23, No. (2022)
dc.identifier.doi10.1109/ECTI-CON54298.2022.9795612
Appears in Collections:Scopus 2022

Files in This Item:
There are no files associated with this item.


Items in SWU repository are protected by copyright, with all rights reserved, unless otherwise indicated.