2021
DOI: 10.1016/j.cmpb.2021.106444
|View full text |Cite
|
Sign up to set email alerts
|

A novel combined dynamic ensemble selection model for imbalanced data to detect COVID-19 from complete blood count

Abstract: Background : As blood testing is radiation-free, low-cost and simple to operate, some researchers use machine learning to detect COVID-19 from blood test data. However, few studies take into consideration the imbalanced data distribution, which can impair the performance of a classifier. Method : A novel combined dynamic ensemble selection (DES) method is proposed for imbalanced data to detect COVID-19 from complete blood count. This method… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
8
0

Year Published

2022
2022
2025
2025

Publication Types

Select...
8

Relationship

0
8

Authors

Journals

citations
Cited by 15 publications
(10 citation statements)
references
References 50 publications
(65 reference statements)
0
8
0
Order By: Relevance
“…In Wu et al [ 43 ], to identify COVID-19 from a complete blood count, a mixed dynamic ensemble selection (DES) approach for unbalanced data is suggested. This approach combines data preparation with enhanced DES.…”
Section: Methodsmentioning
confidence: 99%
“…In Wu et al [ 43 ], to identify COVID-19 from a complete blood count, a mixed dynamic ensemble selection (DES) approach for unbalanced data is suggested. This approach combines data preparation with enhanced DES.…”
Section: Methodsmentioning
confidence: 99%
“…Datasets related to COVID-19 have imbalanced data ( 62 ); some studies declare the improvement of machine learning methods applying SMOTE technique ( 63 66 ) and a novel variant of SMOTE ( 67 ), also ROSE is used ( 68 ).…”
Section: Methodsmentioning
confidence: 99%
“…Considering the data imbalance, the predictive performances of the four mod els were compared based on the three evaluation metrics, including F1, G-mean, and t J o u r n a l P r e -p r o o f he area under the receiver operating characteristic curve (AUROC), to select the optim al model. 32,33 Other evaluation metrics included confusion metrics, accuracy, precision, recall, and specificity. The confusion matrices included four indicators: true negative, f alse positive, false negative, and true positive 32 .…”
Section: Performance and Validation Of Modelsmentioning
confidence: 99%