A multiple combined method for rebalancing medical data with class imbalances

Wang, Yunchun; Cheng, Ching‐Hsue

doi:10.1016/j.compbiomed.2021.104527

Cited by 39 publications

(14 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because class imbalance can affect the efficiency of ML modeling [ 72 , 73 , 74 ], we investigated this possibility by using four methods: Oversampling, downsampling, ROSE, and SMOTE. These methods employ different tactics to balance class in the training dataset (see [ 75 ] for a detailed discussion). Differences in the efficiency of the four methods for model training were revealed by their predictive performance on the independent test data.…”

Section: Discussionmentioning

confidence: 99%

Detection of Embryonic Trisomy 21 in the First Trimester Using Maternal Plasma Cell-Free RNA

et al. 2022

View full text Add to dashboard Cite

Prenatal trisomy 21 (T21) screening commonly involves testing a maternal blood sample for fetal DNA aneuploidy. It is reliable but poses a cost barrier to universal screening. We hypothesized maternal plasma RNA screening might provide similar reliability but at a lower cost. Discovery experiments used plasma cell-free RNA from 20 women 11–13 weeks tested by RNA and miRNA microarrays followed by qRT-PCR. Thirty-six mRNAs and 18 small RNAs of the discovery cDNA were identified by qPCR as potential markers of embryonic T21. The second objective was validation of the RNA predictors in 998 independent pregnancies at 11–13 weeks including 50 T21. Initial analyses identified 9–15 differentially expressed RNA with modest predictive power (AUC < 0.70). The 54 RNAs were then subjected to machine learning. Eleven algorithms were trained on one partition and tested on an independent partition. The three best algorithms were identified by Kappa score and the effects of training/testing partition size and dataset class imbalance on prediction were evaluated. Six to ten RNAs predicted T21 with AUCs up to 1.00. The findings suggest that maternal plasma collected at 11–13 weeks, tested by qRT-PCR, and classified by machine learning, may accurately predict T21 for a lower cost than plasma DNA, thus opening the door to universal screening.

show abstract

Section: Discussionmentioning

confidence: 99%

Detection of Embryonic Trisomy 21 in the First Trimester Using Maternal Plasma Cell-Free RNA

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The SARS-CoV-2 is classified as

-CoV [ 10 ] and has received widespread research attention across the world [ [11] , [12] , [13] ]. Every day, new genome sequences, as well as primary protein sequences of SARS-CoV-2, are being added to databases, such as the NCBI virus database [ 14 , 15 ] As of this writing, no antiviral drugs with proven efficacy nor vaccines for CoV2 prevention have been reported [ 16 , 17 ], while researchers have yet to attain a complete understanding of the molecular biology of SARS-CoV-2 infection [ 18 , 19 ]As a result, COVID-19 cases increase and have reached a global pandemic level, thus urgently requiring in-depth knowledge, infection mechanism, and other aspects of the virus-like forecasting its progression [ 18 , 20 ]. Although various protein-protein interactions (PPIs) of the virus and host are known, its viral infection mechanism is not fully understood [ 21 , 22 ]Therefore, identifying interactions between the SARS-CoV-2 virus proteins and host proteins will largely help to understand this mechanism and further develop treatments and vaccines [ 23 ].…”

Section: Introductionmentioning

confidence: 99%

Feature-extraction and analysis based on spatial distribution of amino acids for SARS-CoV-2 Protein sequences

Rout

Hassan²,

Sheikh

et al. 2022

Computers in Biology and Medicine

View full text Add to dashboard Cite

“…Classes with fewer instances (minority class) are often ignored in the classification algorithm, or there is misclassification of the minority class into another class even though the minority class is a class with a high value because it is the center of observation [3]. Class imbalance is unavoidable; for example, medical datasets are obtained from patient medical data, where the number of patients suffering from the disease is much less than the number of patients without the disease [4].…”

Section: Introductionmentioning

confidence: 99%

Avoiding Overfitting dan Overlapping in Handling Class Imbalanced Using Hybrid Approach with Smoothed Bootstrap Resampling and Feature Selection

Hartono¹,

Ongko

2022

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

The dataset tends to have the possibility to experience imbalance as indicated by the presence of a class with a much larger number (majority) compared to other classes(minority). This condition results in the possibility of failing to obtain a minority class even though the accuracy obtained is high. In handling class imbalance, the problems of diversity and classifier performance must be considered. Hence, the Hybrid Approach method that combines the sampling method and classifier ensembles presents satisfactory results. The Hybrid Approach generally uses the oversampling method, which is prone to overfitting problems. The overfitting condition is indicated by high accuracy in the training data, but the testing data can show differences in accuracy. Therefore, in this study, Smoothed Bootstrap Resampling is the oversampling method used in the Hybrid Approach, which can prevent overfitting. However, it is not only the class imbalance that contributes to the decline in classifier performance. There are also overlapping issues that need to be considered. The approach that can be used to overcome overlapping is Feature Selection. Feature selection can reduce overlap by minimizing the overlap degree. This research combined the application of Feature Selection with Hybrid Approach Redefinition, which modifies the use of Smoothed Bootstrap Resampling in handling class imbalance in medical datasets. The preprocessing stage in the proposed method was carried out using Smoothed Bootstrap Resampling and Feature Selection. The Feature Selection method used is Feature Assessment by Sliding Thresholds (FAST). While the processing is done using Random Under Sampling and SMOTE. The overlapping measurement parameters use Augmented R-Value, and Classifier Performance uses the Balanced Error Rate, Precision, Recall, and F-Value parameters. The Balanced Error Rate states the combined error of the majority and minority classes in the 10-Fold Validation test, allowing each subset to become training data. The results showed that the proposed method provides better performance when compared to the comparison method

show abstract

A multiple combined method for rebalancing medical data with class imbalances

Cited by 39 publications

References 59 publications

Detection of Embryonic Trisomy 21 in the First Trimester Using Maternal Plasma Cell-Free RNA

Detection of Embryonic Trisomy 21 in the First Trimester Using Maternal Plasma Cell-Free RNA

Feature-extraction and analysis based on spatial distribution of amino acids for SARS-CoV-2 Protein sequences

Avoiding Overfitting dan Overlapping in Handling Class Imbalanced Using Hybrid Approach with Smoothed Bootstrap Resampling and Feature Selection

Contact Info

Product

Resources

About