Selecting Feature Subsets Based on SVM-RFE and the Overlapping Ratio with Applications in Bioinformatics

Lin, Xiaohui; Li, Chao; Zhang, Yanhui; Su, Benzhe; Fan, Meng; Wei, Hai

doi:10.3390/molecules23010052

Cited by 82 publications

(49 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RFE combined with ML classifiers have been used in various clinical dataset successfully [25][26][27][28]. We also used Recursive feature elimination (RFE) to find a minimal and best set of PLOS ONE variables by removing the least important features and compare them with feature selection by ML methods (RF, SVM and LR) [29,30].…”

Section: Feature Selectionmentioning

confidence: 99%

Short- and long-term mortality prediction after an acute ST-elevation myocardial infarction (STEMI) in Asians: A machine learning approach

et al. 2021

View full text Add to dashboard Cite

Background Conventional risk score for predicting short and long-term mortality following an ST-segment elevation myocardial infarction (STEMI) is often not population specific. Objective Apply machine learning for the prediction and identification of factors associated with short and long-term mortality in Asian STEMI patients and compare with a conventional risk score. Methods The National Cardiovascular Disease Database for Malaysia registry, of a multi-ethnic, heterogeneous Asian population was used for in-hospital (6299 patients), 30-days (3130 patients), and 1-year (2939 patients) model development. 50 variables were considered. Mortality prediction was analysed using feature selection methods with machine learning algorithms and compared to Thrombolysis in Myocardial Infarction (TIMI) score. Invasive management of varying degrees was selected as important variables that improved mortality prediction. Results Model performance using a complete and reduced variable produced an area under the receiver operating characteristic curve (AUC) from 0.73 to 0.90. The best machine learning model for in-hospital, 30 days, and 1-year outperformed TIMI risk score (AUC = 0.88, 95% CI: 0.846–0.910; vs AUC = 0.81, 95% CI:0.772–0.845, AUC = 0.90, 95% CI: 0.870–0.935; vs AUC = 0.80, 95% CI: 0.746–0.838, AUC = 0.84, 95% CI: 0.798–0.872; vs AUC = 0.76, 95% CI: 0.715–0.802, p < 0.0001 for all). TIMI score underestimates patients’ risk of mortality. 90% of non-survival patients are classified as high risk (>50%) by machine learning algorithm compared to 10–30% non-survival patients by TIMI. Common predictors identified for short- and long-term mortality were age, heart rate, Killip class, fasting blood glucose, prior primary PCI or pharmaco-invasive therapy and diuretics. The final algorithm was converted into an online tool with a database for continuous data archiving for algorithm validation. Conclusions In a multi-ethnic population, patients with STEMI were better classified using the machine learning method compared to TIMI scoring. Machine learning allows for the identification of distinct factors in individual Asian populations for better mortality prediction. Ongoing continuous testing and validation will allow for better risk stratification and potentially alter management and outcomes in the future.

show abstract

Section: Feature Selectionmentioning

confidence: 99%

Short- and long-term mortality prediction after an acute ST-elevation myocardial infarction (STEMI) in Asians: A machine learning approach

et al. 2021

View full text Add to dashboard Cite

show abstract

“…It starts from the complete feature set and recursively creates a model by storing the best and worst performed models. It gives rank to each feature based on the order of removal (Lin et al, 2018, Huang et al, 2014 They tend to perform better than filter methods but computational complexity is more. The advantage of RFE-CV over RFE is that it uses the cross-validated score to select the optimal number of features.…”

Section: Feature Selectionmentioning

confidence: 99%

Eye Movement Feature Set and Predictive Model for Dyslexia

Appadurai

Bhargavi

2021

International Journal of Cognitive Informatics and Natural Intelligence

View full text Add to dashboard Cite

Dyslexia is a learning disorder that can cause difficulties in reading or writing. Dyslexia is not a visual problem but many dyslexics have impaired magnocellular system which causes poor eye control. Eye-trackers are used to track eye movements. This research work proposes a set of significant eye movement features that are used to build a predictive model for dyslexia. Fixation and saccade eye events are detected using the dispersion-threshold and velocity-threshold algorithms. Various machine learning models are experimented. Validation is done on 185 subjects using 10-fold cross-validation. Velocity based features gave high accuracy compared to statistical and dispersion features. Highest accuracy of 96% was achieved using the Hybrid Kernel Support Vector Machine- Particle Swarm Optimization model followed by the Xtreme Gradient Boosting model with an accuracy of 95%. The best set of features are the first fixation start time, average fixation saccade duration, the total number of fixations, total number of saccades and ratio between saccades and fixations.

show abstract

“…Compared with the linear model, LASSO model can reduce the variable numbers and effectively avoid over tting. The SVM-RFE is an algorithm of machine learning and the optimal subset was selected via a k-fold cross-validation approach [18]. We further evaluated the expression of the 13 key genes by using an another dataset.…”

Section: Discussionmentioning

confidence: 99%

Identification of key genes associated with Idiopathic Pulmonary Fibrosis by combining multiple analytical methods

Zhao

Yang

Dong

et al. 2020

Preprint

View full text Add to dashboard Cite

Idiopathic Pulmonary Fibrosis (IPF) is the most common type of idiopathic interstitial pneumonias (IIPs) with unclear etiology and lack of effective diagnostic biomarker or therapeutic targets. This study aimed to identify the key genes associated with IPF through multiple microarray datasets. two datasets including GSE32537 and GSE110147 retrieved from Gene Expression Omnibus (GEO) database were used as training dataset (N =169) and external validation dataset (N =33). A total of 365 differentially expressed genes (DEGs) were identified between normal tissue and IPF tissue in the training dataset. Function enrichment analysis result indicated that these genes were involved in cell proliferation, response to stimulus, cellular process and immune system process. We then constructed a protein-protein network (PPI) using the cytoscape software based on the DEGs and the hub modules were screened using the MCODE algorithm. Then the DEGs from hub modules were further exploited into Least absolute shrinkage and selection operator (LASSO) and support vector machine (SVM) analysis in the training dataset. 13 key genes including SERPIND1, CDH2, CP, WDR63, DNAH5, FGG, THBS1, VCAM1, COL1A2, POSTN, CXCL12, MMP13, SERPINE1 were further validated in the validation dataset. In addition, we also applied the CIBERSORT algorithm to evaluate the infiltration level of immune cells in IPF tissue, and the correlation between key genes and infiltrating immune cells. We identified that Plasma cells, CD4 naive T cells, NK resting cells, Monocytes, Mast resting cells and Neutrophils might involved in the process of IPF. Moreover, we also identified several drugs including pregnenolone, indoprofen, ramipril, inburnine may contribute to the treatment of IPF. In conclusion, the 13 genes might serve as potential diagnostic markers of IPF, and the immune cell infiltration plays an essential role in the occurrence and progression of IPF.

show abstract

Selecting Feature Subsets Based on SVM-RFE and the Overlapping Ratio with Applications in Bioinformatics

Cited by 82 publications

References 36 publications

Short- and long-term mortality prediction after an acute ST-elevation myocardial infarction (STEMI) in Asians: A machine learning approach

Short- and long-term mortality prediction after an acute ST-elevation myocardial infarction (STEMI) in Asians: A machine learning approach

Eye Movement Feature Set and Predictive Model for Dyslexia

Identification of key genes associated with Idiopathic Pulmonary Fibrosis by combining multiple analytical methods

Contact Info

Product

Resources

About