Efficient feature selection and classification for microarray data

Li, Zifa; Xie, Weibo; Liu, Tao

doi:10.1371/journal.pone.0202167

Cited by 81 publications

(52 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As such, we applied the Recursive Feature Elimination (RFE) method coupled with Random Forest for measuring variable importance. The RFE technique has been widely applied in healthcare applications due to its efficiency in reducing the complexity (Li, Xie, & Liu, 2018). Furthermore, studies demonstrated that RF-RFE outperformed SVM-RFE in finding small subsets of features with a high discrimination capability and required no parameter tuning to produce competitive results (Granitto, Furlanello, Biasioli & Gasperi, 2006).…”

Section: Methodsmentioning

confidence: 99%

A practical computerized decision support system for predicting the severity of Alzheimer’s disease of an individual

Bucholc

Ding

Wang

et al. 2019

Preprint

View full text Add to dashboard Cite

1Computerized clinical decision support systems can help to provide objective, standardized, 2 and timely dementia diagnosis. However, current computerized systems are mainly based 3 on the group analysis, discrete classification of disease stages, or expensive and not readily 4 accessible biomarkers, while current clinical practice relies relatively heavily on cognitive and 5 functional assessments (CFA). In this study, we developed a computational framework using 6 a suite of machine learning tools for identifying key markers in predicting the severity of 7 Alzheimer's disease (AD) from a large set of biological and clinical measures. Six machine 8 learning approaches, namely Kernel Ridge Regression (KRR), Support Vector Regression 9 (SVR), and k-Nearest Neighbor (kNN reg ) for regression and Support Vector Machine (SVM), 10Random Forest (RF), and k-Nearest Neighbor (kNN class ) for classification, were used for the 11 development of predictive models. We demonstrated high predictive power of CFA. 12Predictive performance of models incorporating CFA was shown to be consistently higher 13 accuracy than those based solely on biomarker modalities. We found that KRR and SVM 14 were the best performing regression and classification methods respectively. The optimal 15 SVM performance was observed for a set of four CFA test scores (FAQ, ADAS13, MoCA, 16MMSE) with multi-class classification accuracy of 83.0%, 95%CI = (72.1%, 93.8%) while the 17 best performance of the KRR model was reported with combined CFA and MRI 18 neuroimaging data, i.e., R 2 = 0.874, 95%CI = (0.827, 0.922). Given the high predictive power 19 of CFA and their widespread use in clinical practice, we then designed a data-driven and 20 self-adaptive computerized clinical decision support system (CDSS) prototype for evaluating 21 the severity of AD of an individual on a continuous spectrum. The system implemented an 22 automated computational approach for data pre-processing, modelling, and validation and 23 used exclusively the scores of selected cognitive measures as data entries. Taken together, 24we have developed an objective and practical CDSS to aid AD diagnosis. 25Keywords: dementia; Alzheimer's disease; decision support system; machine learning; 26 diagnosis support; cognitive impairment 27 97 CDSS for evaluating the severity of AD of an individual on a continuous spectrum. In order to 98 achieve this, we first utilize a suite of machine learning techniques to extract useful 99 information from large volumes of patient data and provide a disease outcome prediction for 100 different types and combinations of AD markers. We demonstrate that CFA can reliably and 101 accurately provide prediction of AD severity. Next, we design a CDSS that incorporates an 102 automated computational approach for data pre-processing, modelling, and validation and 103 uses selected CFA scores as data input. Since our system was designed to utilize 104 information from readily available and cost-effective CFA markers, it can be easily 105 implemented in general cli...

show abstract

Section: Methodsmentioning

confidence: 99%

A practical computerized decision support system for predicting the severity of Alzheimer’s disease of an individual

Bucholc

Ding

Wang

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…Nonetheless, the high dimensionality of microarray data frequently means that wrappers and embedded methods cannot be used. This issue inspired an attempt to reduce SVM-RFE time consumption by proposing an improved version of RFE called RFE with variable step size (VSSRFE) [84]. The idea is to use a large step that decreases in size as the number of selected features decreases.…”

Section: Dna Microarray Datamentioning

confidence: 99%

A review of feature selection methods in medical applications

Remeseiro

Bolón-Canedo

2019

Computers in Biology and Medicine

523

280

View full text Add to dashboard Cite

Feature selection is a preprocessing technique that identifies the key features of a given problem. It has traditionally been applied in a wide range of problems that include biological data processing, finance, and intrusion detection systems. In particular, feature selection has been successfully used in medical applications, where it can not only reduce dimensionality but also help us understand the causes of a disease. We describe some basic concepts related to medical applications and provide some necessary background information on feature selection. We review the most recent feature selection methods developed for and applied in medical problems, covering prolific research fields such as medical imaging, biomedical signal processing, and DNA microarray data analysis. A case study of two medical applications that includes actual patient data is used to demonstrate the suitability of applying feature selection methods in medical problems and to illustrate how these methods work in real-world scenarios.

show abstract

“…Most probably, the classifiers yield worse prognostic performance when trained on such small number of classes [12]. Typically, large dimensionality is one of the significant challenges that faces the interpretation and the analysis of gene expression data measured using microarray technology [13]. In microarray technology, thousands of gene expressions are produced under few conditions' samples.…”

Section: Introductionmentioning

confidence: 99%

Classical and Deep Learning Paradigms for Detection and Validation of Key Genes of Risky Outcomes of HCV

Samee

2020

Algorithms

View full text Add to dashboard Cite

Hepatitis C virus (HCV) is one of the most dangerous viruses worldwide. It is the foremost cause of the hepatic cirrhosis, and hepatocellular carcinoma, HCC. Detecting new key genes that play a role in the growth of HCC in HCV patients using machine learning techniques paves the way for producing accurate antivirals. In this work, there are two phases: detecting the up/downregulated genes using classical univariate and multivariate feature selection methods, and validating the retrieved list of genes using Insilico classifiers. However, the classification algorithms in the medical domain frequently suffer from a deficiency of training cases. Therefore, a deep neural network approach is proposed here to validate the significance of the retrieved genes in classifying the HCV-infected samples from the disinfected ones. The validation model is based on the artificial generation of new examples from the retrieved genes’ expressions using sparse autoencoders. Subsequently, the generated genes’ expressions data are used to train conventional classifiers. Our results in the first phase yielded a better retrieval of significant genes using Principal Component Analysis (PCA), a multivariate approach. The retrieved list of genes using PCA had a higher number of HCC biomarkers compared to the ones retrieved from the univariate methods. In the second phase, the classification accuracy can reveal the relevance of the extracted key genes in classifying the HCV-infected and disinfected samples.

show abstract

Efficient feature selection and classification for microarray data

Cited by 81 publications

References 27 publications

A practical computerized decision support system for predicting the severity of Alzheimer’s disease of an individual

A practical computerized decision support system for predicting the severity of Alzheimer’s disease of an individual

A review of feature selection methods in medical applications

Classical and Deep Learning Paradigms for Detection and Validation of Key Genes of Risky Outcomes of HCV

Contact Info

Product

Resources

About