Machine Learning and Feature Selection Methods for EGFR Mutation Status Prediction in Lung Cancer

The evolution of personalized medicine has changed the therapeutic strategy from classical chemotherapy and radiotherapy to a genetic modification targeted therapy, and although biopsy is the traditional method to genetically characterize lung cancer tumor, it is an invasive and painful procedure for the patient. Nodule image features extracted from computed tomography (CT) scans have been used to create machine learning models that predict gene mutation status in a noninvasive, fast, and easy-to-use manner. However, recent studies have shown that radiomic features extracted from an extended region of interest (ROI) beyond the tumor, might be more relevant to predict the mutation status in lung cancer, and consequently may be used to significantly decrease the mortality rate of patients battling this condition. In this work, we investigated the relation between image phenotypes and the mutation status of Epidermal Growth Factor Receptor (EGFR), the most frequently mutated gene in lung cancer with several approved targeted-therapies, using radiomic features extracted from the lung containing the nodule. A variety of linear, nonlinear, and ensemble predictive classification models, along with several feature selection methods, were used to classify the binary outcome of wild-type or mutant EGFR mutation status. The results show that a comprehensive approach using a ROI that included the lung with nodule can capture relevant information and successfully predict the EGFR mutation status with increased performance compared to local nodule analyses. Linear Support Vector Machine, Elastic Net, and Logistic Regression, combined with the Principal Component Analysis feature selection method implemented with 70% of variance in the feature set, were the best-performing classifiers, reaching Area Under the Curve (AUC) values ranging from 0.725 to 0.737. This approach that exploits a holistic analysis indicates that information from more extensive regions of the lung containing the nodule allows a more complete lung cancer characterization and should be considered in future radiogenomic studies.

Download Full-text

Diagnostic Performance of 2D and 3D T2WI-Based Radiomics Features With Machine Learning Algorithms to Distinguish Solid Solitary Pulmonary Lesion

Frontiers in Oncology ◽

10.3389/fonc.2021.683587 ◽

2021 ◽

Vol 11 ◽

Author(s):

Qi Wan ◽

Jiaxuan Zhou ◽

Xiaoying Xia ◽

Jianfeng Hu ◽

Peng Wang ◽

...

Keyword(s):

Machine Learning ◽

Feature Selection ◽

Diagnostic Performance ◽

Feature Selection Method ◽

Machine Learning Algorithms ◽

Support Vector ◽

Learning Approaches ◽

Selection Methods ◽

Linear Discriminant ◽

2D And 3D

ObjectiveTo evaluate the performance of 2D and 3D radiomics features with different machine learning approaches to classify SPLs based on magnetic resonance(MR) T2 weighted imaging (T2WI).Material and MethodsA total of 132 patients with pathologically confirmed SPLs were examined and randomly divided into training (n = 92) and test datasets (n = 40). A total of 1692 3D and 1231 2D radiomics features per patient were extracted. Both radiomics features and clinical data were evaluated. A total of 1260 classification models, comprising 3 normalization methods, 2 dimension reduction algorithms, 3 feature selection methods, and 10 classifiers with 7 different feature numbers (confined to 3–9), were compared. The ten-fold cross-validation on the training dataset was applied to choose the candidate final model. The area under the receiver operating characteristic curve (AUC), precision-recall plot, and Matthews Correlation Coefficient were used to evaluate the performance of machine learning approaches.ResultsThe 3D features were significantly superior to 2D features, showing much more machine learning combinations with AUC greater than 0.7 in both validation and test groups (129 vs. 11). The feature selection method Analysis of Variance(ANOVA), Recursive Feature Elimination(RFE) and the classifier Logistic Regression(LR), Linear Discriminant Analysis(LDA), Support Vector Machine(SVM), Gaussian Process(GP) had relatively better performance. The best performance of 3D radiomics features in the test dataset (AUC = 0.824, AUC-PR = 0.927, MCC = 0.514) was higher than that of 2D features (AUC = 0.740, AUC-PR = 0.846, MCC = 0.404). The joint 3D and 2D features (AUC=0.813, AUC-PR = 0.926, MCC = 0.563) showed similar results as 3D features. Incorporating clinical features with 3D and 2D radiomics features slightly improved the AUC to 0.836 (AUC-PR = 0.918, MCC = 0.620) and 0.780 (AUC-PR = 0.900, MCC = 0.574), respectively.ConclusionsAfter algorithm optimization, 2D feature-based radiomics models yield favorable results in differentiating malignant and benign SPLs, but 3D features are still preferred because of the availability of more machine learning algorithmic combinations with better performance. Feature selection methods ANOVA and RFE, and classifier LR, LDA, SVM and GP are more likely to demonstrate better diagnostic performance for 3D features in the current study.

Download Full-text

Comparing Methods of Feature Extraction of Brain Activities for Octave Illusion Classification Using Machine Learning

Sensors ◽

10.3390/s21196407 ◽

2021 ◽

Vol 21 (19) ◽

pp. 6407

Author(s):

Nina Pilyugina ◽

Akihiko Tsukahara ◽

Keita Tanaka

Keyword(s):

Machine Learning ◽

Feature Extraction ◽

Feature Selection ◽

Principal Component ◽

Machine Learning Algorithms ◽

Recursive Feature Elimination ◽

Support Vector ◽

Selection Methods ◽

Automatic Feature Extraction ◽

Octave Illusion

The aim of this study was to find an efficient method to determine features that characterize octave illusion data. Specifically, this study compared the efficiency of several automatic feature selection methods for automatic feature extraction of the auditory steady-state responses (ASSR) data in brain activities to distinguish auditory octave illusion and nonillusion groups by the difference in ASSR amplitudes using machine learning. We compared univariate selection, recursive feature elimination, principal component analysis, and feature importance by testifying the results of feature selection methods by using several machine learning algorithms: linear regression, random forest, and support vector machine. The univariate selection with the SVM as the classification method showed the highest accuracy result, 75%, compared to 66.6% without using feature selection. The received results will be used for future work on the explanation of the mechanism behind the octave illusion phenomenon and creating an algorithm for automatic octave illusion classification.

Download Full-text

Determining the Geotechnical Slope Failure Factors via Ensemble and Individual Machine Learning Techniques: A Case Study in Mandi, India

Frontiers in Earth Science ◽

10.3389/feart.2021.701837 ◽

2021 ◽

Vol 9 ◽

Author(s):

Naresh Mali ◽

Varun Dutt ◽

K. V. Uday

Keyword(s):

Machine Learning ◽

Feature Selection ◽

Slope Failure ◽

Feature Selection Method ◽

Failure Prediction ◽

Selection Method ◽

Support Vector ◽

Selection Methods ◽

Slope Failures ◽

Causal Factors

Landslide disaster risk reduction necessitates the investigation of different geotechnical causal factors for slope failures. Machine learning (ML) techniques have been proposed to study causal factors across many application areas. However, the development of ensemble ML techniques for identifying the geotechnical causal factors for slope failures and their subsequent prediction has lacked in literature. The primary goal of this research is to develop and evaluate novel feature selection methods for identifying causal factors for slope failures and assess the potential of ensemble and individual ML techniques for slope failure prediction. Twenty-one geotechnical causal factors were obtained from 60 sites (both landslide and non-landslide) spread across a landslide-prone area in Mandi, India. Relevant causal factors were evaluated by developing a novel ensemble feature selection method that involved an average of different individual feature selection methods like correlation, information-gain, gain-ratio, OneR, and F-ratio. Furthermore, different ensemble ML techniques (Random Forest (RF), AdaBoost (AB), Bagging, Stacking, and Voting) and individual ML techniques (Bayesian network (BN), decision tree (DT), multilayer perceptron (MLP), and support vector machine (SVM)) were calibrated to 70% of the locations and tested on 30% of the sites. The ensemble feature selection method yielded six major contributing parameters to slope failures: relative compaction, porosity, saturated permeability, slope angle, angle of the internal friction, and in-situ moisture content. Furthermore, the ensemble RF and AB techniques performed the best compared to other ensemble and individual ML techniques on test data. The present study discusses the implications of different causal factors for slope failure prediction.

Download Full-text

A fuzzy gaussian rank aggregation ensemble feature selection method for microarray data

International Journal of Knowledge-based and Intelligent Engineering Systems ◽

10.3233/kes-190134 ◽

2021 ◽

Vol 24 (4) ◽

pp. 289-301

Author(s):

B. Venkatesh ◽

J. Anuradha

Keyword(s):

Feature Selection ◽

Microarray Data ◽

Classification Accuracy ◽

Performance Metrics ◽

Feature Selection Method ◽

Selection Method ◽

Support Vector ◽

Svm Classifier ◽

Binary Particle Swarm Optimization ◽

Selection Methods

In Microarray Data, it is complicated to achieve more classification accuracy due to the presence of high dimensions, irrelevant and noisy data. And also It had more gene expression data and fewer samples. To increase the classification accuracy and the processing speed of the model, an optimal number of features need to extract, this can be achieved by applying the feature selection method. In this paper, we propose a hybrid ensemble feature selection method. The proposed method has two phases, filter and wrapper phase in filter phase ensemble technique is used for aggregating the feature ranks of the Relief, minimum redundancy Maximum Relevance (mRMR), and Feature Correlation (FC) filter feature selection methods. This paper uses the Fuzzy Gaussian membership function ordering for aggregating the ranks. In wrapper phase, Improved Binary Particle Swarm Optimization (IBPSO) is used for selecting the optimal features, and the RBF Kernel-based Support Vector Machine (SVM) classifier is used as an evaluator. The performance of the proposed model are compared with state of art feature selection methods using five benchmark datasets. For evaluation various performance metrics such as Accuracy, Recall, Precision, and F1-Score are used. Furthermore, the experimental results show that the performance of the proposed method outperforms the other feature selection methods.

Download Full-text

Evaluating Variable Selection and Machine Learning Algorithms for Estimating Forest Heights by Combining Lidar and Hyperspectral Data

ISPRS International Journal of Geo-Information ◽

10.3390/ijgi9090507 ◽

2020 ◽

Vol 9 (9) ◽

pp. 507

Author(s):

Sanjiwana Arjasakusuma ◽

Sandiaga Swahyu Kusuma ◽

Stuart Phinn

Keyword(s):

Machine Learning ◽

Feature Selection ◽

Learning Algorithms ◽

Principal Component ◽

Hyperspectral Data ◽

Machine Learning Algorithms ◽

Gradient Boosting ◽

Support Vector ◽

Forest Height ◽

Extreme Gradient Boosting

Machine learning has been employed for various mapping and modeling tasks using input variables from different sources of remote sensing data. For feature selection involving high- spatial and spectral dimensionality data, various methods have been developed and incorporated into the machine learning framework to ensure an efficient and optimal computational process. This research aims to assess the accuracy of various feature selection and machine learning methods for estimating forest height using AISA (airborne imaging spectrometer for applications) hyperspectral bands (479 bands) and airborne light detection and ranging (lidar) height metrics (36 metrics), alone and combined. Feature selection and dimensionality reduction using Boruta (BO), principal component analysis (PCA), simulated annealing (SA), and genetic algorithm (GA) in combination with machine learning algorithms such as multivariate adaptive regression spline (MARS), extra trees (ET), support vector regression (SVR) with radial basis function, and extreme gradient boosting (XGB) with trees (XGbtree and XGBdart) and linear (XGBlin) classifiers were evaluated. The results demonstrated that the combinations of BO-XGBdart and BO-SVR delivered the best model performance for estimating tropical forest height by combining lidar and hyperspectral data, with R2 = 0.53 and RMSE = 1.7 m (18.4% of nRMSE and 0.046 m of bias) for BO-XGBdart and R2 = 0.51 and RMSE = 1.8 m (15.8% of nRMSE and −0.244 m of bias) for BO-SVR. Our study also demonstrated the effectiveness of BO for variables selection; it could reduce 95% of the data to select the 29 most important variables from the initial 516 variables from lidar metrics and hyperspectral data.

Download Full-text

Multivariate Analysis and Machine Learning for Ripeness Classification of Cape Gooseberry Fruits

Processes ◽

10.3390/pr7120928 ◽

2019 ◽

Vol 7 (12) ◽

pp. 928 ◽

Cited By ~ 2

Author(s):

Miguel De-la-Torre ◽

Omar Zatarain ◽

Himer Avila-George ◽

Mirna Muñoz ◽

Jimy Oblitas ◽

...

Keyword(s):

Machine Learning ◽

Principal Component Analysis ◽

Feature Selection ◽

Principal Component ◽

Component Analysis ◽

Support Vector ◽

Color Spaces ◽

Combination Methods ◽

Fruit Samples ◽

Cape Gooseberry

This paper explores five multivariate techniques for information fusion on sorting the visual ripeness of Cape gooseberry fruits (principal component analysis, linear discriminant analysis, independent component analysis, eigenvector centrality feature selection, and multi-cluster feature selection.) These techniques are applied to the concatenated channels corresponding to red, green, and blue (RGB), hue, saturation, value (HSV), and lightness, red/green value, and blue/yellow value (L*a*b) color spaces (9 features in total). Machine learning techniques have been reported for sorting the Cape gooseberry fruits’ ripeness. Classifiers such as neural networks, support vector machines, and nearest neighbors discriminate on fruit samples using different color spaces. Despite the color spaces being equivalent up to a transformation, a few classifiers enable better performances due to differences in the pixel distribution of samples. Experimental results show that selection and combination of color channels allow classifiers to reach similar levels of accuracy; however, combination methods still require higher computational complexity. The highest level of accuracy was obtained using the seven-dimensional principal component analysis feature space.

Download Full-text

Identification of Novel COVID-19 Biomarkers by Multiple Feature Selection Strategies

Computational and Mathematical Methods in Medicine ◽

10.1155/2021/2203636 ◽

2021 ◽

Vol 2021 ◽

pp. 1-8

Author(s):

Shuai Zhang ◽

Renliang Qu ◽

Pengyan Wang ◽

Shenghan Wang

Keyword(s):

Feature Selection ◽

Expression Profiles ◽

Feature Selection Method ◽

Principal Component ◽

Enrichment Analysis ◽

Functional Enrichment ◽

Nucleic Acid Detection ◽

Support Vector ◽

New Biomarkers ◽

Optimal Feature

Coronavirus disease 2019 (COVID-19) arising from severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has resulted in a global pandemic since its first report in December 2019. So far, SARS-CoV-2 nucleic acid detection has been deemed as the golden standard of COVID-19 diagnosis. However, this detection method often leads to false negatives, thus triggering missed COVID-19 diagnosis. Therefore, it is urgent to find new biomarkers to increase the accuracy of COVID-19 diagnosis. To explore new biomarkers of COVID-19 in this study, expression profiles were firstly accessed from the GEO database. On this basis, 500 feature genes were screened by the minimum-redundancy maximum-relevancy (mRMR) feature selection method. Afterwards, the incremental feature selection (IFS) method was used to choose a classifier with the best performance from different feature gene-based support vector machine (SVM) classifiers. The corresponding 66 feature genes were set as the optimal feature genes. Lastly, the optimal feature genes were subjected to GO functional enrichment analysis, principal component analysis (PCA), and protein-protein interaction (PPI) network analysis. All in all, it was posited that the 66 feature genes could effectively classify positive and negative COVID-19 and work as new biomarkers of the disease.

Download Full-text

Machine Learning-Enriched Lamb Wave Approaches for Automated Damage Detection

Sensors ◽

10.3390/s20061790 ◽

2020 ◽

Vol 20 (6) ◽

pp. 1790

Author(s):

Zi Zhang ◽

Hong Pan ◽

Xingyu Wang ◽

Zhibin Lin

Keyword(s):

Machine Learning ◽

Feature Extraction ◽

Feature Selection ◽

Damage Detection ◽

Lamb Wave ◽

Lamb Waves ◽

Feature Selection Method ◽

Support Vector ◽

Time Frequency ◽

Damage States

Lamb wave approaches have been accepted as efficiently non-destructive evaluations in structural health monitoring for identifying damage in different states. Despite significant efforts in signal process of Lamb waves, physics-based prediction is still a big challenge due to complexity nature of the Lamb wave when it propagates, scatters and disperses. Machine learning in recent years has created transformative opportunities for accelerating knowledge discovery and accurately disseminating information where conventional Lamb wave approaches cannot work. Therefore, the learning framework was proposed with a workflow from dataset generation, to sensitive feature extraction, to prediction model for lamb-wave-based damage detection. A total of 17 damage states in terms of different damage type, sizes and orientations were designed to train the feature extraction and sensitive feature selection. A machine learning method, support vector machine (SVM), was employed for the learning model. A grid searching (GS) technique was adopted to optimize the parameters of the SVM model. The results show that the machine learning-enriched Lamb wave-based damage detection method is an efficient and accuracy wave to identify the damage severity and orientation. Results demonstrated that different features generated from different domains had certain levels of sensitivity to damage, while the feature selection method revealed that time-frequency features and wavelet coefficients exhibited the highest damage-sensitivity. These features were also much more robust to noise. With increase of noise, the accuracy of the classification dramatically dropped.

Download Full-text

A Study of Feature Selection and Dimensionality Reduction Methods for Classification-Based Phishing Detection System

International Journal of Information Retrieval Research ◽

10.4018/ijirr.2021010101 ◽

2021 ◽

Vol 11 (1) ◽

pp. 1-35

Author(s):

Amit Singh ◽

Abhishek Tiwari

Keyword(s):

Machine Learning ◽

Feature Selection ◽

Dimensionality Reduction ◽

Detection System ◽

Parallel Evolution ◽

Feature Selection Method ◽

Sensitive Information ◽

Selection Methods ◽

Survey Paper ◽

Reduction Methods

Phishing was introduced in 1996, and now phishing is the biggest cybercrime challenge. Phishing is an abstract way to deceive users over the internet. Purpose of phishers is to extract the sensitive information of the user. Researchers have been working on solutions of phishing problem, but the parallel evolution of cybercrime techniques have made it a tough nut to crack. Recently, machine learning-based solutions are widely adopted to tackle the menace of phishing. This survey paper studies various feature selection method and dimensionality reduction methods and sees how they perform with machine learning-based classifier. The selection of features is vital for developing a good performance machine learning model. This work is comparing three broad categories of feature selection methods, namely filter, wrapper, and embedded feature selection methods, to reduce the dimensionality of data. The effectiveness of these methods has been assessed on several machine learning classifiers using k-fold cross-validation score, accuracy, precision, recall, and time.

Download Full-text

Implementasi teknik seleksi fitur pada klasifikasi malware Android menggunakan support vector machine (SVM)

Repositor ◽

10.22219/repositor.v1i1.1 ◽

2019 ◽

Vol 1 (1) ◽

pp. 1

Author(s):

Hendra Saputra ◽

Setio Basuki ◽

Mahar Faiqurahman

Keyword(s):

Machine Learning ◽

Support Vector Machine ◽

Feature Selection ◽

Feature Selection Method ◽

Selection Method ◽

Support Vector ◽

Chi Square ◽

Android Malware ◽

Correlation Based Feature Selection ◽

Selection Of

AbstrakPertumbuhan Malware Android telah meningkat secara signifikan seiring dengan majunya jaman dan meninggkatnya keragaman teknik dalam pengembangan Android. Teknik Machine Learning adalah metode yang saat ini bisa kita gunakan dalam memodelkan pola fitur statis dan dinamis dari Malware Android. Dalam tingkat keakurasian dari klasifikasi jenis Malware peneliti menghubungkan antara fitur aplikasi dengan fitur yang dibutuhkan dari setiap jenis kategori Malware. Kategori jenis Malware yang digunakan merupakan jenis Malware yang banyak beredar saat ini. Untuk mengklasifikasi jenis Malware pada penelitian ini digunakan Support Vector Machine (SVM). Jenis SVM yang akan digunakan adalah class SVM one against one menggunakan Kernel RBF. Fitur yang akan dipakai dalam klasifikasi ini adalah Permission dan Broadcast Receiver. Untuk meningkatkan akurasi dari hasil klasifikasi pada penelitian ini digunakan metode Seleksi Fitur. Seleksi Fitur yang digunakan ialah Correlation-based Feature Selection (CSF), Gain Ratio (GR) dan Chi-Square (CHI). Hasil dari Seleksi Fitur akan di evaluasi bersama dengan hasil yang tidak menggunakan Seleksi Fitur. Akurasi klasifikasi Seleksi Fitur CFS menghasilkan akurasi sebesar 90.83% , GR dan CHI sebesar 91.25% dan data yang tidak menggunakan Seleksi Fitur sebesar 91.67%. Hasil dari pengujian menunjukan bahwa Permission dan Broadcast Receiver bisa digunakan dalam mengklasifikasi jenis Malware, akan tetapi metode Seleksi Fitur yang digunakan mempunyai akurasi yang berada sedikit dibawah data yang tidak menggunakan Seleksi Fitur. Kata kunci: klasifikasi malware android, seleksi fitur, SVM dan multi class SVM one agains one Abstract Android Malware has growth significantly along with the advance of the times and the increasing variety of technique in the development of Android. Machine Learning technique is a method that now we can use in the modeling the pattern of a static and dynamic feature of Android Malware. In the level of accuracy of the Malware type classification, the researcher connect between the application feature with the feature required by each types of Malware category. The category of malware used is a type of Malware that many circulating today, to classify the type of Malware in this study used Support Vector Machine (SVM). The SVM type wiil be used is class SVM one against one using the RBF Kernel. The feature will be used in this classification are the Permission and Broadcast Receiver. To improve the accuracy of the classification result in this study used Feature Selection method. Selection of feature used are Correlation-based Feature Selection (CFS), Gain Ratio (GR) and Chi-Square (CHI). Result from Feature Selection will be evaluated together with result that not use Feature Selection. Accuracy Classification Feature Selection CFS result accuracy of 90.83%, GR and CHI of 91.25% and data that not use Feature Selection of 91.67%. The result of testing indicate that permission and broadcast receiver can be used in classyfing type of Malware, but the Feature Selection method that used have accuracy is a little below the data that are not using Feature Selection. Keywords: Classification Android Malware, Feature Selection, SVM and Multi Class SVM one against one

Download Full-text