Improving survival prediction using a novel feature selection and feature reduction framework based on the integration of clinical and molecular data

2019 ◽  
Author(s):  
Lisa Neums ◽  
Richard Meier ◽  
Devin C. Koestler ◽  
Jeffrey A. Thompson
Keyword(s):  
Feature Selection ◽  
Molecular Data ◽  
Feature Reduction ◽  
Survival Prediction

Identification of 6 gene markers for survival prediction in osteosarcoma cases based on multi-omics analysis

2021 ◽  
pp. 153537022199201
Author(s):  
Runmin Li ◽  
Guosheng Wang ◽  
ZhouJie Wu ◽  
HuaGuang Lu ◽  
Gen Li ◽  
...  
Keyword(s):  
Feature Selection ◽  
Cox Regression ◽  
Cancer Genomics ◽  
Predictive Performance ◽  
Training Group ◽  
Gene Expression Omnibus ◽  
Survival Prediction ◽  
Screening Process ◽  
Gene Markers ◽  
Validation Set

Multiple-omics sequencing information with high-throughput has laid a solid foundation to identify genes associated with cancer prognostic process. Multiomics information study is capable of revealing the cancer occurring and developing system according to several aspects. Currently, the prognosis of osteosarcoma is still poor, so a genetic marker is needed for predicting the clinically related overall survival result. First, Office of Cancer Genomics (OCG Target) provided RNASeq, copy amount variations information, and clinically related follow-up data. Genes associated with prognostic process and genes exhibiting copy amount difference were screened in the training group, and the mentioned genes were integrated for feature selection with least absolute shrinkage and selection operator (Lasso). Eventually, effective biomarkers received the screening process. Lastly, this study built and demonstrated one gene-associated prognosis mode according to the set of the test and gene expression omnibus validation set; 512 prognosis-related genes ( P < 0.01), 336 copies of amplified genes ( P < 0.05), and 36 copies of deleted genes ( P < 0.05) were obtained, and those genes of the mentioned genomic variants display close associations with tumor occurring and developing mechanisms. This study generated 10 genes for candidates through the integration of genomic variant genes as well as prognosis-related genes. Six typical genes (i.e. MYC, CHIC2, CCDC152, LYL1, GPR142, and MMP27) were obtained by Lasso feature selection and stepwise multivariate regression study, many of which are reported to show a relationship to tumor progressing process. The authors conducted Cox regression study for building 6-gene sign, i.e. one single prognosis-related element, in terms of cases carrying osteosarcoma. In addition, the samples were able to be risk stratified in the training group, test set, and externally validating set. The AUC of five-year survival according to the training group and validation set reached over 0.85, with superior predictive performance as opposed to the existing researches. Here, 6-gene sign was built to be new prognosis-related marking elements for assessing osteosarcoma cases’ surviving state.

scholarly journals A hybrid sentiment analysis approach using black widow optimization based feature selection

2021 ◽  
Author(s):  
Anand Joseph Daniel ◽  
◽  
M Janaki Meena ◽  
Keyword(s):  
Feature Selection ◽  
Sentiment Analysis ◽  
Performance Metrics ◽  
Computation Time ◽  
Online Reviews ◽  
Reduction Technique ◽  
Feature Reduction ◽  
Analysis Approach ◽  
Black Widow ◽  
Feature Selection Technique

With the massive development of Internet technologies and e-commerce technology, people rely on the product reviews provided by users through web. Sentiment analysis of online reviews has become a mainstream way for businesses on e-commerce platforms to satisfy the customers. This paper proposes a novel hybrid framework with Black Widow Optimization (BWO) based feature reduction technique which combines the merits of both machine learning and lexicon-based approaches to attain better scalability and accuracy. The scalability problem arises due to noisy, irrelevant and unique features present in the extracted features from proposed approach, which can be eliminated by adopting an effective feature reduction technique. In our proposed BWO approach, without changing the accuracy (90%), the feature-set size is reduced up to 43%. The proposed feature selection technique outperforms other commonly used Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) based feature selection techniques with reduced computation time of 21 sec. Moreover, our sentiment analysis approach is analyzed using performance metrics such as precision, recall, F-measure, and computation time. Many organizations can use these online reviews to make well-informed decisions towards the users’ interests and preferences to enhance customer satisfaction, product quality and to find the aspects to improve the products, thereby to generate more profits.

scholarly journals Extracting salient features for network intrusion detection using machine learning methods

2014 ◽  
Vol 52 ◽  
Author(s):  
Ralf C. Staudemeyer ◽  
Christian W. Omlin
Keyword(s):  
Feature Selection ◽  
Intrusion Detection ◽  
Information Gain ◽  
Selection Process ◽  
Denial Of Service ◽  
Reduction Process ◽  
Feature Reduction ◽  
General Nature ◽  
Network Intrusion ◽  
Salient Features

This work presents a data preprocessing and feature selection framework to support data mining and network security experts in minimal feature set selection of intrusion detection data. This process is supported by detailed visualisation and examination of class distributions. Distribution histograms, scatter plots and information gain are presented as supportive feature reduction tools. The feature reduction process applied is based on decision tree pruning and backward elimination. This paper starts with an analysis of the KDD Cup '99 datasets and their potential for feature reduction. The dataset consists of connection records with 41 features whose relevance for intrusion detection are not clear. All traffic is either classified `normal' or into the four attack types denial-of-service, network probe, remote-to-local or user-to-root. Using our custom feature selection process, we show how we can significantly reduce the number features in the dataset to a few salient features. We conclude by presenting minimal sets with 4--8 salient features for two-class and multi-class categorisation for detecting intrusions, as well as for the detection of individual attack classes; the performance using a static classifier compares favourably to the performance using all features available. The suggested process is of general nature and can be applied to any similar dataset.

scholarly journals Feature Selection Models Based on Hybrid Firefly Algorithm with Mutation Operator for Network Intrusion Detection

2021 ◽  
Vol 14 (1) ◽  
pp. 192-202
Author(s):  
Karrar Alwan ◽  
◽  
Ahmed AbuEl-Atta ◽  
Hala Zayed ◽  
◽  
...  
Keyword(s):  
Feature Selection ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Firefly Algorithm ◽  
Detection System ◽  
Binary Classification ◽  
Feature Reduction ◽  
Detection Accuracy ◽  
Multi Classification ◽  
Modified Firefly Algorithm

Accurate intrusion detection is necessary to preserve network security. However, developing efficient intrusion detection system is a complex problem due to the nonlinear nature of the intrusion attempts, the unpredictable behaviour of network traffic, and the large number features in the problem space. Hence, selecting the most effective and discriminating feature is highly important. Additionally, eliminating irrelevant features can improve the detection accuracy as well as reduce the learning time of machine learning algorithms. However, feature reduction is an NPhard problem. Therefore, several metaheuristics have been employed to determine the most effective feature subset within reasonable time. In this paper, two intrusion detection models are built based on a modified version of the firefly algorithm to achieve the feature selection task. The first and, the second models have been used for binary and multiclass classification, respectively. The modified firefly algorithm employed a mutation operation to avoid trapping into local optima through enhancing the exploration capabilities of the original firefly. The significance of the selected features is evaluated using a Naïve Bayes classifier over a benchmark standard dataset, which contains different types of attacks. The obtained results revealed the superiority of the modified firefly algorithm against the original firefly algorithm in terms of the classification accuracy and the number of selected features under different scenarios. Additionally, the results assured the superiority of the proposed intrusion detection system against other recently proposed systems in both binary classification and multi-classification scenarios. The proposed system has 96.51% and 96.942% detection accuracy in binary classification and multi-classification, respectively. Moreover, the proposed system reduced the number of attributes from 41 to 9 for binary classification and to 10 for multi-classification.

scholarly journals A Novel Sentiment Analysis for Amazon Data with TSA based Feature Selection

2021 ◽  
Vol 22 (1) ◽  
pp. 53-66
Author(s):  
D. Anand Joseph Daniel ◽  
M. Janaki Meena
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Sentiment Analysis ◽  
User Satisfaction ◽  
Performance Metrics ◽  
Computation Time ◽  
Feature Reduction ◽  
Training Data ◽  
Product Reviews ◽  
Online Product Reviews

Sentiment analysis of online product reviews has become a mainstream way for businesses on e-commerce platforms to promote their products and improve user satisfaction. Hence, it is necessary to construct an automatic sentiment analyser for automatic identification of sentiment polarity of the online product reviews. Traditional lexicon-based approaches used for sentiment analysis suffered from several accuracy issues while machine learning techniques require labelled training data. This paper introduces a hybrid sentiment analysis framework to bond the gap between both machine learning and lexicon-based approaches. A novel tunicate swarm algorithm (TSA) based feature reduction is integrated with the proposed hybrid method to solve the scalability issue that arises due to a large feature set. It reduces the feature set size to 43% without changing the accuracy (93%). Besides, it improves the scalability, reduces the computation time and enhances the overall performance of the proposed framework. From experimental analysis, it can be observed that TSA outperforms existing feature selection techniques such as particle swarm optimization and genetic algorithm. Moreover, the proposed approach is analysed with performance metrics such as recall, precision, F1-score, feature size and computation time.

scholarly journals Feature Selection Based on Binary Tree Growth Algorithm for the Classification of Myoelectric Signals

Machines ◽  
2018 ◽  
Vol 6 (4) ◽  
pp. 65 ◽  
Author(s):  
Jingwei Too ◽  
Abdul Abdullah ◽  
Norhashimah Mohd Saad ◽  
Nursabillilah Mohd Ali
Keyword(s):  
Feature Selection ◽  
Tree Growth ◽  
Binary Tree ◽  
Feature Vector ◽  
Classification Performance ◽  
Feature Reduction ◽  
Feature Subset ◽  
Selection Methods ◽  
Time Frequency ◽  
Mutation Operators

Electromyography (EMG) has been widely used in rehabilitation and myoelectric prosthetic applications. However, a recent increment in the number of EMG features has led to a high dimensional feature vector. This in turn will degrade the classification performance and increase the complexity of the recognition system. In this paper, we have proposed two new feature selection methods based on a tree growth algorithm (TGA) for EMG signals classification. In the first approach, two transfer functions are implemented to convert the continuous TGA into a binary version. For the second approach, the swap, crossover, and mutation operators are introduced in a modified binary tree growth algorithm for enhancing the exploitation and exploration behaviors. In this study, short time Fourier transform (STFT) is employed to transform the EMG signals into time-frequency representation. The features are then extracted from the STFT coefficient and form a feature vector. Afterward, the proposed feature selection methods are applied to evaluate the best feature subset from a large available feature set. The experimental results show the superiority of MBTGA not only in terms of feature reduction, but also the classification performance.

Multi-stage modeling using fuzzy multi-criteria feature selection to improve survival prediction of ICU septic shock patients

2012 ◽  
Vol 39 (16) ◽  
pp. 12332-12339 ◽  
Author(s):  
Federico Cismondi ◽  
Abigail L. Horn ◽  
André S. Fialho ◽  
Susana M. Vieira ◽  
Shane R. Reti ◽  
...  
Keyword(s):  
Septic Shock ◽  
Feature Selection ◽  
Survival Prediction ◽  
Multi Stage ◽  
Stage Modeling

scholarly journals Relevant and Non-Redundant Feature Selection for Cancer Classification and Subtype Detection

Cancers ◽  
2021 ◽  
Vol 13 (17) ◽  
pp. 4297
Author(s):  
Pratip Rana ◽  
Phuc Thai ◽  
Thang Dinh ◽  
Preetam Ghosh
Keyword(s):  
Feature Selection ◽  
Gene Selection ◽  
False Negative ◽  
Multiclass Classification ◽  
Feature Reduction ◽  
Control Group ◽  
Normal Sample ◽  
Classification Problems ◽  
Column Subset Selection

Biologists seek to identify a small number of significant features that are important, non-redundant, and relevant from diverse omics data. For example, statistical methods such as LIMMA and DEseq distinguish differentially expressed genes between a case and control group from the transcript profile. Researchers also apply various column subset selection algorithms on genomics datasets for a similar purpose. Unfortunately, genes selected by such statistical or machine learning methods are often highly co-regulated, making their performance inconsistent. Here, we introduce a novel feature selection algorithm that selects highly disease-related and non-redundant features from a diverse set of omics datasets. We successfully applied this algorithm to three different biological problems: (a) disease-to-normal sample classification; (b) multiclass classification of different disease samples; and (c) disease subtypes detection. Considering the classification of ROC-AUC, false-positive, and false-negative rates, our algorithm outperformed other gene selection and differential expression (DE) methods for all six types of cancer datasets from TCGA considered here for binary and multiclass classification problems. Moreover, genes picked by our algorithm improved the disease subtyping accuracy for four different cancer types over state-of-the-art methods. Hence, we posit that our proposed feature reduction method can support the community to solve various problems, including the selection of disease-specific biomarkers, precision medicine design, and disease sub-type detection.

scholarly journals An Integrated Deep Network for Cancer Survival Prediction Using Omics Data

2021 ◽  
Vol 4 ◽  
Author(s):  
Hamid Reza Hassanzadeh ◽  
May D. Wang
Keyword(s):  
Cancer Survival ◽  
Molecular Data ◽  
Survival Prediction ◽  
Cellular Mechanisms ◽  
Large Size ◽  
Learning Techniques ◽  
Proper Training ◽  
Cancer Types ◽  
High Risk Cancer ◽  
Prediction Problems

As a highly sophisticated disease that humanity faces, cancer is known to be associated with dysregulation of cellular mechanisms in different levels, which demands novel paradigms to capture informative features from different omics modalities in an integrated way. Successful stratification of patients with respect to their molecular profiles is a key step in precision medicine and in tailoring personalized treatment for critically ill patients. In this article, we use an integrated deep belief network to differentiate high-risk cancer patients from the low-risk ones in terms of the overall survival. Our study analyzes RNA, miRNA, and methylation molecular data modalities from both labeled and unlabeled samples to predict cancer survival and subsequently to provide risk stratification. To assess the robustness of our novel integrative analytics, we utilize datasets of three cancer types with 836 patients and show that our approach outperforms the most successful supervised and semi-supervised classification techniques applied to the same cancer prediction problems. In addition, despite the preconception that deep learning techniques require large size datasets for proper training, we have illustrated that our model can achieve better results for moderately sized cancer datasets.

Sign in / Sign up

Export Citation Format

Share Document