A multilayer perceptron neural network-based approach for the identification of responsiveness to interferon therapy in multiple sclerosis patients

Calcagno, Giuseppe; Staiano, Antonino; Fortunato, Giuliana; Morra, V. Brescia; Salvatore, Elena; Liguori, Rosario; Capone, Silvana; Filla, Alessandro; Longo, Giuseppe; Sacchetti, Lucia

doi:10.1016/j.ins.2010.07.004

Cited by 31 publications

(18 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Handling missing values can be a challenge as it requires a careful examination of the data to identify the type and pattern of missingness, and also have a clear understanding of the most appropriate imputation method. Gaps in water quality data-sets may arise due to several reasons, among which are imperfect data entry, equipment error, loss of sample before analysis and incorrect measurements [37]. Missing values complicate data analysis, cause loss of statistical efficiency and reduces statistical estimation power [37][38][39].…”

Section: Missing Valuesmentioning

confidence: 99%

“…Gaps in water quality data-sets may arise due to several reasons, among which are imperfect data entry, equipment error, loss of sample before analysis and incorrect measurements [37]. Missing values complicate data analysis, cause loss of statistical efficiency and reduces statistical estimation power [37][38][39]. For data intended for time-series analysis and model building, gaps become a significant obstacle since both generally require continuous data [40,41].…”

Section: Missing Valuesmentioning

confidence: 99%

See 1 more Smart Citation

Validity and Errors in Water Quality Data — A Review

Rangeti¹,

Dzwairo²,

Barratt³

et al. 2015

Research and Practices in Water Quality

View full text Add to dashboard Cite

Section: Missing Valuesmentioning

confidence: 99%

Section: Missing Valuesmentioning

confidence: 99%

Validity and Errors in Water Quality Data — A Review

Rangeti¹,

Dzwairo²,

Barratt³

et al. 2015

Research and Practices in Water Quality

View full text Add to dashboard Cite

“…Neural networks [24,26,5] and support vector machines [3] are popular, although [24] asserts that neural networks are unable to handle incomplete data. GWAS data will often include samples and SNPs with missing genotype information, which limits the usefulness of neural network approaches.…”

Section: Previous Statistical and Artificial Intelligence Researchmentioning

confidence: 99%

Ant colony optimisation to identify genetic variant association with type 2 diabetes

Christmas

Keedwell

Frayling

et al. 2011

Information Sciences

View full text Add to dashboard Cite

“…a small number of samples, and effectively identifying the most significant differentially expressed genes under different conditions is prominent (Xiong, Fang & Zhao, 2001). The selected genes are very useful in clinical applications such as recognizing diseased profiles (Calcagno et al, 2010;Staiano et al, 2013;Di Taranto et al, 2015;Camastra, Di Taranto & Staiano, 2015), nonetheless, because of its high costs, the number of experiments that can be used for classification purposes is usually limited due to the small number of samples compared to the large number of genes in an experiment, that gives rise to the Curse of Dimensionality problem (Friedman, Hastie & Tibshirani, 2001), which challenges the classification as well as other data analysis tasks (Staiano et al, 2004;Ciaramella et al, 2008). Furthermore, microarray data are usually not immune from several issues, such as sensitivity, accuracy, specificity, reproducibility of results, and noisy data (Draghici et al, 2006).…”

Section: Introductionmentioning

confidence: 99%

A Sparse-Modeling Based Approach for Class Specific Feature Selection

Nardone

Ciaramella

Staiano

2019

PeerJ Computer Science

Self Cite

View full text Add to dashboard Cite

In this work, we propose a novel Feature Selection framework called Sparse-Modeling Based Approach for Class Specific Feature Selection (SMBA-CSFS), that simultaneously exploits the idea of Sparse Modeling and Class-Specific Feature Selection. Feature selection plays a key role in several fields (e.g., computational biology), making it possible to treat models with fewer variables which, in turn, are easier to explain, by providing valuable insights on the importance of their role, and likely speeding up the experimental validation. Unfortunately, also corroborated by the no free lunch theorems, none of the approaches in literature is the most apt to detect the optimal feature subset for building a final model, thus it still represents a challenge. The proposed feature selection procedure conceives a two-step approach: (a) a sparse modeling-based learning technique is first used to find the best subset of features, for each class of a training set; (b) the discovered feature subsets are then fed to a class-specific feature selection scheme, in order to assess the effectiveness of the selected features in classification tasks. To this end, an ensemble of classifiers is built, where each classifier is trained on its own feature subset discovered in the previous phase, and a proper decision rule is adopted to compute the ensemble responses. In order to evaluate the performance of the proposed method, extensive experiments have been performed on publicly available datasets, in particular belonging to the computational biology field where feature selection is indispensable: the acute lymphoblastic leukemia and acute myeloid leukemia, the human carcinomas, the human lung carcinomas, the diffuse large B-cell lymphoma, and the malignant glioma. SMBA-CSFS is able to identify/retrieve the most representative features that maximize the classification accuracy. With top 20 and 80 features, SMBA-CSFS exhibits a promising performance when compared to its competitors from literature, on all considered datasets, especially those with a higher number of features. Experiments show that the proposed approach may outperform the state-of-the-art methods when the number of features is high. For this reason, the introduced approach proposes itself for selection and classification of data with a large number of features and classes.

show abstract

A multilayer perceptron neural network-based approach for the identification of responsiveness to interferon therapy in multiple sclerosis patients

Cited by 31 publications

References 30 publications

Validity and Errors in Water Quality Data — A Review

Validity and Errors in Water Quality Data — A Review

Ant colony optimisation to identify genetic variant association with type 2 diabetes

A Sparse-Modeling Based Approach for Class Specific Feature Selection

Contact Info

Product

Resources

About