Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Feature selection”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 469 records · Page 26Linked to original sources
PubMed2002

Relevant EEG features for the classification of spontaneous motor-related tasks.

There is a growing interest in the use of physiological signals for communication and operation of devices for the severely motor disabled as well as for healthy people. A few groups around the world have developed brain-computer interfaces (BCIs) that rely upon the recognition of motor-related tasks (i.e., imagination of movements) from on-line EEG signals. In this paper we seek to find and analyze the set of relevant EEG features that best differentiate spontaneous motor-related mental tasks from each other. This study empirically demonstrates the benefits of heuristic feature selection methods for EEG-based classification of mental tasks. In particular, it is shown that the classifier performance improves for all the considered subjects with only a small proportion of features. Thus, the use of just those relevant features increases the efficiency of the brain interfaces and, most importantly, enables a greater level of adaptation of the personal BCI to the individual user.

Brain Mapping↗
PubMed2026

Linking MRI radiomics to transcriptomics-based radiosensitivity in lower-grade glioma: A radiogenomic framework.

BACKGROUND: RSI is a transcriptomics-based biomarker associated with radiotherapy outcomes, but its clinical application is constrained by the requirement for tumor tissue and RNA sequencing. This study investigates whether MRI-derived radiomic features can reflect RSI-defined intrinsic radiosensitivity in lower-grade glioma.This addresses a critical gap arising from the limited availability of matched imaging and genomic data in routine clinical practice. METHODS: MRI-derived radiomic features were extracted from FLAIR images of lower-grade glioma patients obtained from TCIA and matched with transcriptomic data from TCGA. A total of 107 patients with both MRI and RNA sequencing data were included in the radiogenomic analysis. Radiomic features were ranked using a Borda-based ensemble feature selection strategy. Five supervised machine-learning classifiers were trained to predict RSI-based radiosensitivity classification, and model interpretability was assessed using SHAP within radiogenomic framework. RESULTS: Classification performance increased with feature number and stabilized at compact subset of 13 radiomic features. Logistic regression showed stable performance with an AUC of 0.82 (95 % CI: 0.71-0.93). SHAP analysis indicated that heterogeneity-related texture features were dominant contributors to model predictions, with many associated with the RR phenotype, while others were linked to the RS phenotype. CONCLUSION: An MRI-based radiomic signature enables non-invasive prediction of RSI-defined radiosensitivity in lower-grade glioma. Rather than offering an immediately deployable clinical tool, this study establishes a proof-of-concept radiogenomic framework demonstrating that intrinsic radiosensitivity, traditionally assessed through invasive molecular assays, can be approximated using quantitative imaging features. These findings highlight the potential of imaging-based radiosensitivity assessment and provide a foundation for future radiogenomic investigations.

Lower-grade glioma↗
PubMed1990

Interaction of porphyrin-containing macrotetracyclic receptor molecule with single-stranded and double-stranded polynucleotides. A photophysical study.

Photophysical methods have been used to study the interaction with nucleic acids of a macrotetracyclic cryptand molecule, Pbiph, containing a porphyrin groups, two macrocycles, and a biphenyl bridge. Pbiph binds with a higher affinity to single-stranded polynucleotides than to double-stranded ones. This selectivity, observed by binding and competition studies, using absorption and fluorescence spectroscopy, is pH dependent. Pbiph does not intercalate into double helices and is suggested to bind into the major groove. These features, selective single-strand binding and nonintercalation, are attributed to steric effects of the bulky Pbiph molecule, resulting from the macropolyclic cryptand cage structure.

DNA↗
PubMed2006

Clustering threshold gradient descent regularization: with applications to microarray studies.

MOTIVATION: An important goal of microarray studies is to discover genes that are associated with clinical outcomes, such as disease status and patient survival. While a typical experiment surveys gene expressions on a global scale, there may be only a small number of genes that have significant influence on a clinical outcome. Moreover, expression data have cluster structures and the genes within a cluster have correlated expressions and coordinated functions, but the effects of individual genes in the same cluster may be different. Accordingly, we seek to build statistical models with the following properties. First, the model is sparse in the sense that only a subset of the parameter vector is non-zero. Second, the cluster structures of gene expressions are properly accounted for. RESULTS: For gene expression data without pathway information, we divide genes into clusters using commonly used methods, such as K-means or hierarchical approaches. The optimal number of clusters is determined using the Gap statistic. We propose a clustering threshold gradient descent regularization (CTGDR) method, for simultaneous cluster selection and within cluster gene selection. We apply this method to binary classification and censored survival analysis. Compared to the standard TGDR and other regularization methods, the CTGDR takes into account the cluster structure and carries out feature selection at both the cluster level and within-cluster gene level. We demonstrate the CTGDR on two studies of cancer classification and two studies correlating survival of lymphoma patients with microarray expressions. AVAILABILITY: R code is available upon request. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Algorithms↗
PubMed2002

Effects of a cross-modal manipulation of attention on somatosensory cortical neuronal responses to tactile stimuli in the monkey.

The role of attention in modulating tactile sensitivity in primary (SI) and secondary somatosensory cortex (SII) was addressed using a cross-modal manipulation of attention, somatosensory versus visual. Two adult monkeys (Macaca mulatta) were trained to perform two tasks: tactile discrimination of a change in the texture of a surface presented to digits 3 and 4 and visual discrimination of a change in the intensity of a light. In each trial, standard texture (2 mm spatial period, SP) and visual stimuli were presented. These were followed by an increase in SP and/or luminance. Each trial was preceded by an instruction cue (colored light) that directed the animal to attend and respond to the change in one modality while ignoring any change in the other modality. The two tasks were interleaved during the recording, on a trial-by-trial basis. Extracellular recordings were made from 178 neurons (SI, 102; SII, 76), all with a cutaneous receptive field on the stimulated digit tips. Discharge was quantified in both tasks during the instruction, the standard-stimuli, and the texture-change periods. The results showed that selective attention to tactile stimuli had qualitatively and quantitatively greater and earlier effects in SII than SI. Twenty-four of 102 SI cells showed a significant change in discharge with the direction of attention. For almost all cells (20/24), discharge was enhanced when attention was directed toward the tactile stimuli; the effects were most frequent in the analysis interval that encompassed the change in SP (16/24). A significantly higher proportion of SII cells were attention-sensitive (47/76). The effects were concentrated in the texture-change period (39/47) but also included earlier periods in the trial (instruction period, n = 15; standard-stimuli period, n = 32). Attention-related modulation that spanned all three intervals (n = 11) likely reflected baseline changes in discharge. For the texture-sensitive cells (43 in SI, 37 in SII), the mean change in discharge frequency (post texture change - pre-texture change) in each task was significantly increased in SII but not SI with selective attention. The results are consistent with a two-stage modulation of parietal cortical discharge, an initial stage (SI) in which there is some enhancement of sensory responses to the salient feature, the texture change, and a second stage (SII) in which baseline changes occur, along with further feature selection. These controls may be independently exerted on SI and SII, or they may reflect top-down controls from SII to SI.

Animals↗
PubMed2004

Metal-responsive transcription factor-1 (MTF-1) selects different types of metal response elements at low vs. high zinc concentration.

Metal-responsive transcription factor-1 (MTF-1) is a zinc finger protein with a central role in heavy metal homeostasis/detoxification. MTF-1 binds to DNA sequence motifs known as metal response elements (MREs) with a core consensus TGCRCNC. Since MTF-1 is also involved in other stress responses, we tested whether it is able to recognize different types of DNA sequence motifs. To this end we selected MTF-1-binding oligonucleotides from a collection of random sequences. Since MTF-1 binds to known target sequences at relatively high zinc concentrations, oligonucleotide selection was performed in a mammalian cell nuclear extract both at high and low zinc concentrations. Irrespective of zinc concentration, we find a robust representation of MRE consensus sequences, however with specific features. Selection was most efficient at 100 microM zinc, yielding many oligonucleotides with two MRE motifs in divergent orientation of the sequence GTGTGCATCACTTTGCGCAC (core consensus underlined). Oligonucleotides selected without zinc supplement contain a single high-affinity MRE with an extended flanking sequence of consensus TTTTGCGCACGGCACTAAAT (core consensus underlined). This low-zinc MRE motif can bind MTF-1 and induce transcription in vivo, and is less dependent on zinc than the classical MREd motif from the mouse metallothionein-I promoter. At low zinc, we also found evidence for a negative role of nuclear factor-I (NF-I/CTF-I) in MTF-1-dependent transcription. Finally, a selection in the presence of cadmium yielded no specific binding site for MTF-1, strongly supporting the concept of an indirect activation of MTF-1 by cadmium within a living cell.

Base Sequence↗
PubMed2006

Sonographic diagnostic criteria for screening Sjögren's syndrome.

OBJECTIVE: The objective of this study is to establish readily applied sonographic diagnostic criteria for Sjögren's syndrome. STUDY DESIGN: Sonographic images of 79 cases of previously suspected Sjögren's syndrome (including 43 actual cases) were analyzed retrospectively for the following characteristic features: (1) multiple hypoechoic areas, (2) multiple hyperechoic lines or spots, (3) multiple hypoechoic areas surrounded with hyperechoic lines or spots, and (4) obscuration of the gland configuration. Logistic regression analysis was used to extract valuable sonographic findings. Sonographic images of 80 prospective patients (of whom 48 proved to have Sjögren's syndrome) were scored prospectively using selected features to verify the usefulness of the established criteria. RESULTS: Three sonographic findings in parotid and submandibular glands were selected by logistic regression analysis and retrospective and prospective patients compared. Experienced observers could differentiate positive cases of Sjögren's syndrome from negative controls to a highly significant degree. Findings correlated very well with sialographic grading. CONCLUSION: Sonography can be substituted for sialography when applying the selected criteria in screening for Sjögren's syndrome.

Female↗
PubMed2004

Qualitative diagnosis of calvarial metastasis by neural network and logistic regression.

RATIONALE AND OBJECTIVES: To simplify the diagnostic features used by an artificial neural network compared with logistic regression (LR) in the diagnosis of calvarial metastasis with computed tomography and analyze their accuracy. MATERIALS AND METHODS: Twenty-one of 167 patients with calvarial lesions were found to have metastasis. Clinical and computed tomography data were used for LR and neural network models. Both models were tested with the leave-one-out method. The final results of each model were compared using the area under receiver operating characteristic curve (Az). RESULTS: The neural network identified metastasis significantly more successfully than LR with an Az of 0.9324 +/- 0.0386 versus 0.9192 +/- 0.0373, P = .01. The most important features selected by the LR and neural network were age and edge definition. CONCLUSION: Neural networks offer wide possibilities over statistics for the study of calvarial metastases other than their minimum clinical and radiologic features for diagnosis.

Adolescent↗
PubMed2005

Combination of feature-reduced MR spectroscopic and MR imaging data for improved brain tumor classification.

The purpose of this paper is to evaluate the effect of the combination of magnetic resonance spectroscopic imaging (MRSI) data and magnetic resonance imaging (MRI) data on the classification result of four brain tumor classes. Suppressed and unsuppressed short echo time MRSI and MRI were performed on 24 patients with a brain tumor and four volunteers. Four different feature reduction procedures were applied to the MRSI data: simple quantitation, principal component analysis, independent component analysis and LCModel. Water intensities were calculated from the unsuppressed MRSI data. Features were extracted from the MR images which were acquired with four different contrasts to comply with the spatial resolution of the MRSI. Evaluation was performed by investigating different combinations of the MRSI features, the MRI features and the water intensities. For each data set, the isolation in feature space of the tumor classes, healthy brain tissue and cerebrospinal fluid was calculated and visualized. A test set was used to calculate classification results for each data set. Finally, the effect of the selected feature reduction procedures on the MRSI data was investigated to ascertain whether it was more important than the addition of MRI information. Conclusions are that the combination of features from MRSI data and MRI data improves the classification result considerably when compared with features obtained from MRSI data alone. This effect is larger than the effect of specific feature reduction procedures on the MRSI data. The addition of water intensities to the data set also increases the classification result, although not significantly. We show that the combination of data from different MR investigations can be very important for brain tumor classification, particularly if a large number of tumors are to be classified simultaneously.

Algorithms↗
PubMed2001

Fuel spill identification using solid-phase extraction and solid-phase microextraction. 1. Aviation turbine fuels.

The water-soluble fraction of aviation jet fuels is examined using solid-phase extraction and solid-phase microextraction. Gas chromatographic profiles of solid-phase extracts and solid-phase microextracts of the water-soluble fraction of kerosene- and nonkerosene-based jet fuels reveal that each jet fuel possesses a unique profile. Pattern recognition analysis reveals fingerprint patterns within the data characteristic of fuel type. By using a novel genetic algorithm (GA) that emulates human pattern recognition through machine learning, it is possible to identify features characteristic of the chromatographic profile of each fuel class. The pattern recognition GA identifies a set of features that optimize the separation of the fuel classes in a plot of the two largest principal components of the data. Because principal components maximize variance, the bulk of the information encoded by the selected features is primarily about the differences between the fuel classes.

Journal Article↗
PubMed2000

A new method for maturity determination in newborn infants.

A two-part study was conducted in several centres in Nigeria to develop and evaluate a simple method for maturity determination in newborn infants. The first part involved the development of a six-feature model which included head circumference, mid-arm circumference, skin texture, ear form, breast size and genitalia. These were features which had highly significant correlation with gestational age in the studied population. The model consisted of a chart showing the regression line of gestational age on total maturity score based on the six selected features. It had comparable accuracy with the Dubowitz method. Different subgroups of term and low-birth weight infants were also reliably identified by the model. In the evaluation of sick newborn infants, the model was more accurate than a previously reported abbreviated method from the same population. The model is suggested as an appropriate clinical tool for rapid and reliable maturity determination in healthy and sick newborn infants.

Arm↗
PubMed1999

Matching the modules: cortical maps and long-range intrinsic connections in visual cortex during development.

Visual cortical neurons exhibit a high degree of response selectivity and are grouped into small columns according to their response preferences. The columns are located at regularly spaced intervals covering the whole cortical representation of the visual field with a modular system of feature-selective neurons. The selectivity of these cells and their modular arrangement is thought to emerge from interactions in the network of specific intracortical and thalamocortical connections. Understanding the ontogenesis of this complex structure and contributions of intrinsic and extrinsic, experience-dependent mechanisms during cortical development can provide new insights into the way the visual cortex processes information about the environment. Available data about the development of connections and response properties in the visual cortex suggest that maturation proceeds in two distinct steps. In the first phase, mechanisms inherent to the cortex establish a crude framework of interconnected neural modules which exhibit the basic but still immature traits of the adult state. Relevant mechanisms in this phase are assumed to consist of molecular cues and patterns of spontaneous neural activity in cortical and corticothalamic interconnections. In a second phase, the primordial layout becomes refined under the control of visual experience establishing a fine-tuned network of connections and mature response properties.

Animals↗
PubMed1983

Powered domestic lawnmowers: design for safety.

The paper describes a detailed accident investigation carried out by the Institute for Consumer Ergonomics for the Consumer Safety Unit at the Department of Trade. As such it serves to illustrate the application of two specific research techniques (i) analysis of product related accident data, and (ii) ergonomics evaluation of current models - and shows how these may be used to help in defining standards and criteria for the design of safer products. The study identified lawnmower features and activities associated with accidents recorded by the Home Accident Surveillance System. Ergonomics appraisal by expert assessment and user trials highlighted hazards associated with currently available powered lawnmowers. Performance criteria for safer design of selected features were developed with the aim of overcoming these hazards. At the end of the study liaison was sought with manufacturers to discuss how the results from the work could be used to effect.

Journal Article↗
PubMed2005

A novel approach to extracting features from motif content and protein composition for protein sequence classification.

This paper presents a novel approach to extracting features from motif content and protein composition for protein sequence classification. First, we formulate a protein sequence as a fixed-dimensional vector using the motif content and protein composition. Then, we further project the vectors into a low-dimensional space by the Principal Component Analysis (PCA) so that they can be represented by a combination of the eigenvectors of the covariance matrix of these vectors. Subsequently, the Genetic Algorithm (GA) is used to extract a subset of biological and functional sequence features from the eigen-space and to optimize the regularization parameter of the Support Vector Machine (SVM) simultaneously. Finally, we utilize the SVM classifiers to classify protein sequences into corresponding families based on the selected feature subsets. In comparison with the existing PSI-BLAST and SVM-pairwise methods, the experiments show the promising results of our approach.

Amino Acid Motifs↗
PubMed2003

Identification of chemically selective displacers using parallel batch screening experiments and quantitative structure efficacy relationship models.

Parallel batch screening experiments were carried out to examine how displacer chemistry and salt counterions affect the selectivity of batch protein displacements in anion exchange chromatographic systems. The results indicate that both salt type and displacer chemistry can have a significant impact on the amount of protein displaced. Importantly, the results indicate that, by changing the displacer, salt counterion, or both, one can induce significant selectivity changes in the relative displacement of two model proteins. This indicates that highly selective separations can be developed in ion exchange systems by the appropriate selection of displacer chemistry and salt counterion. The experimental batch screening data were also used in conjunction with various molecular descriptors to generate quantitative structure efficacy relationship (QSER) models based on a support vector machine feature selection and regression tool. The models resulted in good correlations and successful predictions for an external test set of displacers. A star plot approach was shown to be a powerful tool to aid in the interpretation of the QSER models. These results indicate that this modeling approach can be employed for the a priori prediction of displacer efficacy as well as for providing insight into displacer design and the selection of proper mobile-phase conditions for highly selective separations.

Algorithms↗
PubMed2005

Computerized diagnosis from tongue appearance using quantitative feature classification.

This study investigates relationships between diseases and the appearance of the human tongue in terms of quantitative features. The experimental samples are digital tongue images captured from three groups of candidates: one group in normal health, one suffering with appendicitis, and a third suffering with pancreatitis. For the purposes of diagnostic classification, we first extract chromatic and textural measurements from original tongue images. A feature selection procedure then identifies the measures most relevant to the classifications, based on which of the three tongue image categories are clearly separated. This study validates the use of tongue inspection by means of quantitative feature classification in medical diagnosis.

Appendicitis↗
PubMed1993

Reliability of grading scales for individual radiographic features of osteoarthritis of the knee. The Baltimore longitudinal study of aging atlas of knee osteoarthritis.

RATIONALE AND OBJECTIVES: The authors present an atlas of individual radiographic features of osteoarthritis of the knee and evaluate the inter- and intra-reader reliability of trained readers using this atlas. METHODS: Four trained readers graded 30 standing anterior-posterior knee radiographs for eight selected features of osteoarthritis (medial and lateral osteophytes, joint space narrowing, and sclerosis; osteophytes of the tibial spines and chondrocalcinosis) as well as the Kellgren-Lawrence global scale. Inter- and intra-reader reliability were calculated using intraclass correlation coefficients. RESULTS: For all features except sclerosis and osteophytes of the tibial spines, inter-reader reliability ranged from 0.63 to 0.83, whereas intra-reader reliability ranged from 0.82 to 0.95. CONCLUSION: Using this atlas, trained readers are reliable in measuring the presence and severity of individual radiographic features of osteoarthritis of the knee. This atlas should be useful in clinical and epidemiologic studies of osteoarthritis of the knee.

Adult↗
PubMed2003

ARTMAP neural networks for information fusion and data mining: map production and target recognition methodologies.

The Sensor Exploitation Group of MIT Lincoln Laboratory incorporated an early version of the ARTMAP neural network as the recognition engine of a hierarchical system for fusion and data mining of registered geospatial images. The Lincoln Lab system has been successfully fielded, but is limited to target/non-target identifications and does not produce whole maps. Procedures defined here extend these capabilities by means of a mapping method that learns to identify and distribute arbitrarily many target classes. This new spatial data mining system is designed particularly to cope with the highly skewed class distributions of typical mapping problems. Specification of canonical algorithms and a benchmark testbed has enabled the evaluation of candidate recognition networks as well as pre- and post-processing and feature selection options. The resulting mapping methodology sets a standard for a variety of spatial data mining tasks. In particular, training pixels are drawn from a region that is spatially distinct from the mapped region, which could feature an output class mix that is substantially different from that of the training set. The system recognition component, default ARTMAP, with its fully specified set of canonical parameter values, has become the a priori system of choice among this family of neural networks for a wide variety of applications.

Computer Simulation↗