SEARCH · PubMed Health

Results for “Feature selection”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

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

At least 235 records · Page 13Linked to original sources

PubMed1999

Computer-supported diagnosis of melanoma in profilometry.

Laser profilometry offers new possibilities to improve non-invasive tumor diagnostics in dermatology. In this paper, a new approach to computer-supported analysis and interpretation of high-resolution skin-surface profiles of melanomas and nevocellular nevi is presented. Image analysis methods are used to describe the profile's structures by texture parameters based on co-occurrence matrices, features extracted from the Fourier power spectrum, and fractal features. Different feature selection strategies, including genetic algorithms, are applied to determine the best possible subsets of features for the classification task. Several architectures of multilayer perceptrons with error back-propagation as learning paradigm are trained for the automatic recognition of melanomas and nevi. Furthermore, network-pruning algorithms are applied to optimize the network topology. In the study, the best neural classifier showed an error rate of 4.5% and was obtained after network pruning. The smallest error rate in all, of 2.3%, was achieved with nearest neighbor classification.

Diagnosis, Differential↗

PubMed1996

Is there feature-based attentional selection in visual search?

A new paradigm combines attentional cuing and rapid serial visual presentation to disentangle the effects of perceptual filtering and location selection. Observers search successive, superimposed arrays, in which feature values are alternated for a target numeral among letters. Two dimensions, size (small, large) and color (red, green) are tested. Selective attention to feature values is jointly manipulated by instructions, presentation probabilities, and payoffs. In Experiment 1, the attended feature provides temporal, not spatial, information; observers show no attentional costs or benefits in response accuracy. In Experiment 2, the attended feature indicates a unique location; observers show consistent attentional costs and benefits. Selective attention to a particular size or color does not cause perceptual exclusion or admission of items containing that feature; it acts by guiding search processes to spatial locations that contain the to-be-attended feature.

Attention↗

PubMed1995

Wavelet analysis of olfactory nerve response to stimulus.

Multiunit electrophysiological activity recorded by gross electrodes from the olfactory nerve was analyzed by wavelet decomposition, a relatively new method of signal processing. The analysis was run on data from the unstimulated olfactory system as well as on data evoked in response to six different odorant stimuli. Like Fourier analysis, wavelet analysis provides a spectral decomposition of the signal. Unlike Fourier, wavelet analysis also locates the dominant spectral features in time. The output of a wavelet analysis can be further processed to enhance selected features. The increased amplitude of the nerve response evoked by stimulation was the most obvious feature, but efforts to learn from it were unproductive. The temporal pattern of receptor cell activity was much more yielding. The analysis resolved the nerve activity into three classes of events based on duration. On wavelet maps these classes of events separate out into three shifting and overlapping but distinct bands, one of which was interpreted as being associated with individual receptor cell firings and the other two as short and somewhat longer duration bursts of activity that was attributed to the synchronized firing of a group of receptor cells. This interpretation is supported by experiments in which waveforms simulating action potentials and bursts of action potentials are added to recorded data. Stimulation of the olfactory system with odorant molecules evokes a significant increase in the number of short duration bursts, and an amplitude increase that can be related to the number of receptor cells responding. Changes in the patterns of wavelet events can be associated with synchrony of cell firing, reset times for bursts of firing, and possibly other physiological dynamics. A number of differences in activity patterns with different odorants were observed, but without sufficient repeatability to allow reliable discrimination among them. While this study is clearly preliminary in that regard, it shows the potential of the wavelet method for contributing to the understanding of olfaction.

Animals↗

PubMed2001

Stepwise logistic regression analysis of tumor contour features for breast ultrasound diagnosis.

To assist the ultrasound (US) differential diagnosis of solid breast tumors by using stepwise logistic regression (SLR) analysis of tumor contour features, we retrospectively reviewed 111 medical records of digitized US images of breast pathologies. They were pathologically proved benign breast tumors from 40 patients (i.e., 40 fibroadenomas) and malignant breast tumors from 71 patients (i.e., 71 infiltrative ductal carcinomas). Radiologists, before analysis by the computer-aided diagnosis (CAD) system, segmented the tumors manually. The contour features were calculated by measuring the radial length of tumor boundaries. The features selection process was accomplished using a stepwise analysis procedure. Then, an SLR model with contour features was used to classify tumors as benign or malignant. In this experiment, cases were sampled with "leave-one-out" test methods to evaluate the SLR performance using a receiver operating characteristic (ROC) curve. The accuracy of our SLR model with contour features for classifying malignancies was 91.0% (101 of 111 tumors), the sensitivity was 97.2% (69 of 71), the specificity was 80.0% (32 of 40), the positive predictive value was 89.6% (69 of 77), and the negative predictive value was 94.1% (32 of 34). The CAD system using SLR can differentiate solid breast nodules with relatively high accuracy and its high negative predictive value could potentially help inexperienced operators to avoid misdiagnoses. Because the SLR model is trainable, it could be optimized if a larger set of tumor images were supplied.

Adolescent↗

PubMed1986

Identification of best electrocardiographic leads for diagnosing anterior and inferior myocardial infarction by statistical analysis of body surface potential maps.

In view of the increasing interest in quantifying and modifying the size of myocardial infarction (MI), it is important to look for clinically practical subsets of electrocardiographic leads that allow the earliest and most accurate diagnosis of the presence and electrocardiographic type of MI. A practical approach is described, taking advantage of the increased information content of body surface potential maps over standard electrocardiographic techniques for facilitating clinical use of body surface potential maps for such a purpose. Multivariate analysis was performed on 120-lead electrocardiographic data, simultaneously recorded in 236 normal subjects, 114 patients with anterior MI and 144 patients with inferior MI, using as features instantaneous voltages on time-normalized QRS and ST-T waveforms. Leads and features for optimal separation of normal subjects from, respectively, anterior MI and inferior MI patients were selected. Features measured on leads originating from the upper left precordial area, lower midthoracic region and the back correctly identified 97% of anterior MI patients, with a specificity of 95%; in patients with inferior MI, features obtained from leads located in the lower left back, left leg, right subclavicular area, upper dorsal region and lower right chest correctly classified 94% of the group, with specificity kept at 95%. Most features were measured in early and mid-QRS, although very potent discriminators were found in the late portion of the T wave.(ABSTRACT TRUNCATED AT 250 WORDS)

Action Potentials↗

PubMed2001

Machine classification of dental images with visual search.

RATIONALE AND OBJECTIVES: The authors performed this study to assess the performance of a computer-based classification system that uses gaze locations of observers to define the subspace for machine learning. MATERIALS AND METHODS: Thirty-two dental radiographs were classified by an expert viewer into four categories of disease of the periapical region: no disease (normal tooth), mild disease (widened periodontal ligament space), moderate disease (destruction of the lamina dura), and severe disease (resorption of bone in the periapical area). There were eight images in each category. Six observers independently viewed the images while their eye gaze position was recorded. They then classified the images into one of the four categories. A sample of image space was used as input to a machine learning routine to develop a machine classifier. Sample space was determined with three techniques: visual gaze, random selection, and constrained random selection. K analyses were used to compare classification accuracies with the three sampling techniques. RESULTS: With use of the expert classification as a standard of reference, observers classified images with 57% accuracy, and the machine classified images with 84% accuracy by using the same gaze-selected features and image space. Results of kappa analyses revealed mean values of 0.78 for gaze-selected sampling, 0.69 for random sampling, 0.68 for constrained random selection, and 0.44 for observers. The use of sample space selected with the visual gaze technique was superior to that selected with both random-selection techniques and by the observers. CONCLUSION: Machine classification of dental images improves the accuracy of individual observers using gaze-selected image space.

Artificial Intelligence↗

PubMed1975

Development of multiple dimension use in form classification.

The use of multiple form dimensions in pattern classification was studied with adults and children in grades 2 and 5. Each subject sorted 30 8-sided random polygons first into 2, then into 3, and finally into 4 groups and repeated the procedure 1 week later. A series of discriminant analyses, using 9 physical form characteristics as predictors, was used to answer several developmental questions. Reliability of classification, number and saliency of features selected, and accuracy with which they were used all implied continuous development of perceptual skills. Multiple feature use in classification was evidenced at all age levels.

Achievement↗

PubMed2026

Essence: A benchmarking-validated transformer framework for early diagnosis of Parkinson's disease using cerebrospinal fluid protein biomarkers.

Parkinson's disease (PD) is a progressive neurodegenerative disorder characterized by motor and non-motor symptoms. The lack of objective molecular biomarkers limits early diagnosis and personalized treatment. Here, we propose Essence, a benchmarking-validated framework integrating cerebrospinal fluid (CSF) proteomics with traditional and deep learning models to identify robust protein signatures for PD. Using data from two independent cohorts, 1266 high-confidence proteins are quantified, among which 178 exhibit differential abundance between PD and healthy controls (HC). Through systematic benchmarking of ten machine learning algorithms and four neural architectures, the Transformer model consistently outperforms alternatives across multiple feature selection strategies, achieving an area under the receiver operating characteristic curve (AUC) of 1.0000 with only 35 features. Functional analyses of the top-ranked 35 proteins reveal enrichment in neuroinflammatory, synaptic, and oxidative stress-related pathways. Importantly, spatial transcriptomic profiling based on the Allen Brain Atlas shows region-specific expression of these biomarkers in PD-relevant brain structures, including the striatum, subthalamic nucleus, hippocampus, and white matter tracts. This anatomical alignment supports the functional relevance of the identified markers and highlights their potential utility in early-stage diagnosis and mechanistic understanding of PD.

Benchmarking↗

PubMed2003

Differential brain responses when applying criterion attribute versus family resemblance rule learning.

Subsystems of category learning have been identified on the basis of general domains of content (e.g., tools, faces). The present study examined categories from the standpoint of internal structure and determined brain topography associated with expressing two fundamentally different category rule structures (criterion attribute, CA, and family resemblance, FR). CA category learning involves processing stimuli by isolated features and classifying by properties held by all members. FR learning involves processing stimuli by integral wholes and classifying on overall similarity among members without sharing identical features. fMRI BOLD response to CA and FR categorization was measured with pseudowords as stimuli. Category knowledge for both tasks was mastered prior to brain imaging. Areas of activation emerged unique to the structure of each category and followed from the nature of the rule abstraction procedure. CA categorization was implemented by strong target monitoring and expectation (medial parietal), rule maintenance in working memory, feature selection processes (inferior frontal), and a sensitivity to high frequency components of the stimulus such as isolated features (anterior temporal). FR categorization, consistent with its multi-featural nature, involved word-level processing (left extrastriate) that evoked articulatory rehearsal (medial cerebellar). The data suggest category structure is an important determinant of brain response during categorization. For instance, anterior temporal structures may help attune visual processing systems to high frequency components to support the learning of criterial, highly predictive rules.

Adolescent↗

PubMedDate not supplied

[The crisis in psychiatry and the protection of the civil rights of mentally ill patients].

In Poland a basic opinion of the mental health care system is that it considers that mental disorders are illnesses and that an ill person is weaker (worse) and less useful in the social distribution of roles and tasks. Consequently, the ill are excluded from the main-stream of social life: they are deprived of jobs by an easy and early recognition of disability, and the granting of disability pensions, by civil law prohibition of marriage, criminal law ban on sexual contacts etc. A person has little chance for a just life if he/she is deprived of the possibility of working, founding a family, if he/she receives an inadequate pension, remains sexually isolated and on the margin of public life. This medical model of care includes a lot of discriminatory features in the area of human and civil rights of the mentally ill. The discussion concentrated on selected features of the crisis in world psychiatry as well as the practical, ideological, clinical, institutional and organizational difficulties of Polish psychiatry. The main goal of this paper is the raising of psychiatry's awareness of its faults, in order to induce the creation of a new system of mental health care, free of the discriminatory stigmas of the ill and more adequately adapted the ideas of a contemporary democratic state.

Civil Rights↗

PubMed1983

Computer applications in hospital pharmacy practice. I. Computer expectations/applications.

Following vendor selection of a pharmacy computer system, attention must be directed toward which computerized functions to include. Although most features are uniform among the various systems, a discussion is presented listing those applications considered the minimum acceptable for any hospital pharmacy computer system. The descriptions focus on computerization of those labor-intensive activities necessary to support drug distribution services. Computerized support of an intravenous (I.V.) admixture and unit dose program centers around label production and charging/crediting functions. Label production is used to generate a manual backup profile and unit dose cart fill list. The scope of information to include on I.V. and unit dose labels is described. Charging/crediting functions via computer are also discussed, with mention of free-form capabilities. Other computer applications mentioned include: medication profiling, drug interaction flagging, data confidentiality, census support, and hard copy reports. Feature selection depends on the aspects and unique needs that benefit most from computerization.

Accounting↗

PubMed2002

Personality features of children treated due to vocal nodules.

There were estimated 14 features of personality of the children treated for vocal nodules. The purpose of study was definition of the selected features, which are typical of the examined group. The conclusion drawn from the conducted studies was: the children cured of the vocal nodules are more excitable, nervous, independent and often--individualists. They are inclined to leading and dominating. The results of the study suggest that psychotherapy can be completion of traditional treatment for vocal nodules in children.

Anxiety↗

PubMed1998

Optimizing sound features for cortical neurons.

The brain's cerebral cortex decomposes visual images into information about oriented edges, direction and velocity information, and color. How does the cortex decompose perceived sounds? A reverse correlation technique demonstrates that neurons in the primary auditory cortex of the awake primate have complex patterns of sound-feature selectivity that indicate sensitivity to stimulus edges in frequency or in time, stimulus transitions in frequency or intensity, and feature conjunctions. This allows the creation of classes of stimuli matched to the processing characteristics of auditory cortical neurons. Stimuli designed for a particular neuron's preferred feature pattern can drive that neuron with higher sustained firing rates than have typically been recorded with simple stimuli. These data suggest that the cortex decomposes an auditory scene into component parts using a feature-processing system reminiscent of that used for the cortical decomposition of visual images.

Acoustic Stimulation↗

PubMedDate not supplied

Fine needle aspiration biopsy diagnosis of mucoepidermoid carcinoma. Statistical analysis.

Fine needle aspiration (FNA) biopsy is an increasingly popular method for the evaluation of salivary gland tumors. Of the common salivary gland tumors, mucoepidermoid carcinoma is probably the most difficult to diagnose accurately by this means. A series of 96 FNA biopsy specimens of salivary gland masses, including 34 mucoepidermoid carcinomas, 51 other benign and malignant neoplasms, 7 nonneoplastic lesions and 4 normal salivary glands, were analyzed in order to identify the most useful criteria for diagnosing mucoepidermoid carcinoma. Thirteen cytologic criteria were evaluated in the FNA specimens, and a stepwise logistic regression analysis was performed. The three cytologic features selected as most predictive of mucoepidermoid carcinoma were intermediate cells, squamous cells and overlapping epithelial groups. Using these three features together, the sensitivity and specificity of accurately diagnosing mucoepidermoid carcinoma were 97% and 100%, respectively.

Biopsy, Needle↗

PubMed1984

Use of logistic regression analysis to improve prediction of prognosis in acute myeloid leukaemia.

The prognostic usefulness of a range of factors has been examined for patients with acute myeloid leukaemia. Although there was a statistical association between some of these factors and remission rate, the association was only partial. To improve the usefulness of the data, multiple logistic regressional analysis was used. The features selected for use in the analysis were age, blood blast count, FAB classification and colony growth pattern. The last three features could be used as categorical variables, since blood blast counts of greater than 100 X 10(9)/1, FAB group 1 and a prolific pattern of colony growth were associated with a low remission rate. Age was used as a continuous variable. Using these features, eight regression groups were defined. Thus when this data for an individual patient is analysed, it is possible to obtain a value for the probability of that patient achieving remission.

Adult↗

PubMedDate not supplied

[Reproducibility of radiologic diagnosis in gonarthrosis].

AIM OF STUDY: Ongoing efforts of the "German Society of Orthopaedic Surgery and Traumatology" (DGOT) to standardize diagnosis and therapy of osteoarthritis, necessitated this study, where the reproducibility of different radiographic features of knee-OA was assessed. METHODS: Three readers graded 100 antero-posterior and lateral knee radiographs for selected features (femorotibial osteophytes, joint space narrowing, sclerosis and chondrocalcinosis; patellofemoral osteophytes) and an overall-score (Kellgren and Lawrence, 1963) at two time points 3 months apart. Intra- and inter-observer-reliability were calculated by intra-class correlation-coefficient (ICC). RESULTS: Osteophytes in the femorotibial as well as in the patellofemoral joint could be assessed with a high intra- and inter-observer-reliability. While for joint space narrowing intra-observer-reliability is excellent, the inter-observer-reliability is less satisfactory, and subchondral sclerosis as well as chondrocalcinosis showed even less reproducibility. The Kellgren-Lawrence global score proofed to be highly reproducible. CONCLUSION: Based on the results of this examination, we can recommend a reliable radiographic classification of knee osteoarthritis by grading of relevant individual features (osteophytes and joint space narrowing) and overall assessment.

Follow-Up Studies↗

PubMed2026

BaGGLS: a Bayesian shrinkage framework for interpretable modeling of interactions in high-dimensional biological data.

MOTIVATION: Biological data is often high dimensional, noisy, and governed by complex interactions among sparse signals. This poses major challenges for interpretability and reliable feature selection. Tasks such as identifying motif interactions in genomics exemplify these difficulties, as only a small subset of biologically relevant features (e.g. motifs) are typically active, and their effects are often non-linear and context-dependent. While statistical approaches often result in more interpretable models, deep learning models have proven effective in modeling complex interactions and prediction accuracy, yet their black-box nature limits interpretability. RESULTS: We introduce BaGGLS, a flexible and interpretable probabilistic binary regression model designed for high-dimensional biological inference involving feature interactions. BaGGLS incorporates a Bayesian group global-local shrinkage prior, aligned with the group structure introduced by interaction terms. This prior encourages sparsity while retaining interpretability, helping to isolate meaningful signals and suppress noise. To enable scalable inference, we employ a partially factorized variational approximation that captures posterior skewness and supports efficient learning even in large feature spaces. In extensive simulations, we compare BaGGLS to frequentist probit regressions (unconstrained and with L1-penalty) as well as a probit model with Markov Chain Monte Carlo (MCMC) sampling under a horseshoe prior. We can show that BaGGLS outperforms the other methods with regard to interaction detection and is many times faster than MCMC sampling under the horseshoe prior. We also demonstrate the usefulness of BaGGLS in the context of interaction discovery from motif scanner outputs (e.g. Find Individual Motif Occurrences (FIMO)) and noisy attribution scores from deep learning models. This shows that BaGGLS is a promising approach for uncovering biologically relevant interaction patterns, with potential applicability across a range of high-dimensional tasks in computational biology. AVAILABILITY: Code is available at gitlab.com/dacs-hpi/baggls.

Bayes Theorem↗

PubMed2004

Cell culture modeling of specialized tissue: identification of genes expressed specifically by follicle-associated epithelium of Peyer's patch by expression profiling of Caco-2/Raji co-cultures.

Peyer's patch follicle-associated epithelium (FAE) regulates intestinal antigen access to the immune system in part through the action of microfold (M) cells which mediate transcytosis of antigens and microorganisms. Studies on M cells have been limited by the difficulties in isolating purified cells, so we applied TOGA mRNA expression profiling to identify genes associated with the in vitro induction of M cell-like features in Caco-2 cells and tested them against normal Peyer's patch tissue for their expression in FAE. Among the genes identified by this method, laminin beta3, a matrix metalloproteinase and a tetraspan family member, showed enriched expression in FAE of mouse Peyer's patches. Moreover, the C. perfringens enterotoxin receptor (CPE-R) appeared to be expressed more strongly by UEA-1(+) M cells relative to neighboring FAE. Expression of the tetraspan TM4SF3 gene and CPE-R was also confirmed in human Peyer's patch FAE. Our results suggest that while the Caco-2 differentiation model is associated with some functional features of M cells, the genes induced may instead reflect the acquisition of a more general FAE phenotype, sharing only select features with the M cell subset.

Animals↗