Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Classification Algorithms”

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 613 records · Page 34Linked to original sources
PubMed1996

Construction and application of hierarchical decision tree for classification of ultrasonographic prostate images.

A non-parametric algorithm is described for the construction of a binary decision tree classifier. This tree is used to correlate textural features, computed from ultrasonographic prostate images, with the histopathology of the imaged tissue. The algorithm consists of two parts; growing and pruning. In the growing phase an optimal tree is grown, based on the concept of mutual information. After growing, the tree is pruned by an alternating interaction of two data sets. Moreover, the structure and performance of the constructed tree are compared to the results using a slightly modified corresponding growing and pruning algorithm. The modified algorithm provides better retrospective and prospective classification results than the original algorithm. The use of the tree for automated cancer detection in ultrasonographic prostate images results in retrospective and prospective accuracy of 77.9% and 72.3%, respectively. Using this tissue characterisation, a supporting tool is provided for the interpretation of transrectal ultrasonographic images.

Algorithms↗
PubMed2002

HapScope: a software system for automated and visual analysis of functionally annotated haplotypes.

We have developed a software analysis package, HapScope, which includes a comprehensive analysis pipeline and a sophisticated visualization tool for analyzing functionally annotated haplotypes. The HapScope analysis pipeline supports: (i) computational haplotype construction with an expectation-maximization or Bayesian statistical algorithm; (ii) SNP classification by protein coding change, homology to model organisms or putative regulatory regions; and (iii) minimum SNP subset selection by either a Brute Force Algorithm or a Greedy Partition Algorithm. The HapScope viewer displays genomic structure with haplotype information in an integrated environment, providing eight alternative views for assessing genetic and functional correlation. It has a user-friendly interface for: (i) haplotype block visualization; (ii) SNP subset selection; (iii) haplotype consolidation with subset SNP markers; (iv) incorporation of both experimentally determined haplotypes and computational results; and (v) data export for additional analysis. Comparison of haplotypes constructed by the statistical algorithms with those determined experimentally shows variation in haplotype prediction accuracies in genomic regions with different levels of nucleotide diversity. We have applied HapScope in analyzing haplotypes for candidate genes and genomic regions with extensive SNP and genotype data. We envision that the systematic approach of integrating functional genomic analysis with population haplotypes, supported by HapScope, will greatly facilitate current genetic disease research.

Algorithms↗
PubMed2005

[Tracheobronchial ruptures: classification and management].

BACKGROUND: Tracheobronchial ruptures are rare surgical emergencies with significant mortality. We present management and outcome of such ruptures treated at the University of Leipzig in Germany and propose a novel therapeutic algorithm-a new classification system for stratifying treatment of patients with tracheobronchial ruptures. METHODS: We retrospectively studied 24 patients 19 to 88 years old who were treated in our institution for tracheobronchial injury. RESULTS: Eighty-seven percent of the injuries were caused iatrogenically. Fifty-four percent were type I injuries (isolated tracheal lesions), 38% type II (involvement of carina or main stem bronchi), and 8% type III (distal lesions of lobar or segmental bronchi). Seventy-five percent of the patients were operated via right-sided dorsolateral thoracotomy. In four (22%), insufficiency of the tracheal closure occurred, with mediastinitis possibly being a significant risk factor for this event (P<0.001). In surgically treated patients, rupture-related and overall mortality were 5.5% and 28%, respectively, whereas in medically treated patients, mortality was 33%. CONCLUSION: The proposed classification of tracheobronchial injuries enables stratifying the treatment of patients with tracheobronchial ruptures. Type I lesions can be surgically closed either by a right-sided thoracotomy or transcervical-transtracheal approach. In contrast, surgical management of type II and III injuries always requires thoracotomy.

Adult↗
PubMed2005

Wavelet packet correlation methods in biometrics.

We introduce wavelet packet correlation filter classifiers. Correlation filters are traditionally designed in the image domain by minimization of some criterion function of the image training set. Instead, we perform classification in wavelet spaces that have training set representations that provide better solutions to the optimization problem in the filter design. We propose a pruning algorithm to find these wavelet spaces by using a correlation energy cost function, and we describe a match score fusion algorithm for applying the filters trained across the packet tree. The proposed classification algorithm is suitable for any object-recognition task. We present results by implementing a biometric recognition system that uses the NIST 24 fingerprint database, and show that applying correlation filters in the wavelet domain results in considerable improvement of the standard correlation filter algorithm.

Algorithms↗
PubMed2004

[Immune restoration inflammatory syndromes].

Increase of prevalence of certain immunodeficiencies is caused by more frequent use of immunosuppresive treatment, by advances in supportive care of immunodeficient individuals and by the pandemic spread of HIV-infection respectively. Highly active antiretroviral treatment (HAART) is able to reconstitute the impaired immunity in the HIV-infected individual and therefore to reduce morbidity and mortality. On the other hand paradoxical exacerbation of inflammatory or opportunistic diseases may develop during immunoreconstitution. By their distinct pathophysiological, clinical and therapeutic particularities these disease have been summarized as Immune Restoration Inflammatory Syndromes (IRIS). This review summarizes the variety of immunoreconstitution disorders and describes possible diagnostic pitfalls. Potential therapeutic options and an algorithm for the classification of the syndrome are proposed.

Algorithms↗
PubMed1995

Self-organising sensory maps in odour classification mimicking.

A system for artificial olfaction is introduced, which is composed of a sensor array for gas sensing and a self-organising artificial neural network. A detailed reformulation of the most effective Self-Organising sensory Map (SOM)-based algorithms for odour classification and other applications is provided. An opto-electronic micromachined implementation of the neural network is introduced, which employs a novel hybrid mechanism for activating neural groups, avoiding fabricated cloning templates hardware.

Algorithms↗
PubMed2004

A comprehensive evaluation of multicategory classification methods for microarray gene expression cancer diagnosis.

MOTIVATION: Cancer diagnosis is one of the most important emerging clinical applications of gene expression microarray technology. We are seeking to develop a computer system for powerful and reliable cancer diagnostic model creation based on microarray data. To keep a realistic perspective on clinical applications we focus on multicategory diagnosis. To equip the system with the optimum combination of classifier, gene selection and cross-validation methods, we performed a systematic and comprehensive evaluation of several major algorithms for multicategory classification, several gene selection methods, multiple ensemble classifier methods and two cross-validation designs using 11 datasets spanning 74 diagnostic categories and 41 cancer types and 12 normal tissue types. RESULTS: Multicategory support vector machines (MC-SVMs) are the most effective classifiers in performing accurate cancer diagnosis from gene expression data. The MC-SVM techniques by Crammer and Singer, Weston and Watkins and one-versus-rest were found to be the best methods in this domain. MC-SVMs outperform other popular machine learning algorithms, such as k-nearest neighbors, backpropagation and probabilistic neural networks, often to a remarkable degree. Gene selection techniques can significantly improve the classification performance of both MC-SVMs and other non-SVM learning algorithms. Ensemble classifiers do not generally improve performance of the best non-ensemble models. These results guided the construction of a software system GEMS (Gene Expression Model Selector) that automates high-quality model construction and enforces sound optimization and performance estimation procedures. This is the first such system to be informed by a rigorous comparative analysis of the available algorithms and datasets. AVAILABILITY: The software system GEMS is available for download from http://www.gems-system.org for non-commercial use. CONTACT: alexander.statnikov@vanderbilt.edu.

Algorithms↗
PubMedDate not supplied

Algorithm for the treatment of calcific tendinitis in the rotator cuff: indications for arthroscopy and results in our experience.

Calcific tendinitis of the rotator cuff is a relatively frequent pathology and at times, in some phases, it is a disabling one: for this reason, numerous therapeutic options have been proposed. The authors propose an algorithm for the classification and treatment of calcific tendinitis and report their experience with arthroscopic treatment over a three-year period from 2001 to 2004. Based on the algorithm proposed, out of a total of 126 shoulders affected with calcific tendinitis of the rotator cuff for which debridement was indicated, 106 us-guided percutaneous surgeries (EPT), and only 20 arthroscopies were performed. Arthroscopy is indicated, on the basis of the algorithm that we followed, in patients affected by chronic and persistent calcific tendinitis who did not benefit from the execution of previous types of non-surgical treatment for a period of at least 6 to 12 months. Shoulder instability was found to be present in 8 patients out of 20 treated arthroscopically. After arthroscopy, short- and medium-term results were always positive with the exception of one case that evolved into adhesive capsulitis. Based on an analysis of this series, we were able to confirm the usefulness and clinical applicability of an algorithm to classify and treat calcific tendinitis of the rotator cuff; we also confirmed the role of arthroscopic treatment that in cases which did not respond to conservative procedures proved to be effective in resolving symptoms.

Adult↗
PubMed2006

[Clinical classification of chronic pruritus. Interdisciplinary consensus proposal for a diagnostic algorithm].

Chronic pruritus is a frequent symptom in dermatology caused by a variety of dermatologic, neurologic and other systemic diseases. For adequate, economically-appropriate medical care of patients with chronic pruritus, a clinical classification of pruritus which also serves as a diagnostic algorithm is necessary. Currently suggested classifications are etiologic and not helpful in daily clinical routine. The proposed clinical classification is oriented at the clinical appearance of the patients and differentiates between disorders with or without primary or secondary skin lesions.

Algorithms↗
PubMed2000

DEA: An architecture for goal planning and classification.

We introduce the differential efficiency algorithm, which partitions a perceptive space during unsupervised learning into categories and uses them to solve goal-planning and classification problems. This algorithm is inspired by a biological model of the cortex proposing the cortical column as an elementary unit. We validate the generality of this approach by testing it on four problems with continuous time and no reinforcement signal until the goal is reached (constrained object moves, Hanoi tower problem, animat control, and simple character recognition).

Algorithms↗
PubMed2004

Comparison of the specificity of implantable dual chamber defibrillator detection algorithms.

The aim of the study was to compare the specificity of dual chamber ICDs detection algorithms for correct classification of supraventricular tachyarrhythmias derived from clinical studies according to their size to detect an impact of sample size on the specificity. Furthermore, the study sought to compare the specificities of detection algorithms calculated from clinical data with the specificity calculated from simulations of tachyarrhythmias. A survey was conducted of all available sources providing data regarding the specificity of five dual chamber ICDs. The specificity was correlated with the number of patients included, number of episodes, and number of supraventricular tachyarrhythmias recorded. The simulation was performed using tachyarrhythmias recorded in the electrophysiology laboratory. The range of the number of patients included into the studies was 78-1,029, the range of the total number of episodes recorded was 362-5,788, and the range of the number of supraventricular tachyarrhythmias used for calculation of the specificity for correct detection of these arrhythmias was 100 (Biotronik) to 1662 (Medtronic). The specificity for correct detection of supraventricular tachyarrhythmias was 90% (Biotronik), 89% (ELA Medical), 89% (Guidant), 68% (Medtronic), and 76% (St. Jude Medical). There was an inverse correlation (r = -0.9, P = 0.037) between the specificity for correct classification of supraventricular tachyarrhythmias and the number of patients. The specificity for correct detection of supraventricular tachyarrhythmias calculated from the simulation after correction for the clinical prevalence of the simulated tachyarrhythmias was 95% (Biotronik), 99% (ELA Medical), 94% (Guidant), 93% (Medtronic), and 92% (St. Jude Medical). In conclusion, the specificity of ICD detection algorithms calculated from clinical studies or registries may depend on the number of patients studied. Therefore, a direct comparison between different detection algorithms based on clinical data is difficult. In contrast, simulation of supraventricular tachyarrhythmias using a uniform database may be a better tool for direct comparison of the specificity of ICD detection algorithms.

Arrhythmias, Cardiac↗
PubMed1987

Learning algorithms and probability distributions in feed-forward and feed-back networks.

Learning algorithms have been used both on feed-forward deterministic networks and on feed-back statistical networks to capture input-output relations and do pattern classification. These learning algorithms are examined for a class of problems characterized by noisy or statistical data, in which the networks learn the relation between input data and probability distributions of answers. In simple but nontrivial networks the two learning rules are closely related. Under some circumstances the learning problem for the statistical networks can be solved without Monte Carlo procedures. The usual arbitrary learning goals of feed-forward networks can be given useful probabilistic meaning.

Journal Article↗
PubMed1990

Classification and identification of rhodococci.

Ninety-nine representative strains of Rhodococcus were compared through 129 unit characters and the data examined using the simple matching, Jaccard and pattern coefficients. Clustering was achieved using the unweighted pair group method with arithmetic averages algorithm. The numerical classification was not affected by the statistics used or by test error, estimated at 1.95%. Sixteen multimembered and 23 single member clusters were defined by the simple matching coefficient at or above the 89% similarity level. The numerical phenetic data support the taxonomic integrity of all 13 validly described species of Rhodococcus, including Rhodococcus aichiensis. Rapid enzymic tests based upon fluorophores 7-amino-4-methylcoumarin and 4-methylumbelliferone provide valuable data for rhodococcal systematics.

Bacterial Typing Techniques↗
PubMed2005

Granular self-organizing map (grSOM) for structure identification.

This work presents a useful extension of Kohonen's Self-Organizing Map (KSOM) for structure identification in linguistic (fuzzy) system modeling applications. More specifically the granular SOM neural model is presented for inducing a distribution of nonparametric fuzzy interval numbers (FINs) from the data. A FIN can represent a local probability distribution function and/or a conventional fuzzy set; moreover, a FIN is interpreted as an information granule. Learning is based on a novel metric distance d(K)(.,.) between FINs. The metric d(K)(.,.) can be tuned nonlinearly by a mass function m(x), the latter attaches a weight of significance to a real number 'x' in a data dimension. Rigorous analysis is based on mathematical lattice theory. A grSOM can cope with ambiguity by processing linguistic (fuzzy) input data and/or intervals. This work presents a simple grSOM variant, namely greedy grSOM, for classification. A genetic algorithm (GA) introduces tunable nonlinearities during training. Extensive comparisons are shown with related work from the literature. The practical effectiveness of the greedy grSOM is demonstrated comparatively in three benchmark classification problems. Statistical evidence strongly suggests that the proposed techniques improve classification performance. In addition, the greedy grSOM induces descriptive decision-making knowledge (fuzzy rules) from the training data.

Fuzzy Logic↗
PubMed2003

Acute injuries of the distal radioulnar joint and triangular fibrocartilage complex.

Distal radioulnar joint disorders have become increasingly recognized. Over the past decade, advances in functional anatomy, kinematics, advanced imaging, and arthroscopy have improved understanding of distal radioulnar joint disorders and their management. In the past, injuries to the triangular fibrocartilage complex and distal radioulnar joint have been regarded as related but separate entities. The authors' classification and treatment algorithm perceives these injuries as a single entity, differing only in their progressively severe anatomic pathology and subsequent clinical manifestations. A discussion of pertinent anatomy, clinical characteristics, ancillary studies, and a new classification system help establish recommended management options of this disorder.

Carpal Bones↗
PubMedDate not supplied

Discrimination between human T and B lymphocytes by computer analysis of digitized data from scanning microphotometry. II. Discrimination and automated classification.

Human B and T lymphocytes were purified and stained according to the Feulgen procedure. Stained preparations were scanned on a microphotometer and the digitized images were processed by analytical programs on a computer. Features of the cells relating to the chromatin distribution were extracted. Computer algorithms automatically derive classification rules and a machine recognition of B cells and T cells results in better than 80% correct assignments. The image data reveal a rich feature structure within both the purified B and T cell populations. Each population appears to contain several subpopulations of cells with distinctive and different chromatin texture.

Autoanalysis↗
PubMed2006

Development and validation of a consensus methodology for the classification of the ANCA-associated vasculitides and polyarteritis nodosa for epidemiological studies.

BACKGROUND: The classification of antineutrophil cytoplasmic antibody-associated vasculitis (AAV) and polyarteritis nodosa (PAN) for epidemiology studies is confusing. The existing schemes such as American College of Rheumatology (ACR) criteria, Chapel Hill Consensus Conference (CHCC) definitions and Lanham criteria produce overlapping and conflicting classifications, making it difficult to compare incidence figures. AIM: To develop a consensus method of using these criteria and definitions for epidemiological studies to permit comparison without confounding by classification. METHODS: A stepwise algorithm was developed by consensus between a group of doctors interested in the epidemiology of vasculitis. The aim was to categorise patients with Wegener's granulomatosis, microscopic polyangiitis (MPA), Churg-Strauss syndrome (CSS) and PAN into single clinically relevant categories. The ACR and Lanham criteria for CSS, and ACR criteria for Wegener's granulomatosis were applied first, as these were considered to be the most specific. Surrogate markers for Wegener's granulomatosis were included to distinguish Wegener's granulomatosis from MPA. MPA was classified using the CHCC definition and surrogate markers for renal vasculitis. Finally, PAN was classified using the CHCC definition. The algorithm was validated by application to 20 cases from each centre and 99 from a single centre, followed by a paper case exercise. RESULTS: A four-step algorithm was devised. It successfully categorises patients into a single classification. There was good correlation between observers in the paper case exercise (91.5%; unweighted kappa = 0.886). CONCLUSION: The algorithm achieves its aim of reliably classifying patients into a single category. The use of the algorithm in epidemiology studies should permit comparison between geographical areas.

Algorithms↗
PubMed2006

Fuzzy clustering of Raman spectral imaging data with a wavelet-based noise-reduction approach.

Raman spectral imaging has been widely used for extracting chemical information from biological specimens. One of the challenges is to cluster the chemical groups from the vast amount of hyperdimensional spectral imaging data so that functionally similar groups can be identified. In this paper, we present an approach that combines a differential wavelet-based data smoothing with a fuzzy clustering algorithm for the classification of Raman spectral images. The preprocessing of the spectral data is facilitated by decomposing them in the differential wavelet domain, where the discrimination of true spectral features and noise can be easily performed using a multi-scale pointwise product (MPP) criterion. This approach is applied to the classification of spectral data collected from adhesive/dentin interface specimens where the spectral data exhibit different signal-to-noise ratios. The proposed wavelet approach has been compared to several conventional noise-removal algorithms.

Adhesives↗