Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “classifier”

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 1,207 records · Page 67Linked to original sources

Glutamate receptor subtypes may be classified into two major categories: a study on Xenopus oocytes injected with rat brain mRNA.

Three major subtypes of glutamate receptors that are coupled to cation channels are known. Recently an additional subtype that is coupled to G proteins and stimulates inositol phospholipid metabolism (the metabotropic glutamate receptor) has been proposed. The pharmacological characteristics of this receptor have now been examined. Although it shares some agonists with N-methyl-D-aspartate- and quisqualate-subtype receptors, it shares virtually no antagonists with any of the three cation channel-coupled receptor subtypes. Thus the metabotropic glutamate receptor belongs to a receptor category that is completely different from that of the other three receptor subtypes, not only functionally, but also pharmacologically.

Animals↗

Discriminative features of alcoholics classified according to family history.

By means of discriminant analysis, the frequently proposed distinction of alcoholics according to family history of alcoholism was tested. The most powerful discriminative factors were dysfunctional attitudes, some particular personality characteristics, and perceived parental rearing patterns. The results lend support to the assumption to regard alcoholics with a positive family history of alcoholism as a homogenous subgroup characterized by a specific etiopathogenesis.

Adult↗

Determining and classifying the region of interest in ultrasonic images of the breast using neural networks.

This paper describes how ultrasonic images of the female breast have been processed and neural nets used to aid the identification of malignant and benign areas in them. The images are windowed, filtered and pre-processed into suitable patterns for processing by a neural net. Two networks are trained and used: one for malignant cases and the other for benign cases. These are used to make predictions of regions of interest which are presented as circles overlaid on the image. The system has been prototyped and tested and experts agreed well with the classification and localisation. The system is usually weak when the evidence on the image is considered weak by the expert. It is concluded that the system is promising and should be developed further by providing more training to the network.

Breast Neoplasms↗

Classifying hepatitis C virus genotypes.

Hepatitis C virus (HCV) is the major aetiological agent for blood-borne non-A, non-B hepatitis worldwide. Since its discovery in 1989, at least 28 HCV genotypes have been reported, which differ by > 20% in the nucleotide sequence of the entire genome (approximately 9500 nucleotides) or the sequence of the E1 gene (576 nucleotides). Different HCV genotypes have distinct geographical distributions, and may be associated with variations in viral replication and disease-inducing activity, as well as poor response to interferons in patients with chronic hepatitis C.

Genetic Techniques↗

Nasolacrimal duct obstruction classified by dacryoendoscopy and treated with inferior meatal dacryorhinotomy. Part I: Positional diagnosis of primary nasolacrimal duct obstruction with dacryoendoscope.

PURPOSE: To investigate the site of primary nasolacrimal duct obstruction (PNLDO) using a dacryoendoscope and nasal endoscope. DESIGN: Retrospective, observational case series. METHODS: After local anesthesia, dacryoendoscopy and nasal endoscopy were performed in 149 cases (138 Japanese subjects) of PNLDO. Membranous nasolacrimal duct obstruction was termed as lower PNLDO, and occlusion at sac/duct junction termed as higher PNLDO. RESULTS: The incidence of lower PNLDO was 26.8% (40 of 149 cases), and 109 cases (73.2%) were diagnosed with higher PNLDO. CONCLUSIONS: The dacryoendoscope is extremely useful to observe directly and evaluate the site of obstruction with accuracy in PNLDO. The higher and lower PNLDO may have a different etiologies.

Adult↗

Nasolacrimal duct obstruction classified by dacryoendoscopy and treated with inferior meatal dacryorhinotomy: Part II. Inferior meatal dacryorhinotomy.

PURPOSE: To report the performance of a newly devised technique, inferior meatal dacryorhinotomy (iDR), for membranous PNLDO (lower PNLDO). DESIGN: Retrospective, nonrandomized clinical trial. METHODS: Forty cases (37 patients) who ranged in age from 42 to 89 years old with lower PNLDO were treated by iDR, which is intubation that is assisted by dacryoendoscope, nasal endoscope, and radio-frequency scalpel. The obstructed site was incised with a radio-frequency scalpel without osseous ablation, after which silicone tubes were placed temporarily. RESULTS: Postoperative follow-up evaluation showed that the success rate was 87.5% after 6 months to 2 years. CONCLUSION: The iDR technique is minimally invasive and effective for lower PNLDO.

Adult↗

Are the postures adopted according to requested linguistic categories similar to those classified by the recording protocols?

Knowledge on how workers perceive and associate their postures for trunk flexion with respect to linguistic categories, could allow for the development of simple and valid instruments for self-assessment and for more effective postural training. Considerable time and expense could be saved if reliable self-assessments were available. This study describes the anterior flexion angles of the trunk adopted by individuals according to linguistic categories (mild, moderate and severe) and registered by photograph. The postures were compared with postural recording protocols. Twenty sedentary individuals (10 male and 10 female) and 12 industrial female workers (6 healthy and 6 low back sufferers) participated. Subjects were capable of discriminating linguistic postural categories, since they adopted different trunk postures when distinct categories were requested (p< 0.0001). However, the individual variability was high for each category estimated. This could explain, at least in part, the low level of agreement between self-assessment and observational studies.

Adolescent↗

Genetic design of feature spaces for pattern classifiers.

Functional piecewise approximation seeks data representation that is compact, highly simplified and meaningful. This study presents a genetic algorithm (GA)-based approach for computing a piecewise polynomial representation of functions, with the focus being on piecewise linear approximation in an application of biomedical spectral data. The area of piecewise linear approximation has been researched in the past four decades approximately, and the method presented here is compared with another well-known approach. The expansion of this method to piecewise polynomial representation is shown to be straightforward. Finally, the application of this method as a feature extraction method for classification of a dataset of feature vectors, specifically biomedical spectra, is demonstrated.

Algorithms↗

Classifier ensembles for protein structural class prediction with varying homology.

Structural class characterizes the overall folding type of a protein or its domain. A number of computational methods have been proposed to predict structural class based on primary sequences; however, the accuracy of these methods is strongly affected by sequence homology. This paper proposes, an ensemble classification method and a compact feature-based sequence representation. This method improves prediction accuracy for the four main structural classes compared to competing methods, and provides highly accurate predictions for sequences of widely varying homologies. The experimental evaluation of the proposed method shows superior results across sequences that are characterized by entire homology spectrum, ranging from 25% to 90% homology. The error rates were reduced by over 20% when compared with using individual prediction methods and most commonly used composition vector representation of protein sequences. Comparisons with competing methods on three large benchmark datasets consistently show the superiority of the proposed method.

Algorithms↗

Is it time to re-classify Crohn's disease?

From the original anatomic classification of Crohn's disease in 1975, there have been three subsequent published classifications. The most recent, the Vienna Classification arose from a 1998 World Congress of Gastroenterology Working Party that attempted to prospectively design a simple and objective Crohn's disease phenotypic classification that encompassed components of age at onset, anatomic location and disease behavior. Subsequent application of the Vienna Classification to clinical practice has demonstrated that the Crohn's disease phenotype changes markedly over time, with nearly 80% of inflammatory disease ultimately evolving into a stricturing or penetrating pattern of behavior, and 15% undergoing a change in anatomic location. Furthermore, in controlled studies, the ability of inflammatory bowel disease experts to similarly identify the disease phenotypes, using the Vienna classification, ranges from poor to fair. Taken together, these failings markedly limit the utilization of the Vienna classification of Crohn's disease in clinical trails or disease management. Recent advances in determining the genetic linkages associated with Crohn's disease will undoubtedly lead to a revised Crohn's disease classification that will combine genotype with phenotype. Nevertheless, before this new classification can become a reality we will need to reconcile a number of key elements, including; (1) localization and grouping of all inflammatory bowel disease(IBD) gene mutations, (2) discovering the function of the IBD genes, (3) understanding the impact of the environment on phenotypic expression, and, (4) linking to well-defined phenotypic databases that will permit accurate prediction of disease natural history and therapeutic response. Indeed, the consistency of the phenotypic data available may be the greatest single challenge in unraveling the complexities of inflammatory bowel disease and developing a new classification of Crohn's disease.

Crohn Disease↗

Defining, quantifying, and classifying acute renal failure.

The syndrome of acute renal failure (ARF) is a common complication of critical illness. Like every other syndrome in the intensive care unit, it requires a consensus definition to progress with a research agenda that is dedicated to preventing and treating it. A consensus definition has been proposed and is being validated. ARF also requires quantification of severity because severity of functional loss is likely to determine the way in which ARF affects outcome. The new consensus definition also offers a quantification of severity. Finally, classification according to pathogenesis would be desirable but remains elusive. Important steps are being taken toward improving the outcome of these patients. Critical care physicians need to understand and participate in this process.

Acute Kidney Injury↗

Defining, classifying, and placing incipient caries lesions in perspective.

A caries lesion begins with the introduction of a disease state, likely due to bacterial strains, in the oral cavity. If accompanied or followed by alterations to salivary flow, frequent periods of reduced salivary pH, or frequent intake of refined carbohydrates, the demineralization of tooth structure is likely to begin. The subsequent lesions first will be visible as white spot lesions, which if ignored, eventually will cavitate. Modern dentistry is capable of testing for the presence of caries lesions before cavitation, and it is suggested that routine testing should be mandatory for all patients who are at risk. If the disease is to be identified and treated before cavitation, it is desirable to adopt a new classification for the recognition and recording of caries lesions.

Dental Caries↗

Don't classify polyketide synthases.

Polyketide synthases are intensively studied as metabolite factories generating diverse biologically active natural products. Contrary to their current classification as different "types," there is now a growing body of evidence illustrating that nature realized limitless transitional stages during evolution.

Multienzyme Complexes↗

Novel system for classifying chromatographic applications, exemplified by comprehensive two-dimensional gas chromatography and multivariate analysis.

For practical chromatographers it is extremely difficult to judge the merits and limitations of new technological developments. On the other hand, it is nearly impossible for those at the forefront of technology to judge the implications of their efforts for all specific applications of chromatography. Both chromatographers and researchers can be aided by a classification of the numerous specific applications into a few well-defined categories. In this paper, we propose such a classification of all chemical analysis by chromatography into three generic types of applications, viz. target-compound analysis, group-type separation, and fingerprinting. The requirements for each type are discussed in general terms. The classification scheme is applied to assess the benefits and limitations of comprehensive two-dimensional gas chromatography (GC x GC) and the possible additional benefits of using multivariate-analysis (MVA) techniques for each type of application. The conclusions pertaining to the generic types of applications are indicative for the implications of new developments for specific chemical analysis by chromatography.

Chromatography, Gas↗