Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “CLASSIFICATION”

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 1,297 records · Page 72Linked to original sources
PubMed2003

An Epicurean learning approach to gene-expression data classification.

We investigate the use of perceptrons for classification of microarray data where we use two datasets that were published in [Nat. Med. 7 (6) (2001) 673] and [Science 286 (1999) 531]. The classification problem studied by Khan et al. is related to the diagnosis of small round blue cell tumours (SRBCT) of childhood which are difficult to classify both clinically and via routine histology. Golub et al. study acute myeloid leukemia (AML) and acute lymphoblastic leukemia (ALL). We used a simulated annealing-based method in learning a system of perceptrons, each obtained by resampling of the training set. Our results are comparable to those of Khan et al. and Golub et al., indicating that there is a role for perceptrons in the classification of tumours based on gene-expression data. We also show that it is critical to perform feature selection in this type of models, i.e. we propose a method for identifying genes that might be significant for the particular tumour types. For SRBCTs, zero error on test data has been obtained for only 13 out of 2308 genes; for the ALL/AML problem, we have zero error for 9 out of 7129 genes that are used for the classification procedure. Furthermore, we provide evidence that Epicurean-style learning and simulated annealing-based search are both essential for obtaining the best classification results.

Algorithms↗
PubMed1999

An intelligent framework for the classification of the 12-lead ECG.

An intelligent framework has been proposed to classify an unknown 12-Lead electrocardiogram into one of a possible number of mutually exclusive and combined diagnostic classes. The framework segregates the classification problem into a number of bi-dimensional classification problems, requiring individual bi-group classifiers for each individual diagnostic class. The bi-group classifiers were generated employing Neural Networks (NN), combined with a combination framework containing an Evidential Reasoning framework to accommodate for any conflicting situations between the bi-group classifiers. A number of different feature selection techniques were investigated with the aim of generating the most appropriate input vector for the bi-group classifiers. It was found that by reducing the original input feature vector, the generalisation ability of the classifiers, when exposed to unseen data, was enhanced and subsequently this reduced the computational requirements of the network itself. The entire framework was compared with a conventional approach to NN classification and a rule based classification approach. The framework attained a significantly higher level of classification in comparison with the other methods; 80.0% compared with 66.7% for the rule based technique and 68.00% for the conventional neural approach.

Computer Simulation↗
PubMed1998

Classification of childhood arthritis: a work in progress.

The classification of chronic childhood arthritis has challenged physicians for a century. Currently used classifications are all based on clinical characteristics and because they are frequently used imprecisely, communication of scientific data has been difficult. The new classification of the International League of Associations of Rheumatologists (ILAR) represents the results of an international effort to clarify the classification of this group of diseases based on identification of clinically homogeneous groups. This classification process is ongoing, and will reflect the results of scientifically based studies as they become available.

Arthritis, Juvenile↗
PubMed2003

"Probable" versus "confirmed" leptospirosis: an epidemiologic and clinical comparison utilizing a surveillance case classification.

PURPOSE: For surveillance purposes, the Centers for Disease Control and Prevention and Council of State and Territorial Epidemiologists (CDC/CSTE) have defined two case classifications for leptospirosis: "confirmed" and "probable." The objective of this study was to provide data to refine the current surveillance case classifications. METHODS: All reported leptospirosis infections from exposures within the State of Hawaii, 1974 to 1998 meeting CDC/CSTE "confirmed" and "probable" case classifications were compared on a number of clinical and epidemiologic parameters. RESULTS: Confirmed cases (n = 276) had more severe clinical manifestations than probable cases (n = 180); however, probable cases with higher peak microscopic agglutination test (MAT) titers (> or =1:800) were clinically and epidemiologically comparable to confirmed cases. In addition, 77 cases demonstrating fourfold or greater MAT titer increases in paired serum collected less than two weeks apart (currently excluded from the "confirmed" case classification) were also comparable to confirmed cases. CONCLUSIONS: Our findings support amending the current CDC/CSTE surveillance confirmed case classification to include demonstration of a fourfold or greater MAT titer increase in paired serum, irrespective of the interval between specimen collection. Consideration should also be given to including single MAT titer > or =1:800 as a criterion for "confirmation." These changes would both simplify and expedite the surveillance confirmation of leptospirosis.

Diagnosis, Differential↗
PubMed2002

A Bayesian method for classification of images from electron micrographs.

Particle classification is an important component of multivariate statistical analysis methods that has been used extensively to extract information from electron micrographs of single particles. Here we describe a new Bayesian Gibbs sampling algorithm for the classification of such images. This algorithm, which is applied after dimension reduction by correspondence analysis or by principal components analysis, dynamically learns the parameters of the multivariate Gaussian distributions that characterize each class. These distributions describe tilted ellipsoidal clusters that adaptively adjust shape to capture differences in the variances of factors and the correlations of factors within classes. A novel Bayesian procedure to objectively select factors for inclusion in the classification models is a component of this procedure. A comparison of this algorithm with hierarchical ascendant classification of simulated data sets shows improved classification over a broad range of signal-to-noise ratios.

Algorithms↗
PubMedDate not supplied

Trauma-instability-voluntarism classification for glenohumeral instability.

Classification of glenohumeral instability is confusing. We think that the existence of trauma, directions of instability, voluntarism, and other factors make classification difficult. The purpose of this article is to create a new classification. One hundred eighty-nine patients with glenohumeral instability involving 207 joints (mean patient age 21.5 years) were subjects of this investigation. Our new classification, which is composed of three main factors (level of trauma, direction of instability, and voluntarism) and some subfactors, simplified it quite well. Abbreviations also make it easier to indicate each joint's condition. About half the subjects had no trauma or mild trauma. Two thirds of the joints with more than one dislocation or subluxation showed instability in other directions in addition to the direction of dislocation or subluxation. This classification is very useful to compare pathogenesis and results of treatment in patients with glenohumeral instability.

Adolescent↗
PubMed1998

The number of metastatic lymph nodes: a promising prognostic determinant for gastric carcinoma in the latest edition of the TNM classification.

BACKGROUND: The number of metastatic regional lymph nodes determines the new pN categories in the 5th edition of the TNM classification. STUDY DESIGN: Our retrospective study was conducted to compare the new method of defining lymph node status with the conventional classification, consisting of the anatomic extent of lymph node metastases, a well-established prognostic factor. The study was based on clinical data for 493 patients with gastric carcinomas who underwent potentially curative operations and had histologically confirmed nodal metastases. These patients were stratified into 1) n categories according to the Japanese Classification of Gastric Carcinoma, 2) the new pN categories, and 3) the pN categories determined by the number of metastatic perigastric nodes resected by standard D1 gastrectomy. Survival data were analyzed for each group. RESULTS: The number of metastatic nodes after D2 lymphadenectomy reflected prognosis well and was shown by multivariate analysis to be a strong independent prognostic factor. When the classification was performed limited to the metastatic perigastric nodes, stage migration was evident, but the variable remained competent as a prognostic indicator. CONCLUSIONS: The number of metastatic nodes is a promising determinant in the new international stage classification.

Adult↗
PubMed1998

New classification and diagnostic criteria for diabetes mellitus.

There has been an explosive growth in knowledge about diabetes mellitus since the National Diabetes Data Group promulgated diagnostic criteria and a classification system in 1979 that was largely adopted by the World Health Organization. However, recent findings regarding the levels of glucose associated with development of retinopathy, and growing confusion caused by a system of classification of diabetes based largely on the treatment used have led to a new assessment of the diagnosis and classification of diabetes mellitus. Using new data from population-based studies, and placing emphasis on a pathophysiology-based system of classification, in 1997, the Expert Committee of the American Diabetes Association released its recommendations for the classification and diagnosis of diabetes. The major changes from the 1979 report include: (a) the preferred use of the terms "type 1" and "type 2" instead of "insulin-dependent" and "non-insulin-dependent" to designate the two major types of diabetes mellitus; (b) a simplification of the diagnostic test to two fasting plasma glucose (FPG) determinations; and (c) a lower cutoff for FPG (126 mg/dL) to diagnose diabetes (this level of FPG having been found equivalent to the 200-mg/dL value in the oral glucose tolerance test for diagnosis). These changes provide an easier and more reliable means of diagnosing persons at risk of complications of hyperglycemia. Even though the fasting criterion was lowered, the total number of persons who will be diagnosed with diabetes by exclusive reliance on FPG will actually be somewhat less than with the old criteria. Moreover, epidemiologic data support the recommendation that screening for diabetes should start at age 45 and be repeated every 3 years in persons without risk factors, and earlier and more often in those with risk factors.

Biomarkers↗
PubMed1999

Classification of tetraplegics through automatic movement evaluation.

The general problem of classification of functional movements in humans with spinal cord injuries requires the following questions to be answered: what are the essential kinematic parameters that we have to observe during the movement? Is it possible to estimate preserved motor skills based on kinematics? Which computational method for identification is suited to geometric feature analysis? To answer these questions we have developed the methodology which has two phases: (1) recordings of a series of specified arm movements; and (2) custom made software for graphical presentation of arm movements and the design of wavelet and neural networks for movement classification. The proposed protocol is automated and both graphical presentation and neural networks allow easy interpretation of the instrumented assessment to accomplish automatic classification of arm movements in tetraplegics. The protocol was evaluated on 16 spinal cord injury (SCI) patients and seven healthy control subjects for three different arm movements. The classification rate yielded results in the range 46-100% for movement trials that were tested. The application of neural networks for classification of arm movements is completed with results using different neural networks: backpropagation, radial basis, recurrent (Elman), self-organizing and Learning Vector Quantization (LVQ).

Adolescent↗
PubMed2002

Evaluation of T-classifications of upper gingival and hard palate carcinomas--a proposition for new criterion of T4.

Most carcinomas of upper gingiva and hard palate are classified as T4 stage on the basis of the UICC criteria, since they easily invade the underlying bone tissue. We classified 43 patients with squamous cell carcinoma of the upper gingiva in terms of three criteria: (1) the original T-classification by UICC, (2) the classification by the Japan Society for Head and Neck Cancer (JSHNC), and (3) a new classification in which the maxillary sinus or nasal floor is used as the defining borderline for T4 (MSF classification). Our study demonstrated that the new classification was superior with regard to distribution of patients by T stage, correlation with prognosis and choice of treatment method.

Carcinoma, Squamous Cell↗
PubMed2000

Classification of movement-related EEG in a memorized delay task experiment.

OBJECTIVES: We studied the activation of cortical motor areas during a memorized delay task with a classification technique. METHODS: Multichannel EEG was recorded during the sequence of warning stimulus, visual cue, reaction stimulus, and actual execution of hand or foot movements. Two different approaches are presented: first, we trained a classifier on data from the time segments immediately preceding the actual movements, and analyzed the whole recordings in overlapping segments with this fixed classifier. The classification rates obtained as a function of experimental time reflect the activation of the same cortical areas that are active during the actual movements. In the second approach, we trained classifiers on data segments with the same latency in time as the data tested ('running classifiers'). By this, we checked whether we could detect event-related activity sufficiently marked to allow for correct classification. RESULTS: With the fixed classifier approach we found two maxima of classification: one maximum after processing of the visual cue corresponding to an activation of motor cortex without overt movement, and a second maximum at the time of the actual movement. The first maximum relates to a very short-lived brain state, in the order of 300 ms, while the broad second maximum (1.5 s) indicates a very stable and long-lasting activation. CONCLUSIONS: With the running classifier approach we found similar maxima as with the fixed classifier, indicating that only the activity of motor areas is relevant for classification. Possible implications of our findings for the development of a brain computer interface (BCI) are discussed.

Acoustic Stimulation↗
PubMed2001

An evaluation of symptom classification systems used for the assessment of patients with heart failure in France.

Many systems have been proposed to assess the degree of functional impairment in patients with chronic heart failure in order to be able to draw comparisons between patients and assess the development of the disease in the same patient. The NYHA classification is subjective and insufficiently reproducible and has no real predictive value with respect to the exertion test. The Canadian classification does not contribute much in terms of validation. The Feinstein and Duke University classifications are too complex, not very easy to use and have never been validated. The scale of activity proposed by Goldman gives details on functional impairment by using examples from daily activities, selected for their variety and grouped according to the energy that they require. This classification is highly reproducible and is concordant with the exertion test (duration of the exertion test, VO2 max). However, it is not suitable for France. The examples are not precise enough: in addition, they do not eliminate contradictions that can make the patient impossible to classify. We propose a scale of activity specifically designed for use in France. It is reproducible and the VO2 peaks are highly concordant. Lastly, the questions the patient is asked are progressive, thus avoiding contradictory answers. This classification could prove to be useful in everyday life and also for multi-center studies in French-speaking countries.

Activities of Daily Living↗
PubMed2002

Molecular validation of the modified Vienna classification of colorectal tumors.

Although the Vienna classification has been introduced to resolve discrepancies in histological diagnoses of colorectal tumors between Western and Japanese pathologists, practical applications of this classification scheme have been problematic because invasion of the lamina propria of tumor cells is often difficult to recognize. Therefore, the following refinements of the classification criteria are needed: category 3, low-grade adenoma/dysplasia; category 4, intramucosal borderline neoplasia; 4-a, high-grade adenoma/dysplasia; 4-b, well-differentiated adenocarcinoma; category 5, definite carcinoma; 5-a, intramucosal moderately-differentiated adenocarcinoma; and 5-b, submucosal carcinoma. We attempted to test whether molecular genetic alterations are related to the modified classification scheme and whether they may help to further categorize the various intramucosal neoplasia grades of colorectal tumors. Two-hundred-thirty-two colorectal tumors were examined using flow cytometric analysis of DNA content, polymerase chain reaction microsatellite assays, and single-strand conformational polymorphism assays to detect abnormalities of DNA content, chromosomal allelic loss, and Ki-ras and p53 gene mutations. Microsatellite instability (MSI) was also examined. Frequencies of genetic alterations and DNA aneuploid states increased with an increase in the grade assigned according to the modified Vienna classification. MSI was a rare event in colorectal adenomas and their frequency of MSI did not correlate with tumor grade. The combined genetic and DNA ploidy data support the conclusion that analysis of genetic alterations and DNA aneuploid states may help in appropriate categorization of colorectal tumors according to the modified Vienna scheme. In addition, MSI-positive tumors may represent a specific subtype of colorectal adenomas.

Adenocarcinoma↗
PubMed1997

The Groote Schuur hospital classification of the orbital complications of sinusitis.

The complications of sinusitis have been well described. The most common classifications used for orbital complications have been that of Chandler et al. (1970) and Moloney et al. (1987). With the ready availability of high-resolution computed tomography (CT) scanners, limitations of these classifications have become apparent. The aims of this study were to determine the relative frequency of the various complications associated with acute sinusitis, to determine which groups of sinuses were most frequently involved and to correlate the orbital signs with a new proposed classification of orbital complications. Over a five-year period, 87 consecutive patients were admitted with acute sinusitis. Sixty-three patients (72.4 per cent) had one or more complications. When orbital complications were classified under the proposed classification, all patients with proptosis and/or decreased eye movement had post-septal infection. Visual impairment occurred only in the post-septal group. Most complications had a combination of sinus involvement with the maxillary/ethmoid/frontal combination being the most common. The authors propose a modification of Moloney's classification for orbital complications of acute sinusitis that allows a clear differentiation between pre- and post-septal infection and a radiological differentiation to be made between cellulitis/phlegmon and abscess formation. The latter is of importance when a decision is made on whether surgical intervention is appropriate or not.

Acute Disease↗
PubMed1988

Classification of mental disorder in primary care.

This monograph describes a study designed to test how far the two major international systems of disease classification, International Classification of Diseases (ICD) and International Classification of Health Problems in Primary Care (ICHPPC), can be consistently applied by General Practitioners (GPs) to mental disorder presenting in primary care, and to identify sources of observer variation occurring at different stages of clinical judgement. A group of 27 senior GPs was exposed to a series of real life general practice consultations, either in the form of videotape or written case-vignette material, chosen to reflect a wide range of minor psychiatric problems, differing not only in respect of phenomenology but also of their associations with social stresses and supports, physical illness and personality features. The findings clearly indicate that neither ICD nor ICHPPC can be applied consistently by GPs. However, while the overall diagnostic concordance using ICD and ICHPPC proved to be disappointingly low, agreement on individual observations relating to psychological, physical, personality and social features was moderately good. It was also noted that participants, when given the opportunity, tended to incorporate several domains into their diagnostic conclusions, aiming for a multidimensional formulation, to which neither ICD nor ICHPPC lend themselves. It is, therefore, not surprising that if the principal diagnostic schemata are neither adequate in themselves nor readily applicable to primary care, then GPs are more likely to resort to symptomatic treatment and evade diagnosis when confronted with minor psychiatric morbidity. The consequence of this approach for National Morbidity Surveys and drug trials are discussed. The historical development of multiaxial schemata of classification is briefly traced, the problems associated with DSM-III are discussed, and a comprehensive model of classification is proposed which incorporates the notions of severity and duration as well as of category on the four dimensions of psychological illness, social stresses and supports, personality and physical illness.

Adjustment Disorders↗
PubMed2006

Human cell type diversity, evolution, development, and classification with special reference to cells derived from the neural crest.

Metazoans are composed of a finite number of recognisable cell types. Similar to the relationship between species and ecosystems, knowledge of cell type diversity contributes to studies of complexity and evolution. However, as with other units of evolution, the cell type often resists definition. This review proposes guidelines for characterising cell types and discusses cell homology and the various developmental pathways by which cell types arise, including germ layers, blastemata (secondary development/neurulation), stem cells, and transdifferentiation. An updated list of cell types is presented for a familiar, albeit overlooked model taxon, adult Homo sapiens, with 411 cell types, including 145 types of neurons, recognised. Two methods for organising these cell types are explored. One is the artificial classification technique, clustering cells using commonly accepted criteria of similarity. The second approach, an empirical method modeled after cladistics, resolves the classification in terms of shared features rather than overall similarity. While the results of each scheme differ, both methods address important questions. The artificial classification provides compelling (and independent) support for the neural crest as the fourth germ layer, while the cladistic approach permits the evaluation of cell type evolution. Using the cladistic approach we observe a correlation between the developmental and evolutionary origin of a cell, suggesting that this method is useful for predicting which cell types share common (multipotential) progenitors. Whereas the current effort is restricted by the availability of phenotypic details for most cell types, the present study demonstrates that a comprehensive cladistic classification is practical, attainable, and warranted. The use of cell types and cell type comparative classification schemes has the potential to offer new and alternative models for therapeutic evaluation.

Evolution, Molecular↗
PubMedDate not supplied

Classification of some active compounds and their inactive analogues using two three-dimensional molecular descriptors derived from computation of three-dimensional convex hulls for structures theoretically generated for them.

Two three-dimensional (3D) molecular descriptors are used to classify 73 protease inhibitors against the human immunodeficiency virus type 1 (HIV-1). X-ray structures of these HIV-1 protease bound inhibitors are used as templates to generate the most probable bioactive conformations of the inhibitors. A convex hull computation algorithm is applied to each structure generated. The frequency of atoms lying on the vertexes of each hull is counted. Vertexes of the same atomic charge state are then gathered together as a set of commonly exposed groups for all the structures generated. The first 3D descriptor is computed as the maximum molecular path length among any three distinct commonly exposed groups, while the second 3D one is computed as the maximum molecular path length among any three atoms of nonconvex hull vertexes. We find that the 73 HIV-1 protease inhibitors can be classified by the first 3D descriptor into two groups, which agrees with the result of visual classification using the activity data as a criterion for these compounds. The classification scheme is then used to classify a database of 427 active trypsin inhibitors and their inactive analogues. The structures of these compounds are generated theoretically from steps of energy minimization and molecular dynamics. Classification for all these compounds is performed using the SYBYL hierarchical clustering method on the first 3D descriptor and then the second 3D one computed. It is found that some inactive analogues are completely separated from the active inhibitors at the first stage of classification using the first 3D descriptor. Most of the highly active inhibitors are classified into a cluster at the second stage of classification using the second 3D descriptor. Finally, most of these highly active inhibitors are separated from all the accompanying inactive analogues in the cluster through a structural alignment process using a set of commonly exposed groups determined for them.

Algorithms↗
PubMedDate not supplied

Classification of inhibitors of protein tyrosine phosphatase 1B using molecular structure based descriptors.

Loss of Protein Tyrosine Phosphatase 1B (PTP 1B) activity is known to enhance insulin sensitivity and resistance to weight gain. So potent and orally active PTP1B inhibitors could be potential pharmacological agents for the treatment of Type 2 diabetes and obesity. Classification models of PTP1B inhibitors are developed using a data set containing 128 compounds. Their inhibitory concentrations ranged from -1.59 to 1.68 log units. Initially a two-class (active, inactive) problem is tackled using a number of different methods. The data set was divided into active and inactive classes on the basis of inhibitory activity of the compounds. Molecular structure-based descriptors were calculated and used in the model development. Descriptors encoding the flexibility of the molecules were investigated. Classification models were generated using k-nearest neighbors (k-NN), linear discriminant analysis (LDA), and radial basis function neural network (RBFNN). All models are tested using an external prediction set, compounds not used anywhere during the model development procedure. A five-descriptor model is developed that produces a classification rate of 85.7% for an external prediction set. Then a three-class (active, moderately active, inactive) problem was explored. This time the data set was divided into highly active, moderate, and inactive classes on the basis of inhibitory activity of the compounds. The best classification rate achieved for an external prediction set was 85%. The classification rates achieved indicate that these models could serve as a screening mechanism, to identify potentially useful PTP 1B inhibitors. In addition multiple linear regression and computational neural network models are also developed for prediction of log IC(50) values. All QSAR models are tested using the same external prediction set.

Benzofurans↗