PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “Classification Algorithms”

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 1,531 records · Page 85Linked to original sources
PubMed2000

A practical primary care approach to hematuria in children.

Although hematuria is a common finding in the unselected population of children, the approach to evaluation is quite variable. Changes in the practice of primary care medicine in the United States mandate an approach to common office problems that is practical and realistic. This review addresses three areas: the current approach to evaluation of hematuria in children, a classification of children with hematuria into four distinct and easily identified clinical categories, and the development of an algorithm for application in the primary care setting. Each category is discussed relative to the more-common etiologies of hematuria, with recommendations for appropriate evaluation as well as suggestions of an appropriate referral to the nephrologist. An algorithm is proposed that provides a practical, systematic approach to the problem without the requirement for a specific diagnosis in every patient. The proposed classification and approach to the evaluation of children with hematuria should help simplify and clarify a potentially complex process.

Child↗
PubMed2001

Acne scarring: a classification system and review of treatment options.

Acne is a common condition experienced by up to 80% of people between 11 and 30 years of age and by up to 5% of older adults. In some patients, the severe inflammatory response to Propionibacterium acnes results in permanent, disfiguring scars. Over the past several decades, numerous descriptive terms and surgical techniques have been used to diagnose the types, and improve the appearance, of scarring in those persons with acne. We propose a descriptive, simple, universally applicable acne scar classification system that includes 3 scar types: icepick, rolling, and boxcar. We also have developed an effective treatment algorithm for reconstructing and improving the appearance of acne scars including punch excision, punch elevation, subcutaneous incision (Subcision), and laser skin resurfacing. This new classification system for acne scars enables the physician to more precisely identify scar subtypes. Once the scar type has been defined, appropriate and effective treatment protocols can be developed.

Acne Vulgaris↗
PubMed2006

Applying pattern recognition methods to analyze the molecular properties of a homologous series of nitrogen mustard agents.

The purpose of this research was to analyze the pharmacological properties of a homologous series of nitrogen mustard (N-mustard) agents formed after inserting 1 to 9 methylene groups (-CH2-) between 2 -N(CH2CH2Cl)2 groups. These compounds were shown to have significant correlations and associations in their properties after analysis by pattern recognition methods including hierarchical classification, cluster analysis, nonmetric multi-dimensional scaling (MDS), detrended correspondence analysis, K-means cluster analysis, discriminant analysis, and self-organizing tree algorithm (SOTA) analysis. Detrended correspondence analysis showed a linear-like association of the 9 homologs, and hierarchical classification showed that each homolog had great similarity to at least one other member of the series-as did cluster analysis using paired-group distance measure. Nonmetric multi-dimensional scaling was able to discriminate homologs 2 and 3 (by number of methylene groups) from homologs 4, 5, and 6 as a group, and from homologs 7, 8, and 9 as a group. Discriminant analysis, K-means cluster analysis, and hierarchical classification distinguished the high molecular weight homologs from low molecular weight homologs. As the number of methylene groups increased the aqueous solubility decreased, dermal permeation coefficient increased, Log P increased, molar volume increased, parachor increased, and index of refraction decreased. Application of pattern recognition methods discerned useful interrelationships within the homologous series that will determine specific and beneficial clinical applications for each homolog and methods of administration.

Antineoplastic Agents, Alkylating↗
PubMed1995

Definition and application of a fourier domain texture measure: applications to histological image segmentation.

A texture measure is defined for the purpose of two-dimensional histological image classification, based upon a novel exploitation of the modulus of the Fourier transform. Its implementation in the form of an algorithm is presented and discussed, and employed to classify a set of histological images. The results, which were obtained by the analysis and classification of different mammalian tissue types, compare favourably with established texture recognition techniques. Furthermore, the results suggest that the method has a comparable performance to other techniques at reduced storage and time costs for images of a high grey level resolution.

Algorithms↗
PubMedDate not supplied

[Empirical French criteria for psychoses. III. Algorithms and decision tree].

The present report presents the final results of an empirical investigation initiated to establish operational definitions for schizophrenia and other non-affective psychoses of classical French nosology. For each category, the authors provide diagnostic criteria and algorithms. In addition, they propose a decision tree for the differential diagnosis of psychotic features included in the French classification of mental disorders.

Affective Disorders, Psychotic↗
PubMed2006

Automated functional classification of experimental and predicted protein structures.

BACKGROUND: Proteins that are similar in sequence or structure may perform different functions in nature. In such cases, function cannot be inferred from sequence or structural similarity. RESULTS: We analyzed experimental structures belonging to the Structural Classification of Proteins (SCOP) database and showed that about half of them belong to multi-functional fold families for which protein similarity alone is not adequate to assign function. We also analyzed predicted structures from the LiveBench and the PDB-CAFASP experiments and showed that accurate homology-based functional assignments cannot be achieved approximately one third of the time, when the protein is a member of a multi-functional fold family. We then conducted extended performance evaluation and comparisons on both experimental and predicted structures using our Functional Signatures from Structural Alignments (FSSA) algorithm that we previously developed to handle the problem of classifying proteins belonging to multi-functional fold families. CONCLUSION: The results indicate that the FSSA algorithm has better accuracy when compared to homology-based approaches for functional classification of both experimental and predicted protein structures, in part due to its use of local, as opposed to global, information for classifying function. The FSSA algorithm has also been implemented as a webserver and is available at http://protinfo.compbio.washington.edu/fssa.

Algorithms↗
PubMed2006

Wavelet-based neural network analysis of internal carotid arterial Doppler signals.

In this study, internal carotid arterial Doppler signals recorded from 130 subjects, where 45 of them suffered from internal carotid artery stenosis, 44 of them suffered from internal carotid artery occlusion and the rest of them were healthy subjects, were classified using wavelet-based neural network. Wavelet-based neural network model, employing the multilayer perceptron, was used for analysis of the internal carotid arterial Doppler signals. Multi-layer perceptron neural network (MLPNN) trained with the Levenberg-Marquardt algorithm was used to detect stenosis and occlusion in internal carotid arteries. In order to determine the MLPNN inputs, spectral analysis of the internal carotid arterial Doppler signals was performed using wavelet transform (WT). The MLPNN was trained, cross validated, and tested with training, cross validation, and testing sets, respectively. All these data sets were obtained from internal carotid arteries of healthy subjects, subjects suffering from internal carotid artery stenosis and occlusion. The correct classification rate was 96% for healthy subjects, 96.15% for subjects having internal carotid artery stenosis and 96.30% for subjects having internal carotid artery occlusion. The classification results showed that the MLPNN trained with the Levenberg-Marquardt algorithm was effective to detect internal carotid artery stenosis and occlusion.

Adult↗
PubMed1999

A global learning algorithm for a RBF network.

This article presents a new learning algorithm for the construction and training of a RBF neural network. The algorithm is based on a global mechanism of parameter learning using a maximum likelihood classification approach. The resulting neurons in the RBF network partitions a multidimensional pattern space into a set of maximum-size hyper-ellipsoid subspaces in terms of the statistical distributions of the training samples. An important feature of the algorithm is that the learning process includes both the tasks of discovering a suitable network structure and of determining the connection weights. The entire network and its parameters are thought of evolved gradually in the learning process.

Journal Article↗
PubMed2004

Classification of cereal flours by chemometric analysis of MIR spectra.

Different kinds of cereal flours submitted to various technological treatments were classified on the basis of their mid-infrared spectra by pattern recognition techniques. Classification in the wavelet domain was achieved by using the wavelet packet transform for efficient pattern recognition (WPTER) algorithm, which allowed singling out the most discriminant spectral regions. Principal component analysis (PCA) on the selected features showed an effective clustering of the analyzed flours. Satisfactory classification models were obtained both on training and test samples. Furthermore, mixtures of varying composition of the studied flours were distributed in the PCA space according to their composition.

Algorithms↗
PubMed2004

Accurate classification of protein structural families using coherent subgraph analysis.

Protein structural annotation and classification is an important problem in bioinformatics. We report on the development of an efficient subgraph mining technique and its application to finding characteristic substructural patterns within protein structural families. In our method, protein structures are represented by graphs where the nodes are residues and the edges connect residues found within certain distance from each other. Application of subgraph mining to proteins is challenging for a number reasons: (1) protein graphs are large and complex, (2) current protein databases are large and continue to grow rapidly, and (3) only a small fraction of the frequent subgraphs among the huge pool of all possible subgraphs could be significant in the context of protein classification. To address these challenges, we have developed an information theoretic model called coherent subgraph mining. From information theory, the entropy of a random variable X measures the information content carried by X and the Mutual Information (MI) between two random variables X and Y measures the correlation between X and Y. We define a subgraph X as coherent if it is strongly correlated with every sufficiently large sub-subgraph Y embedded in it. Based on the MI metric, we have designed a search scheme that only reports coherent subgraphs. To determine the significance of coherent protein subgraphs, we have conducted an experimental study in which all coherent subgraphs were identified in several protein structural families annotated in the SCOP database (Murzin et al, 1995). The Support Vector Machine algorithm was used to classify proteins from different families under the binary classification scheme. We find that this approach identifies spatial motifs unique to individual SCOP families and affords excellent discrimination between families.

Algorithms↗
PubMed2005

Robust multi-scale clustering of large DNA microarray datasets with the consensus algorithm.

MOTIVATION: Hierarchical and relocation clustering (e.g. K-means and self-organizing maps) have been successful tools in the display and analysis of whole genome DNA microarray expression data. However, the results of hierarchical clustering are sensitive to outliers, and most relocation methods give results which are dependent on the initialization of the algorithm. Therefore, it is difficult to assess the significance of the results. We have developed a consensus clustering algorithm, where the final result is averaged over multiple clustering runs, giving a robust and reproducible clustering, capable of capturing small signal variations. The algorithm preserves valuable properties of hierarchical clustering, which is useful for visualization and interpretation of the results. RESULTS: We show for the first time that one can take advantage of multiple clustering runs in DNA microarray analysis by collecting re-occurring clustering patterns in a co-occurrence matrix. The results show that consensus clustering obtained from clustering multiple times with Variational Bayes Mixtures of Gaussians or K-means significantly reduces the classification error rate for a simulated dataset. The method is flexible and it is possible to find consensus clusters from different clustering algorithms. Thus, the algorithm can be used as a framework to test in a quantitative manner the homogeneity of different clustering algorithms. We compare the method with a number of state-of-the-art clustering methods. It is shown that the method is robust and gives low classification error rates for a realistic, simulated dataset. The algorithm is also demonstrated for real datasets. It is shown that more biological meaningful transcriptional patterns can be found without conservative statistical or fold-change exclusion of data. AVAILABILITY: Matlab source code for the clustering algorithm ClusterLustre, and the simulated dataset for testing are available upon request from T.G. and O.W.

Algorithms↗
PubMed2003

Mining a tandem mass spectrometry database to determine the trends and global factors influencing peptide fragmentation.

A database of 5500 unique peptide tandem mass spectra acquired in an ion trap mass spectrometer was assembled for peptides derived from proteins digested with trypsin. Peptides were identified initially from their tandem mass spectra by the SEQUEST algorithm and subsequently validated manually. Two different statistical methods were used to identify sequence-dependent fragmentation patterns that could be used to improve fragmentation models incorporated into current peptide sequencing and database search algorithms. The currently accepted "mobile proton" model was expanded to derive a new classification scheme for peptide mass spectra, the "relative proton mobility" scale, which considers peptide ion charge state and amino acid composition to categorize peptide mass spectra into peptide ions containing "nonmobile", "partially mobile", or "mobile" protons. Quantitation of amide bond fragmentation, both N- and C-terminal to any given amino acid, as well as the positional effect of an amino acid in a peptide and peptide length on such fragmentation, has been determined. Peptide bond cleavage propensities, both positive (i.e., enhanced) and negative (i.e., suppressed), were determined and ranked in order of their cleavage preferences as primary, secondary, or tertiary cleavage effects. For example, primary positive cleavage effects were observed for Xaa-Pro and Asp-Xaa bond cleavage for mobile and nonmobile peptide ion categories, respectively. We also report specific pairwise interactions (e.g., Asn-Gly) that result in enhanced amide bond cleavages analogous to those observed in solution-phase chemistry. Peptides classified as nonmobile gave low or insignificant scores, below reported MS/MS score thresholds (cutoff filters), indicating that incorporation of the relative proton mobility scale classification would lead to improvements in current MS/MS scoring functions.

Algorithms↗
PubMed2006

Shape representation and classification using the poisson equation.

We present a novel approach that allows us to reliably compute many useful properties of a silhouette. Our approach assigns, for every internal point of the silhouette, a value reflecting the mean time required for a random walk beginning at the point to hit the boundaries. This function can be computed by solving Poisson's equation, with the silhouette contours providing boundary conditions. We show how this function can be used to reliably extract various shape properties including part structure and rough skeleton, local orientation and aspect ratio of different parts, and convex and concave sections of the boundaries. In addition to this, we discuss properties of the solution and show how to efficiently compute this solution using multigrid algorithms. We demonstrate the utility of the extracted properties by using them for shape classification and retrieval.

Algorithms↗
PubMed2005

Classification of bacterial species from proteomic data using combinatorial approaches incorporating artificial neural networks, cluster analysis and principal components analysis.

MOTIVATION: Robust computer algorithms are required to interpret the vast amounts of proteomic data currently being produced and to generate generalized models which are applicable to 'real world' scenarios. One such scenario is the classification of bacterial species. These vary immensely, some remaining remarkably stable whereas others are extremely labile showing rapid mutation and change. Such variation makes clinical diagnosis difficult and pathogens may be easily misidentified. RESULTS: We applied artificial neural networks (Neuroshell 2) in parallel with cluster analysis and principal components analysis to surface enhanced laser desorption/ionization (SELDI)-TOF mass spectrometry data with the aim of accurately identifying the bacterium Neisseria meningitidis from species within this genus and other closely related taxa. A subset of ions were identified that allowed for the consistent identification of species, classifying >97% of a separate validation subset of samples into their respective groups. AVAILABILITY: Neuroshell 2 is commercially available from Ward Systems.

Algorithms↗
PubMed2004

Clustering of protein structural fragments reveals modular building block approach of nature.

Structures of peptide fragments drawn from a protein can potentially occupy a vast conformational continuum. We co-ordinatize this conformational space with the help of geometric invariants and demonstrate that the peptide conformations of the currently available protein structures are heavily biased in favor of a finite number of conformational types or structural building blocks. This is achieved by representing a peptides' backbone structure with geometric invariants and then clustering peptides based on closeness of the geometric invariants. This results in 12,903 clusters, of which 2207 are made up of peptides drawn from functionally and/or structurally related proteins. These are termed "functional" clusters and provide clues about potential functional sites. The rest of the clusters, including the largest few, are made up of peptides drawn from unrelated proteins and are termed "structural" clusters. The largest clusters are of regular secondary structures such as helices and beta strands as well as of beta hairpins. Several categories of helices and strands are discovered based on geometric differences. In addition to the known classes of loops, we discover several new classes, which will be useful in protein structure modeling. Our algorithm does not require assignment of secondary structure and, therefore, overcomes the limitations in loop classification due to ambiguity in secondary structure assignment at loop boundaries.

Algorithms↗
PubMed2004

Impact of descriptor vector scaling on the classification of drugs and nondrugs with artificial neural networks.

The influence of preprocessing of molecular descriptor vectors for solving classification tasks was analyzed for drug/nondrug classification by artificial neural networks. Molecular properties were used to form descriptor vectors. Two types of neural networks were used, supervised multilayer neural nets trained with the back-propagation algorithm, and unsupervised self-organizing maps (Kohonen maps). Data were preprocessed by logistic scaling and histogram equalization. For both types of neural networks, the preprocessing step significantly improved classification compared to nonstandardized data. Classification accuracy was measured as prediction mean square error and Matthews correlation coefficient in the case of supervised learning, and quantization error in the case of unsupervised learning. The results demonstrate that appropriate data preprocessing is an essential step in solving classification tasks.

Algorithms↗
PubMed2005

Detection of ophthalmic arterial doppler signals with Behcet disease using multilayer perceptron neural network.

Doppler ultrasound is known as a reliable technique, which demonstrates the flow characteristics and resistance of ophthalmic arteries. In this study, ophthalmic arterial Doppler signals were obtained from 106 subjects, 54 of whom suffered from ocular Behcet disease while the rest were healthy subjects. Multilayer perceptron neural network (MLPNN) employing delta-bar-delta training algorithm was used to detect the presence of ocular Behcet disease. Spectral analysis of the ophthalmic arterial Doppler signals was performed by least squares (LS) autoregressive (AR) method for determining the MLPNN inputs. The MLPNN was trained with training set, cross validated with cross validation set and tested with testing set. All these data sets were obtained from ophthalmic arteries of healthy subjects and subjects suffering from ocular Behcet disease. Performance indicators and statistical measures were used for evaluating the MLPNN. The correct classification rate was 96.43% for healthy subjects and 93.75% for unhealthy subjects suffering from ocular Behcet disease. The classification results showed that the MLPNN employing delta-bar-delta training algorithm was effective to detect the ophthalmic arterial Doppler signals with Behcet disease.

Adolescent↗