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 1,423 records · Page 79Linked to original sources

PubMed2002

A comparison of maximum covariance and K-means cluster analysis in classifying cases into known taxon groups.

Maximum covariance (MAXCOV) is a method for determining whether a group of 3 or more indicators marks 1 continuous or 2 discrete latent distributions of individuals. Although the circumstances under which MAXCOV is effective in detecting latent taxa have been specified, its efficiency in classifying cases into groups has not been assessed, and few studies have compared its performance with that of cluster analysis. In the present Monte Carlo study, the classification efficiencies of MAXCOV and the k-means algorithm were compared across ranges of sample size, effect size, indicator number, taxon base rate, and within-groups covariance. When the impact of these parameters was minimized, k-means classified more data points correctly than MAXCOV. However, when the effects of all parameters were increased concurrently, MAXCOV outperformed k-means.

Cluster Analysis↗

PubMed1992

A nationwide survey of migraine in France: prevalence and clinical features in adults. GRIM.

In November 1990 a nationwide survey of migraine was conducted in France on a representative sample of residents aged 15 years and older. The diagnosis of migraine was based on the International Headache Society (IHS) classification. In a previous study, we validated a diagnostic algorithm which classifies headache sufferers as IHS migraine, "borderline" migraine, possible migraine and non-migrainous headache. The overall prevalence of migraine patients with the IHS criteria in the present study was 8.1%; another 4% were classified as "borderline" migraine, which we in fact considered as definite migraine. Age, gender and occupation were found to be risk factors for migraine. Neither frequency and duration of attacks nor length of time of disease differed with gender. Expressed intensity of attacks, however, was greater in females.

Adolescent↗

PubMed2004

Comparative homology agreement search: an effective combination of homology-search methods.

Many methods have been developed to search for homologous members of a protein family in databases, and the reliability of results and conclusions may be compromised if only one method is used, neglecting the others. Here we introduce a general scheme for combining such methods. Based on this scheme, we implemented a tool called comparative homology agreement search (chase) that integrates different search strategies to obtain a combined "E value." Our results show that a consensus method integrating distinct strategies easily outperforms any of its component algorithms. More specifically, an evaluation based on the Structural Classification of Proteins database reveals that, on average, a coverage of 47% can be obtained in searches for distantly related homologues (i.e., members of the same superfamily but not the same family, which is a very difficult task), accepting only 10 false positives, whereas the individual methods obtain a coverage of 28-38%.

Databases, Protein↗

PubMed2003

A mathematical programming approach for gene selection and tissue classification.

MOTIVATION: Extracting useful information from expression levels of thousands of genes generated with microarray technology needs a variety of analytical techniques. Mathematical programming approaches for classification analysis outperform parametric methods when the data depart from assumptions underlying these methods. Therefore, a mathematical programming approach is developed for gene selection and tissue classification using gene expression profiles. RESULTS: A new mixed integer programming model is formulated for this purpose. The mixed integer programming model simultaneously selects genes and constructs a classification model to classify two groups of tissue samples as accurately as possible. Very encouraging results were obtained with two data sets from the literature as examples. These results show that the mathematical programming approach can rival or outperform traditional classification methods.

Algorithms↗

PubMed2004

GeneCluster 2.0: an advanced toolset for bioarray analysis.

SUMMARY: GeneCluster 2.0 is a software package for analyzing gene expression and other bioarray data, giving users a variety of methods to build and evaluate class predictors, visualize marker lists, cluster data and validate results. GeneCluster 2.0 greatly expands the data analysis capabilities of GeneCluster 1.0 by adding classification, class discovery and permutation test methods. It includes algorithms for building and testing supervised models using weighted voting and k-nearest neighbor algorithms, a module for systematically finding and evaluating clustering via self-organizing maps, and modules for marker gene selection and heat map visualization that allow users to view and sort samples and genes by many criteria. GeneCluster 2.0 is a stand-alone Java application and runs on any platform that supports the Java Runtime Environment version 1.3.1 or greater. AVAILABILITY: http://www.broad.mit.edu/cancer/software

Algorithms↗

PubMed2005

Regularized ROC method for disease classification and biomarker selection with microarray data.

MOTIVATION: An important application of microarrays is to discover genomic biomarkers, among tens of thousands of genes assayed, for disease classification. Thus there is a need for developing statistical methods that can efficiently use such high-throughput genomic data, select biomarkers with discriminant power and construct classification rules. The ROC (receiver operator characteristic) technique has been widely used in disease classification with low-dimensional biomarkers because (1) it does not assume a parametric form of the class probability as required for example in the logistic regression method; (2) it accommodates case-control designs and (3) it allows treating false positives and false negatives differently. However, due to computational difficulties, the ROC-based classification has not been used with microarray data. Moreover, the standard ROC technique does not incorporate built-in biomarker selection. RESULTS: We propose a novel method for biomarker selection and classification using the ROC technique for microarray data. The proposed method uses a sigmoid approximation to the area under the ROC curve as the objective function for classification and the threshold gradient descent regularization method for estimation and biomarker selection. Tuning parameter selection based on the V-fold cross validation and predictive performance evaluation are also investigated. The proposed approach is demonstrated with a simulation study, the Colon data and the Estrogen data. The proposed approach yields parsimonious models with excellent classification performance.

Algorithms↗

PubMed2006

Automated classification of protein crystallization images using support vector machines with scale-invariant texture and Gabor features.

Protein crystallography laboratories are performing an increasing number of experiments to obtain crystals of good diffraction quality. Better automation has enabled researchers to prepare and run more experiments in a shorter time. However, the problem of identifying which experiments are successful remains difficult. In fact, most of this work is still performed manually by humans. Automating this task is therefore an important goal. As part of a project to develop a new and automated high-throughput capillary-based protein crystallography instrument, a new image-classification subsystem has been developed to greatly reduce the number of images that require human viewing. This system must have low rates of false negatives (missed crystals), possibly at the cost of raising the number of false positives. The image-classification system employs a support vector machine (SVM) learning algorithm to classify the blocks making up each image. A new algorithm to find the area within the image that contains the drop is employed. The SVM uses numerical features, based on texture and the Gabor wavelet decomposition, that are calculated for each block. If a block within an image is classified as containing a crystal, then the entire image is classified as containing a crystal. In a study of 375 images, 87 of which contained crystals, a false-negative rate of less than 4% with a false-positive rate of about 40% was consistently achieved.

Algorithms↗

PubMed1990

Temporal feature extraction and clustering analysis of electromyographic linear envelopes in gait studies.

A technique for automatically clustering linear envelopes of the EMG during gait has been developed which uses a temporal feature representation and a maximum peak matching scheme. This new technique provides a viable way to define compact and meaningful EMG waveform features. The envelope matching is performed by dynamic programming, providing qualitatively the largest numbers of matched peaks and quantitatively a minimum distance measurement. The resulting averaged EMG profiles have low statistical variation and can serve as templates for EMG comparison and further classification.

Algorithms↗

PubMed1997

Digital tomosynthesis in breast imaging.

PURPOSE: To describe and evaluate a method of tomosynthesis breast imaging with a full-field digital mammographic system. MATERIALS AND METHODS: In this tomosynthesis method, low-radiation-dose images were acquired as the x-ray source was moved in an arc above the stationary breast and digital detector. A step-and-expose method of imaging was used. Breast tomosynthesis and conventional images of two imaging phantoms and four mastectomy specimens were obtained. Three experienced readers scored the relative lesion visibility, lesion margin visibility, and confidence in the classification of six lesions. RESULTS: Tomosynthesis image-reconstruction algorithms allow tomographic imaging of the entire breast from a single arc of the x-ray source and at a radiation dose comparable with that in single-view mammography. Except for images of a large mass in a fatty breast, the tomosynthesis images were superior to the conventional images. CONCLUSION: Digital mammographic systems make breast tomosynthesis possible. Tomosynthesis may improve the specificity of mammography with improved lesion margin visibility and may improve early breast cancer detection, especially in women with radiographically dense breasts.

Female↗

PubMed2001

Microarray analysis of trophoblast differentiation: gene expression reprogramming in key gene function categories.

Placental development results from a highly dynamic differentiation program. We used DNA microarray analysis to characterize the process by which human cytotrophoblast cells differentiate into syncytiotrophoblast cells in a purified cell culture system. Of 6,918 genes analyzed, 141 genes were induced and 256 were downregulated by more than 2-fold. Dynamically regulated genes were divided by the K-means algorithm into 9 kinetic pattern groups, then by biologic classification into 6 overall functional categories: cell and tissue structural dynamics, cell cycle and apoptosis, intercellular communication, metabolism, regulation of gene expression, and expressed sequence tag (EST) and function unknown. Gene expression changes within key functional categories were tightly coupled to morphological changes. In several key gene function categories, such as cell and tissue structure, many gene members of the category were strongly activated while others were strongly repressed. These findings suggest that differentiation is augmented by "categorical reprogramming" in which the function of induced genes is enhanced by preventing the further synthesis of categorically related gene products.

Cell Differentiation↗

PubMedDate not supplied

Stability and interpersonal agreement of the interview-based diagnosis of autism.

Interpersonal agreement and stability of the Autism Diagnostic Interview-Revised (ADI-R) was examined in this study. Four raters judging 55 subjects agreed moderately to excellently on the items of the diagnostic algorithm, operationalizing the main autistic symptoms according to the classification guidelines of ICD-10 and DSM-IV. When retesting 33 individuals, some items revealed only weak stability. On the level of domains of autistic behavior and diagnosis, the interrater reliability and retest reliability were consistently convincing.

Adolescent↗

PubMed2006

MultiSeq: unifying sequence and structure data for evolutionary analysis.

BACKGROUND: Since the publication of the first draft of the human genome in 2000, bioinformatic data have been accumulating at an overwhelming pace. Currently, more than 3 million sequences and 35 thousand structures of proteins and nucleic acids are available in public databases. Finding correlations in and between these data to answer critical research questions is extremely challenging. This problem needs to be approached from several directions: information science to organize and search the data; information visualization to assist in recognizing correlations; mathematics to formulate statistical inferences; and biology to analyze chemical and physical properties in terms of sequence and structure changes. RESULTS: Here we present MultiSeq, a unified bioinformatics analysis environment that allows one to organize, display, align and analyze both sequence and structure data for proteins and nucleic acids. While special emphasis is placed on analyzing the data within the framework of evolutionary biology, the environment is also flexible enough to accommodate other usage patterns. The evolutionary approach is supported by the use of predefined metadata, adherence to standard ontological mappings, and the ability for the user to adjust these classifications using an electronic notebook. MultiSeq contains a new algorithm to generate complete evolutionary profiles that represent the topology of the molecular phylogenetic tree of a homologous group of distantly related proteins. The method, based on the multidimensional QR factorization of multiple sequence and structure alignments, removes redundancy from the alignments and orders the protein sequences by increasing linear dependence, resulting in the identification of a minimal basis set of sequences that spans the evolutionary space of the homologous group of proteins. CONCLUSION: MultiSeq is a major extension of the Multiple Alignment tool that is provided as part of VMD, a structural visualization program for analyzing molecular dynamics simulations. Both are freely distributed by the NIH Resource for Macromolecular Modeling and Bioinformatics and MultiSeq is included with VMD starting with version 1.8.5. The MultiSeq website has details on how to download and use the software: http://www.scs.uiuc.edu/~schulten/multiseq/

Algorithms↗

PubMed2005

Evolutional analysis in determining pathogenic versus nonpathogenic mutations of ATPase 6 in human mitochondriopathy.

Because mitochondrial ATPase 6 plays an important role in ATP synthesis, mutations affecting ATPase 6 can undoubtedly cause human diseases. In contrast, the ATPase 6 gene is known to be a fast-evolving gene and has generated enough polymorphisms to allow identity investigation for forensic casework. To investigate these seemingly opposite views, we analyzed amino acid sequences of ATPase 6 in at least 1,266 humans, 102 mammals, and 213 vertebrates. The result showed that the amino acids of human ATPase 6 could be divided into the following four groups. Amino acid residue 192 (affected by alteration at nt 9101) and 79 other residues were variable, and therefore substitutions of these residues would not be pathogenic. Amino acid residue 156 (affected by alteration at nt 8993) and 93 other residues were conserved in Homo sapiens, but not in Mammalia. Therefore, they were potentially pathogenic if altered. Function studies would be necessary to confirm their role in pathogenesis. Amino acid residue 217 (affected by alteration at nt 9176) and 9 other residues were conserved across all species, including S. cerevisiae and E. coli. Mutations involving these residues would be pathogenic, some of which might even be life threatening. The remainder (42 residues) were conserved in Mammalia, but not in yeast and E. coli. They were probably pathogenic if mutated. The classification proposed in this study may, therefore, provide an algorithm for a diagnostic approach when a newly identified change of ATPase 6 is suspected for human mitochondriopathy.

Adenosine Triphosphatases↗

PubMed1996

Juvenile rheumatoid arthritis.

Musculoskeletal problems account for the majority of initial complaints attended to by primary care physicians. It is likely that a child who eventually has juvenile rheumatoid arthritis diagnosed will initially be evaluated by a family physician or a pediatrician. Primary care physicians will play an increasingly important role in management of juvenile rheumatoid arthritis, as the availability of specialists in many communities is limited, and access to them may be further limited by managed care initiatives. This article offers a brief review of the definition and classification of juvenile rheumatoid arthritis and introduces a diagnostic algorithm to provide a simplified approach toward evaluating children with arthritis. Treatment and outcomes are summarized in text and graphic formats.

Age of Onset↗

PubMed1983

The study of depressive disorders using the PSE-ID-CATEGO system.

The PSE-CATEGO-ID system and its approach to the sub-classification of depression is described. The principle of sub-classification partly corresponds to the empirical relationships between symptoms on affective disorder. Comparison of CATEGO and DSM III demonstrates that major differences of classification can arise because of differences of the classificatory algorithm even though similar lists of symptoms are used. Empirical studies of the PSE-CATEGORO-ID system are described and their importance in providing evidence for a rational choice between classificatory system is emphasised.

Anxiety Disorders↗

PubMed1995

Gunshot wounds to the elbow.

Gunshot wound injuries to the elbow are rare. This article presents the experience of the King/Drew Medical Center. Classification and management of these injuries are emphasized. An algorithm is presented.

Adult↗

PubMed2001

The use of 1H magnetic resonance spectroscopy in inflammatory bowel diseases: distinguishing ulcerative colitis from Crohn's disease.

OBJECTIVES: The distinction between the two major forms of inflammatory bowel diseases (IBD), i.e., ulcerative colitis (UC) and Crohn's disease is sometimes difficult and may lead to a diagnosis of indeterminate colitis. We have used 1H magnetic resonance spectroscopy (MRS) combined with multivariate methods of spectral data analysis to differentiate UC from Crohn's disease and to evaluate normal-appearing mucosa in IBD. METHODS: Colon mucosal biopsies (45 UC and 31 Crohn's disease) were submitted to 1H MRS, and multivariate analysis was applied to distinguish the two diseases. A second study was performed to test endoscopically and histologically normal biopsies from IBD patients. A classifier was developed by training on 101 spectra (76 inflamed IBD tissues and 25 normal control tissues). The spectra of 38 biopsies obtained from endoscopically and histologically normal areas of the colons of patients with IBD were put into the validation test set. RESULTS: The classification accuracy between UC and Crohn's disease was 98.6%, with only one case of Crohn's disease and no cases of UC misclassified. The diagnostic spectral regions identified by our algorithm included those for taurine, lysine, and lipid. In the second study, the classification accuracy between normal controls and IBD was 97.9%. Only 47.4% of the endoscopically and histologically normal IBD tissue spectra were classified as true normals; 34.2% showed "abnormal" magnetic resonance spectral profiles, and the remaining 18.4% could not be classified unambiguously. CONCLUSIONS: There is a strong potential for MRS to be used in the accurate diagnosis of indeterminate colitis; it may also be sensitive in detecting preclinical inflammatory changes in the colon.

Adult↗

PubMed1980

Further experience with computer-assisted diagnosis of diseases of the liver and biliary tree.

Computer-assisted classification of disease has largely relied upon testing the diagnostic algorithm in the same population from which it was originally derived, as a means of validation. To evaluate the accuracy of a diagnostic program in which discriminant function analysis is used, we applied it to a separate population, selected by different criteria from those used to define the original case material on which the diagnostic program was based. We selected a group of 315 patients having abnormal values for alkaline phosphatase, bilirubin, or aspartate aminotransferase for further biochemical and immunological investigations. We used a computer program involving discriminant function analysis and classification procedures primed with the results of 10 tests obtained on each of 535 patients in a previous series to allocate those 173 new patients who had diseases of the liver or biliary tree into one of 13 disease groups. The classification was less accurate than was the case in previous cross-validation studies. We developed new discriminants with the new case material, using the same group of tests, and when cross-validation was performed, overall accuracy was greatly improved. These experiences point to the powerful influence of group selection upon computer-assisted diagnostic procedures, and the hazards of applying to one clinical population discriminant functions derived from a different population.

Autoanalysis↗