SEARCH · PubMed Health

Results for “cluster analysis”

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 289 records · Page 16Linked to original sources

PubMed2004

Empirically derived symptom sub-groups correspond poorly with diagnostic criteria for functional dyspepsia and irritable bowel syndrome. A factor and cluster analysis of a patient sample.

AIM: To determine how clusters (groups) of patients with respect to symptoms compare with a clinical diagnosis in patients with irritable bowel syndrome and non-ulcer dyspepsia. METHODS: All patients who attended a gastroenterology practice at Nepean Hospital were included in the study. All patients received the previously validated Bowel Disease Questionnaire, and were independently assessed by the gastroenterologist. Factor analysis and a k-means cluster analysis were completed. RESULTS: The study population comprised 897 patients [320 males (36%) and 577 females (64%)]. Factor analysis identified nine symptom factors: (1) diarrhoea; (2) constipation; (3) dysmotility; (4) dyspepsia/reflux; (5) nausea/vomiting; (6) bowel; (7) meal-related pain; (8) weight loss; and (9) abdominal pain. A k-means cluster analysis identified seven distinct subject groups, which included an undifferentiated group: (1) diarrhoea; (2) meal-related pain; (3) abdominal pain; (4) faecal indicators; (5) nausea/vomiting/weight loss; and (6) constipation. The majority of irritable bowel syndrome patients fitted into two cluster groups [diarrhoea (25%) and constipation (20%)], whereas those with non-ulcer dyspepsia predominantly fitted into the undifferentiated cluster (34%) and the nausea/vomiting cluster (18%). CONCLUSION: This study supports the concept of symptom subgroups, including the subdivision of patients into diarrhoea- and constipation-predominant irritable bowel syndrome.

Adolescent↗

PubMed2000

The Use of Cluster Analysis in Distinguishing Farmland Prone to Residential Development: A Case Study of Sterling, Massachusetts.

/ Residential development of farmland is one of the primary driving forces of land degradation in both rural and urban fringe areas throughout the world. The loss of prime agricultural land is of great concern to planning offices and organizations seeking to preserve open space. The objective of this study is to demonstrate the use of clusteranalysis as a possible tool for the identification of farms prone to residential development. Eighty-four farms in Sterling, Massachusetts, were separated into two groups by k-means nonhierarchical cluster analysis using farm size, slope, and distance to the nearest city center and highway as surrogates of farmland conversion. Discriminant analysis showed that the two groups derived from the cluster analysis were 98.8% accurate (P < 0.0000). Results from the statistical analysis may serve as a starting point for the identification of individual farms prone to residential development. To explain the driving forces of farmland conversion to residential uses, interviews should be conducted with farmers, landowners, and land buyers. The use of multivariate statistical techniques to identify farms in jeopardy of residential development, in conjunction with qualitative assessments that explain the probability of development of individual farms, may prove a useful strategy to understand and predict farmland conversion.

Journal Article↗

PubMed2004

Cluster analysis of soft X-ray spectromicroscopy data.

Soft X-ray spectromicroscopy provides spectral data on the chemical speciation of light elements at sub-100 nm spatial resolution. When all chemical species in a specimen are known and separately characterized, existing approaches can be used to measure the concentration of each component at each pixel. In other cases (such as often occur in biology or environmental science), some spectral signatures may not be known in advance so other approaches must be used. We describe here an approach that uses principal component analysis to orthogonalize and noise-filter spectromicroscopy data. We then use cluster analysis (a form of unsupervised pattern matching) to classify pixels according to spectral similarity, to extract representative, cluster-averaged spectra with good signal-to-noise ratio, and to obtain gradations of concentration of these representative spectra at each pixel. The method is illustrated with a simulated data set of organic compounds, and a mixture of lutetium in hematite used to understand colloidal transport properties of radionuclides.

Cluster Analysis↗

PubMed2004

Biosphere: the interoperation of web services in microarray cluster analysis.

UNLABELLED: The growing use of DNA microarrays in biomedical research has led to the proliferation of analysis tools. These software programs address different aspects of analysis (e.g. normalisation and clustering within and across individual arrays) as well as extended analysis methods (e.g. clustering, annotation and mining of multiple datasets). Therefore, microarray data analysis typically requires the interoperability of multiple software programs involving different analysis types and methods. Such interoperation is often hampered by the heterogeneity inherent in the software tools (which may function by implementing different interfaces and using different programming languages). To address this problem, we employed the simple object access protocol (SOAP)-based web service approach that provides a uniform programmatic interface to these heterogeneous software components. To demonstrate this approach in the microarray context, we created a web server application, Biosphere, which interoperates a number of web services that are geographically widely distributed. These web services include a clustering web service, which is a suite of different clustering algorithms for analysing microarray data; XEMBL, developed at the European Bioinformatics Institute (EBI) for retrieving EMBL Nucleotide Sequence Database sequence data; and three gene annotation web services: GetGO, GetHAPI and GetUMLS. GetGO allows retrieval of Gene Ontology (GO) annotation, and the other two web services retrieve annotation from the biomedical literature that is indexed based on the Medical Subject Headings (MeSH) terms. With these web services, Biosphere allows the users to do the following: (i) cluster gene expression data using seven different algorithms; (ii) visualise the clustering results that are grouped statistically in colour; and (iii) retrieve sequence, annotation and citation data for the genes of interest. AVAILABILITY: Biosphere and its web services described in Web Service Description Language (WSDL) can be accessed at http://rook.cecid.hku.hk:8280/BiosphereServer.

Cluster Analysis↗

PubMed1978

Behavioural syndromes identified by cluster analysis in a sample of 100 severely and profoundly retarded adults.

Very little is known about psychiatric disorders in severely and profoundly retarded adults. We have investigated these disorders by systematically recording and collecting data about the behaviour of 100 severely and profoundly retarded hospitalized adults and subjecting the data thus derived to cluster analysis. Eight clusters were isolated. The clinical psychiatric significance of these clusters is discussed and their relationship to cause retardation, duration of stay in hospital and visiting is considered. A diagnostic framework for psychiatric disorder in severely and profoundly retarded adults is put forward and some possible treatment approaches are suggested.

Adult↗

PubMed2006

Improved temporal clustering analysis method for detecting multiple response peaks in fMRI.

PURPOSE: To develop an improved temporal clustering analysis (TCA) method for detecting multiple active peaks by running the method once. MATERIALS AND METHODS: Two cases of simulation data and a set of actual fMRI data from nine subjects were used to compare the traditional TCA method with the new method, termed extremum TCA (ETCA). The first case of simulation data simulated event-related activation and block activation in one cerebral area, and the second case simulated event-related activation and block activation in two cerebral areas. An in vivo visual stimulating experiment was performed on a 1.5T MR scanner. All imaging data were processed using both traditional TCA and the new method. RESULTS: The results of both the simulated and actual fMRI data show that the new method is more sensitive and exact than traditional TCA in detecting multiple response peaks. CONCLUSION: The new method is effective in detecting multiple activations even when the timing and location of the brain activation are completely unknown.

Brain Mapping↗

PubMed1989

Cellulase families revealed by hydrophobic cluster analysis.

The amino acid sequences of 21 beta-glycanases have been compared by hydrophobic cluster analysis. Six families of cellulases have been identified on the basis of primary structure homology: (A) endoglucanases B, C and E of Clostridium thermocellum; endoglucanases of Erwinia chrysanthemi and Bacillus sp.; endoglucanase III of Trichoderma reesei; endoglucanase I of Schizophyllum commune; (B) cellobiohydrolase II of T. reesei; endoglucanases of Cellulomonas fimi and Streptomyces sp; (C) cellobiohydrolases I of T. reesei and of Phanerochaete chrysosporium; endoglucanase I of T. reesei; (D) endoglucanase A of C. thermocellum and an endoglucanase from Ce. uda; (E) endoglucanase D of C. thermocellum and an endoglucanase from Pseudomonas fluorescens; (F) xylanases of C. thermocellum and of Cryptococcus albidus and the cellobio-hydrolase of Ce. fimi. For each family, conserved potentially catalytic residues have have been listed and previous allocations of the active-site residues are evaluated in the light of the alignment of the amino acid sequences. A strong homology is also reported for the putative cellulose-binding domains of cellulases of Ce. fimi and of P. fluorescens.

Amino Acid Sequence↗

PubMed1984

Cluster analysis of visual cortical responses evoked by moving lines.

The cortical evoked responses to a bar of light (line) moving in 8 different directions across the visual field of 6 unanaesthetized, immobilized cats were compared in 18 experimental sessions. The shape of the response is unique for each direction. This is particularly apparent during the first 350 msec of the response. Cluster analysis of the evoked potentials reveals that the recognition of the direction of the moving line is probably less distinct when the line moves in a downward direction. This finding is more pronounced in the left hemisphere. The results of the cluster analysis indicate that the technique may be a useful tool in the analysis and classification of large numbers of evoked potentials. Furthermore, such clustering may eventually reveal some of the physiological mechanisms that contribute to the shape of the evoked response.

Animals↗

PubMed1986

Effects of naloxone upon the behavioural organisation of specific defeat activities in intruder mice: assessment by cluster analysis.

The present experiment examined the effects of naloxone (0.5, 2.5 and 12.5 mg/kg) upon the responses of male Swiss mice to attack by aggressive male conspecifics in the resident-intruder paradigm by measuring the time spent in broad behavioural categories, frequency of individual acts or postures, and performing a cluster analysis of activities according to their frequency and position within the behavioural sequence. The former two measures detected little naloxone-induced change in behaviour. Cluster analysis revealed changes in behavioural organisation which suggested modification in the motivation and/or function underlying specific defeat behaviour.

Aggression↗

PubMed2004

Clustering analysis of SAGE data using a Poisson approach.

Serial analysis of gene expression (SAGE) data have been poorly exploited by clustering analysis owing to the lack of appropriate statistical methods that consider their specific properties. We modeled SAGE data by Poisson statistics and developed two Poisson-based distances. Their application to simulated and experimental mouse retina data show that the Poisson-based distances are more appropriate and reliable for analyzing SAGE data compared to other commonly used distances or similarity measures such as Pearson correlation or Euclidean distance.

Animals↗

PubMed2002

Cluster analysis of symptoms during antidepressant treatment with Hypericum extract in mildly to moderately depressed out-patients. A meta-analysis of data from three randomized, placebo-controlled trials.

RATIONALE: Although extracts from Hypericum have long played a major role in the treatment of mild to moderate depression, information pertaining to the drug's therapeutic profile is sparse. OBJECTIVES: To investigate whether the administration of the Hypericum extract has a selective effect on particular signs and symptoms of depression as opposed to a more general acceleration of recovery. METHODS: A meta-analysis was performed on the original data of three double-blind, randomized multicenter trials, during which 544 out-patients suffering from mild to moderate depression according to DSM-IV criteria received 3x300 mg/day Hypericum extract (WS 5570 or WS 5572) or placebo over a double-blind treatment period of 6 weeks. The primary outcome measure for treatment efficacy in the original trials was the change in the total score of the Hamilton Rating Scale for Depression (HAMD, 17-item version) between baseline and treatment end. The relationship between the symptoms of depression represented by the items of the HAMD was assessed by means of cluster analysis and individual item analysis. RESULTS: Two clusters of items were identified which were stable in several independent subsets of the full data set. While cluster 1 (HAMD items 1, 2, 3, 7, 8, 12, 13, 14, 16) was interpreted to represent the core symptoms of depression (including somatic aspects), cluster 2 (items 4, 5, 6, 9, 10, 11, 15, 17) was primarily composed of items assessing depression-related anxiety and insomnia. In both clusters, Hypericum extract reduced the symptoms of depression more effectively than placebo. However, the herbal drug was particularly effective in the core symptoms of the disorder. CONCLUSIONS: The results indicate that Hypericum extract accelerated the recovery from depression in a rather general manner, by influencing all investigated signs and symptoms of the disease. The drug's therapeutic profile was thus found to be similar to the profile of selective serotonin reuptake inhibitors.

Antidepressive Agents↗

PubMed1995

A cluster analysis of detected and substantiated child maltreatment incidents in rural Colorado.

This paper reports the results of a cluster analysis of the incidents of detected and substantiated child maltreatment in 31 rural Colorado counties during the 5-year period (1986-1990). Mapping and statistical techniques employed revealed time-space clustering in the occurrence of child abuse and neglect in sparsely settled rural areas of the state. The study examined temporal-geographic patterns among all 830 confirmed incidents in the Colorado Child Abuse and Neglect Registry for counties of less than 10,000 population. These findings suggest that a first incident of abuse or neglect serves as a sentinel event, predicting a period of more frequent receipt and substantiation of maltreatment cases by child protection professionals in the county or community of occurrence. Clustering was apparent using 3-, 7-, 14-, 30-, and 60-day intervals of time; a scheme endorsed by the Centers for Disease Control for national study of the epidemicity of adolescent suicide. An agenda is proposed to review the appropriateness and adequacy of child protection policies and protocols in view of this phenomenon, and to pursue additional related research objectives.

Child↗

PubMed1990

The use of cluster analysis in clinical chemical diagnosis of liver diseases.

Diagnostic judgement is usually based on recognition of patterns. Unfortunately more than three quantitative data cannot be judged simultaneously without help of mathematical methods. Working on laboratory reports, a clinician usually goes linearly through the columns and reduces quantitative to qualitative data. Therefore the medical decision process should be improved if data reduction is performed with the aid of mathematical methods for pattern recognition. A total of 191 consecutive outpatients with a tentative or proven diagnosis of hepatobiliary disease were examined clinically, clinically chemically and partly histologically. Nineteen clinical chemical parameters were determined. Prior to pattern cognition, a principal component analysis was performed. Using six factors, accounting for 72.4% of total variance, cluster analysis was done, applying a hierarchical algorithm for ascertaining a starting partition, followed by the k-means algorithm. The validity of the solution was scrutinized, and a stable structure was found with nine clusters. Patients with a rejected suspect of liver disease were mainly located in clusters 1, 6 and 7. Cluster 1 also contains patients with compensated cirrhosis without inflammation, idiopathic hyperbilirubinaemia, focal nodular hyperplasia and haemangioma of the liver. In contrast, one third of cirrhoses, all with inflammatory activity were assigned to cluster 5. Patients with primary biliary disease were distributed among clusters 2, 3 and 4. All malignant neoplasias were assigned to cluster 9. More than 50% of fatty livers were classified to cluster 7. Cluster 2 and 8 contain only one patient with primary biliary cirrhosis (cluster 2) and fatty liver hepatitis (cluster 8). The follow-up of 66 patients also showed clinically meaningful changes of cluster assignment.

Cluster Analysis↗

PubMed2006

Incorporating biological knowledge into distance-based clustering analysis of microarray gene expression data.

MOTIVATION: Because co-expressed genes are likely to share the same biological function, cluster analysis of gene expression profiles has been applied for gene function discovery. Most existing clustering methods ignore known gene functions in the process of clustering. RESULTS: To take advantage of accumulating gene functional annotations, we propose incorporating known gene functions into a new distance metric, which shrinks a gene expression-based distance towards 0 if and only if the two genes share a common gene function. A two-step procedure is used. First, the shrinkage distance metric is used in any distance-based clustering method, e.g. K-medoids or hierarchical clustering, to cluster the genes with known functions. Second, while keeping the clustering results from the first step for the genes with known functions, the expression-based distance metric is used to cluster the remaining genes of unknown function, assigning each of them to either one of the clusters obtained in the first step or some new clusters. A simulation study and an application to gene function prediction for the yeast demonstrate the advantage of our proposal over the standard method.

Algorithms↗

PubMed2005

Investigating spiritual care perceptions and practice patterns in Hong Kong nurses: results of a cluster analysis.

AIM: Nurses' spiritual care perceptions and practices are explored by identifying profiles of nurses studying in a part-time baccalaureate course in a local Hong Kong university. Relationships between nurses' spiritual care perceptions and their practices are explored. RESEARCH METHOD: Hundred and ninety three nurses completed a structured questionnaire. OUTCOME MEASURES: Spiritual care perceptions and practices. RESULTS: Two-step cluster analysis yielded three clusters. Clusters A, B, and C consisted of 15.0% (n = 29), 44.6% (n = 86), and 40.4% (n = 78), respectively. Cluster A nurses were characterized by relatively negative spiritual care perceptions and practices. Cluster C nurses reported positive perceptions, but negative practices; they mainly chose 'uncertain' for most items on both scales. Cluster B was a large group of nurses holding both positive spiritual care perceptions and practices. Significant differences towards spiritual care were found among clusters. Nurses' perceptions were significant positively correlated with practices (r = 0.62). High positive correlations were found between the two scales (r = 0.83) for nurses in Cluster A, for nurses in Clusters B and C, low positive correlations (r = 0.37) were found. CONCLUSION: Three clusters of Hong Kong nurses were differentiated. They showed differences in the level of their spiritual care perceptions and practices. Despite their level of spiritual care perceptions, nurses seldom incorporated spiritual care practices into their daily nursing care, and the level of spiritual care awareness of some nurses was low. Findings may be used to improve support of nurses, to ensure sensitive spiritual care in their daily practices, and to enhance nursing curricula.

Adult↗

PubMed2004

Cluster analysis of water molecules in alanine racemase and their putative structural role.

Conservation of water molecules was identified by a cluster analysis of seven crystal structures of alanine racemase from Bacillus stearothermophilus. A total of 47 clusters of consensus water sites were determined and found to be highly localized, as indicated by their low mobilities. These clusters are located in the region of the active sites as well as at the interface between the N-terminal domain (the alpha/beta-barrel) of the first monomer and the C-terminal domain of the second monomer. The clusters located at the dimer interface form extensive hydrogen-bonding networks linked to the protein backbone. These water-mediated hydrogen bonds, and also all hydrogen-bonding interactions at the dimer interface, were monitored during a 2 ns molecular dynamics simulation and showed that when the inhibitor propionate was bound to the enzyme, some of these interactions were disrupted. The data we present here indicate that the consensus water sites identified at the interface between the two monomers of alanine racemase may play a structural role, which is to maintain and stabilize the alanine racemase dimer. A second role might be to supply the active site continuously with water molecules in order to allow rapid equilibration of active site protons with the solvent.

Alanine↗

PubMed1988

Comparison of 16S rRNA sequences from the family Pasteurellaceae: phylogenetic relatedness by cluster analysis.

The taxonomy of the family Pasteurellaceae has remained controversial despite investigations of biochemistry, serology, and nucleic acid relatedness. In an attempt to resolve some of this confusion, we have partially sequenced the 16S rRNAs of seven members of the family, representing all three genera. The sequences were aligned, similarity scores calculated, and single, average and complete linkage cluster analysis of the resulting distance matrix performed. In this way, an evolutionary branching pattern of these closely related species was reconstructed, and the approximate phylogenetic position of the family determined. Actinobacillus (Haemophilus) actinomycetemcomitans clustered with Haemophilus instead of Actinobacillus, supporting transfer of this species to the genus Haemophilus. Thus cluster analysis of phylogenetic relatedness was found to be particularly useful for studying closely related organisms, and could be performed using a microcomputer.

Actinobacillus↗

PubMed1992

[Computed cluster analysis of citations as a tool in studying structures of research trends].

The method of computer cluster-analysis of citation to determine the structure of a scientific trend is suggested. The map of the current status of research in neurobiology of aging as one of the most promising research areas in gerontology is under consideration. The possibilities and perspectives of this method as a tool of science-of-science research in medicine are analyzed.

Aging↗