PubMed Health⌕ Search

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 901 records · Page 50Linked to original sources
PubMed2006

Extent of horizontal gene transfer in evolution of Streptococci of the salivarius group.

The phylogenetically closely related species Streptococcus salivarius and Streptococcus vestibularis are oral bacteria that are considered commensals, although they can also be found in human infections. The relationship between these two species and the relationship between strains isolated from carriers and strains responsible for invasive infections were investigated by multilocus sequence typing and additional sequence analysis. The clustering of several S. vestibularis alleles and the extent of genomic divergence at certain loci support the conclusion that S. salivarius and S. vestibularis are separate species. The level of sequence diversity in S. salivarius alleles is generally high, whereas that in S. vestibularis alleles is low at certain loci, indicating that the latter species might have evolved recently. Cluster analysis indicated that there has been genetic exchange between S. salivarius and S. vestibularis at three of the nine loci investigated. Horizontal gene transfer between streptococci belonging to the S. salivarius group and other oral streptococci was also detected at several loci. A high level of recombination in S. salivarius was revealed by allele index association and split decomposition sequence analyses. Commensal and infection-associated S. salivarius strains could not be distinguished by cluster analysis, suggesting that the pathogen isolates are opportunistic. Taken together, our results indicate that there is a high level of gene exchange that contributes to the evolution of two streptococcal species from the human oral cavity.

Base Sequence↗
PubMed2000

Host-correlated morphological variation of Myzus persicae (Hemiptera: Aphididae) populations in Greece.

Morphological variation in nine characters of 157 clones of Myzus persicae (Sulzer) was examined by multivariate analysis. The clones were collected from peach, Prunus persica, the primary host and the secondary hosts tobacco, Nicotiana tabacum, cabbage, Brassica oleracea, sugarbeet, Beta vulgaris and pepper Capsicum annuum. The 156 clones originated from various regions of Greece, both in the north, where a large part of the population has an annual bisexual generation on peach, and in more southerly regions, where populations are predominantly unisexual. One clone was collected from tobacco in Caserta, Italy. All clones were laboratory-reared on potato. Canonical variate analysis, hierarchical cluster analysis and a non-parametric classification tree method both revealed morphological differences associated with the host-plant on which they were collected. The scores of the first two canonical variates separated the tobacco-feeding clones from those originating from other secondary host-plants. However, in tobacco-growing areas the tobacco-feeding form predominated in spring populations on peach, and was sometimes found on other secondary hosts. In addition, using cluster analysis, the clones from tobacco which were sampled in the most southeasterly region showed a relatively large phenotypic distance from those collected further north and west. Moreover, clonal phenotypes were affected both by host plant and by long-term parthenogenetic rearing. However, in spite of these effects, the tobacco form was generally distinguishable from aphids originating from other hosts, indicating that the difference must have a genetic basis. In separate analyses of the clones originating from secondary hosts no association was found between morphology and either life cycle category or colour. Discriminant analysis showed that 89% of 1723 specimens could be correctly classified into the two groups.

Animals↗
PubMed1989

[Multivariate statistical analysis in stabilometry in human upright standing (the first report)--age-related factor].

Posturography is not a clearly defined examination. Recently a number of parameters can be obtained in stabilometry by means of computers. To evaluate each parameter and to decide its normal range, subject's age must be considered. The age-related factors found in stabilometry were studied in terms of both multiple regression analysis and cluster analysis. The parameters used in this study were as follows: the area of an ellipse for rejection and of the figure displayed on an X-Y recorder, the maximum width on both the X axis (left and right direction) and the Y axis (anterior and posterior direction), the total length and the sum of excursion in each direction, the root mean square, the velocity, the acceleration, and the averaged frequency of body sway in both X and Y directions. One hundred normal subjects, aged from the second to sixth decade, including 10 males and 10 females in each decade, were tested. Each subject was asked to stand on a platform in Romberg's position for 60 seconds with both eyes open and closed. The significant parameters to predict age, which were determined by multiple regression analysis, were as follows (P less than 0.05): the averaged frequency in the Y direction with eyes closed, the maximum width in the X direction with eyes open, the area of the ellipse for rejection and of the figure with eyes closed, the maximum width in the Y direction and the area of the ellipse and the velocity in the X direction with eyes open. All test subjects were successfully classified into two groups by cluster analysis. One was the younger group aged less than 40 years and the other was the older group not younger than 40-year-old. However, the difference between with eyes open and with eyes closed was not significant (P less than 0.01) as regards the parameters of root mean square and averaged frequency in both sexes and at every decade. The difference between both sexes was supposed to be significant in the Y direction in the younger group and in the X direction in the older one.

Adult↗
PubMed2005

Multivariate analysis of selected metals in tannery effluents and related soil.

Effluent and relevant soil samples from 38 tanning units housed in Kasur, Pakistan, were obtained for metal analysis by flame atomic absorption spectrophotometric method. The levels of 12 metals, Na, Ca, K, Mg, Fe, Mn, Cr, Co, Cd, Ni, Pb and Zn were determined in the two media. The data were evaluated towards metal distribution and metal-to-metal correlations. The study evidenced enhanced levels of Cr (391, 16.7 mg/L) and Na (25,519, 9369 mg/L) in tannery effluents and relevant soil samples, respectively. The effluent versus soil trace metal content relationship confirmed that the effluent Cr was strongly correlated with soil Cr. For metal source identification the techniques of principal component analysis, and cluster analysis were applied. The principal component analysis yielded two factors for effluents: factor 1 (49.6% variance) showed significant loading for Ca, Fe, Mn, Cr, Cd, Ni, Pb and Zn, referring to a tanning related source for these metals, and factor 2 (12.6% variance) with higher loadings of Na, K, Mg and Co, was associated with the processes during the skin/hide treatment. Similarly, two factors with a cumulative variance of 34.8% were obtained for soil samples: factor 1 manifested the contribution from Mg, Mn, Co, Cd, Ni and Pb, which though soil-based is basically effluent-derived, while factor 2 was found associated with Na, K, Ca, Cr and Zn which referred to a tannery-based source. The dendograms obtained from cluster analysis, also support the observed results. The study exhibits a gross pollution of soils with Cr at levels far exceeding the stipulated safe limit laid down for tannery effluents.

Environmental Monitoring↗
PubMed2002

Issues in the meta-analysis of cluster randomized trials.

Meta-analyses involving the synthesis of evidence from cluster randomization trials are being increasingly reported. These analyses raise challenging methodologic issues beyond those raised by meta-analyses which include only individually randomized trials. In this paper we review and comment on a selected number of these issues, including problems of study heterogeneity, difficulties in estimating design effects from individual trials and the choice of statistical methods.

Cluster Analysis↗
PubMedDate not supplied

Regression analysis with clustered data.

Clustered data are found in many different types of studies, for example, studies involving repeated measures, inter-rater agreement studies, household surveys, crossover designs and community randomized trials. Analyses based on population average and cluster specific models are commonly used for estimating treatment (exposure) effects with clustered data. This paper discusses conditions when one or both types of models are appropriate for estimating causal effects and when there is agreement between population average and cluster specific analyses. Applications of survey sampling methods to the robust estimation of standard errors of estimated treatment parameters are discussed.

Animals↗
PubMed2005

Marginal analysis for clustered failure time data.

Clustered failure time data are commonly encountered in biomedical research where the study subjects from the same cluster (e.g., family) share the common genetic and/or environmental factors such that the failure times within the same cluster are correlated. Two approaches that are commonly used to account for the intra-cluster association are frailty models and marginal models. In this paper, we study the marginal proportional hazards model, where the structure of dependence between individuals within a cluster is unspecified. An estimation procedure is developed based on a pseudo-likelihood approach, and a risk set sampling method is proposed for the formulation of the pseudo-likelihood. The asymptotic properties of the proposed estimators are studied, and the related issues regarding the statistical efficiencies are discussed. The performances of the proposed estimator are demonstrated by the simulation studies. A data example from a child vitamin A supplementation trial in Nepal (Nepal Nutrition Intervention Project-Sarlahi, or NNIPS) is used to illustrate this methodology.

Cluster Analysis↗
PubMed2004

Multivariate statistical techniques for the evaluation of spatial and temporal variations in water quality of Gomti River (India)--a case study.

This case study reports different multivariate statistical techniques applied for evaluation of temporal/spatial variations and interpretation of a large complex water-quality data set obtained during monitoring of Gomti River in Northern part of India. Water quality of the Gomti River, a major tributary of the Ganga River was monitored at eight different sites selected in relatively low, moderate and high pollution regions, regularly over a period of 5 years (1994-1998) for 24 parameters. The complex data matrix (17,790 observations) was treated with different multivariate techniques such as cluster analysis, factor analysis/principal component analysis (FA/PCA) and discriminant analysis (DA). Cluster analysis (CA) showed good results rendering three different groups of similarity between the sampling sites reflecting the different water-quality parameters of the river system. FA/PCA identified six factors, which are responsible for the data structure explaining 71% of the total variance of the data set and allowed to group the selected parameters according to common features as well as to evaluate the incidence of each group on the overall variation in water quality. However, significant data reduction was not achieved, as it needed 14 parameters to explain 71% of both the temporal and spatial changes in water quality. Discriminant analysis showed the best results for data reduction and pattern recognition during both temporal and spatial analysis. Discriminant analysis showed five parameters (pH, temperature, conductivity, total alkalinity and magnesium) affording more than 88% right assignations in temporal analysis, while nine parameters (pH, temperature, alkalinity, Ca-hardness, DO, BOD, chloride, sulfate and TKN) to afford 91% right assignations in spatial analysis of three different regions in the basin. Thus, DA allowed reduction in dimensionality of the large data set, delineating a few indicator parameters responsible for large variations in water quality. This study presents necessity and usefulness of multivariate statistical techniques for evaluation and interpretation of large complex data sets with a view to get better information about the water quality and design of monitoring network for effective management of water resources.

Data Collection↗
PubMed2001

Mosaic structure of the DNA molecules of the human chromosomes 21 and 22.

We calculated nucleotide distribution curves along the DNA molecules of the human chromosomes 21 and 22, their correlations in more than 10,000 equidistant positions, and subjected the correlations to cluster analysis. The cluster analysis demonstrated that both DNA molecules were composed of two types of segments exhibiting qualitatively different correlations. The segments differed most in the correlation of the distribution curves of cytosine and guanine, which was very high in type I segments but weak in type II segments. The type I and II segments also significantly differed in the correlations of the distribution curves of adenine with thymine. In addition, adenine strongly anticorrelated with cytosine but this anticorrelation was uniform along both chromosomes and, therefore, it did not contribute to the distinction of the two types of segments. The segments were up to 100 kbp long but they had nothing in common with isochores. Building blocks of the mosaic structure of the DNA molecules of the human chromosomes 21 and 22 are very similar but different in several interesting aspects from those of E. coli.

Chromosomes, Human, Pair 21↗
PubMed2002

Optimal weight functions for marginal proportional hazards analysis of clustered failure time data.

The choice of weights in estimating equations for multivariate survival data is considered. Specifically, we consider families of weight functions which are constant on fixed time intervals, including the special case of time-constant weights. For a fixed set of time intervals, the optimal weights are identified as the solution to a system of linear equations. The optimal weights are computed for several scenarios. It is found that for the scenarios examined, the gains in efficiency using the optimal weights are quite small relative to simpler approaches except under extreme dependence, and that a simple estimator of an exchangeable approximation to the weights also performs well.

Cluster Analysis↗
PubMed2003

Weighted estimating equations for linear regression analysis of clustered failure time data.

Estimation of regression parameters in linear survival models is considered in the clustered data setting. One step updates from an initial consistent estimator are proposed. The updates are based on scores that are functions of ranks of the residuals, and that incorporate weight matrices to improve efficiency. Optimal weights are approximated as the solution to a quadratic programming problem, and asymptotic relative efficiencies to various other weights computed. Except under strong dependence, simpler methods are found to be nearly as efficient as the optimal weights. The performance of several practical estimators based on exchangeable and independence working models is explored in simulations.

Cluster Analysis↗
PubMed2002

Statistically based postprocessing of phylogenetic analysis by clustering.

MOTIVATION: Phylogenetic analyses often produce thousands of candidate trees. Biologists resolve the conflict by computing the consensus of these trees. Single-tree consensus as postprocessing methods can be unsatisfactory due to their inherent limitations. RESULTS: In this paper we present an alternative approach by using clustering algorithms on the set of candidate trees. We propose bicriterion problems, in particular using the concept of information loss, and new consensus trees called characteristic trees that minimize the information loss. Our empirical study using four biological datasets shows that our approach provides a significant improvement in the information content, while adding only a small amount of complexity. Furthermore, the consensus trees we obtain for each of our large clusters are more resolved than the single-tree consensus trees. We also provide some initial progress on theoretical questions that arise in this context.

Algorithms↗
PubMed2005

Analysis of clustered recurrent event data with application to hospitalization rates among renal failure patients.

End-stage renal disease (commonly referred to as renal failure) is of increasing concern in the United States and many countries worldwide. Incidence rates have increased, while the supply of donor organs has not kept pace with the demand. Although renal transplantation has generally been shown to be superior to dialysis with respect to mortality, very little research has been directed towards comparing transplant and wait-list patients with respect to morbidity. Using national data from the Scientific Registry of Transplant Recipients, we compare transplant and wait-list hospitalization rates. Hospitalizations are subject to two levels of dependence. In addition to the dependence among within-patient events, patients are also clustered by listing center. We propose two marginal methods to analyze such clustered recurrent event data; the first model postulates a common baseline event rate, while the second features cluster-specific baseline rates. Our results indicate that kidney transplantation offers a significant decrease in hospitalization, but that the effect is negated by a waiting time (until transplant) of more than 2 years. Moreover, graft failure (GF) results in a significant increase in the hospitalization rate which is greatest in the first month post-GF, but remains significantly elevated up to 4 years later. We also compare results from the proposed models to those based on a frailty model, with the various methods compared and contrasted.

Biometry↗
PubMed1994

A population-based study of the association of medical manpower with county trauma death rates in the United States.

OBJECTIVE: To determine the association between measures of medical manpower available to treat trauma patients and county trauma death rates in the United States. The primary hypothesis was that greater availability of medical manpower to treat trauma injury would be associated with lower trauma death rates. SUMMARY BACKGROUND DATA: When viewed from the standpoint of the number of productive years of life lost, trauma has a greater effect on health care and lost productivity in the United States than any disease. Allocation of health care manpower to treat injuries seems logical, but studies have not been done to determine its efficacy. The effect of medical manpower and hospital resource allocation on the outcome of injury in the United States has not been fully explored or adequately evaluated. METHODS: Data on trauma deaths in the United States were obtained from the National Center for Health Statistics. Data on the number of surgeons and emergency medicine physicians were obtained from the American Hospital Association and the American Medical Association. Data on physicians who have participated in the American College of Surgeons (ACS) Advanced Trauma Life Support Course (ATLS) were obtained from the ACS. Membership information for the American Association for Surgery of Trauma (AAST) was obtained from that organization. Demographic data were obtained from the United States Census Bureau. Multivariate stepwise linear regression and cluster analysis were used to model the county trauma death rates in the United States. The Statistical Analysis System (Cary, NC) for statistical analysis was used. RESULTS: Bivariate and multivariate analyses showed that a variety of medical manpower measures and demographic factors were associated with county trauma death rates in the United States. As in other studies, measures of low population density and high levels of poverty were found to be strongly associated with increased trauma death rates. After accounting for these variables, using multivariate analysis and cluster analysis, an increase in the following medical manpower measures were associated with decreased county trauma death rates: number of board-certified general surgeons, number of board-certified emergency medicine physicians, number of AAST members, and number of ATLS-trained physicians. CONCLUSIONS: This study confirms previous work that showed a strong relation among measures of poverty, rural setting, and increased county trauma death rates. It also found that counties with more board-certified surgeons per capita and with more surgeons with an increased interest (AAST membership) or increased training (ATLS) in trauma care have lower per-capita trauma death rates.(ABSTRACT TRUNCATED AT 400 WORDS)

Black or African American↗
PubMed2004

Analysis of clusters formed by the moving average of a long-range correlated time series.

We analyze the stochastic function C(n)(i) identical with y(i)-y(n)(i), where y(i) is a long-range correlated time series of length N(max) and y(n)(i) identical with (1/n) Sigma(n-1)(k=0)y(i-k) is the moving average with window n. We argue that C(n)(i) generates a stationary sequence of self-affine clusters C with length l, lifetime tau, and area s. The length and the area are related to the lifetime by the relationships l approximately tau(psi(l)) and s approximately tau(psi(s)), where psi(l)=1 and psi(s)=1+H. We also find that l, tau, and s are power law distributed with exponents depending on H: P(l) approximately l(-alpha), P(tau) approximately tau(-beta), and P(s) approximately s(-gamma), with alpha=beta=2-H and gamma=2/(1+H). These predictions are tested by extensive simulations on series generated by the midpoint displacement algorithm of assigned Hurst exponent H (ranging from 0.05 to 0.95) of length up to N(max)=2(21) and n up to 2(13).

Biophysics↗
PubMed2002

Analysis of clustered binary outcomes using within-cluster paired resampling.

Conditional logistic regression (CLR) is useful for analyzing clustered binary outcome data when interest lies in estimating a cluster-specific exposure parameter while treating the dependency arising from random cluster effects as a nuisance. CLR aggregates unmeasured cluster-specific factors into a cluster-specific baseline risk and is invalid in the presence of unmodeled heterogeneous covariate effects or within-cluster dependency. We propose an alternative, resampling-based method for analyzing clustered binary outcome data, within-cluster paired resampling (WCPR), which allows for within-cluster dependency not solely due to baseline heterogeneity. For example, dependency may be in part caused by heterogeneity in response to an exposure across clusters due to unmeasured cofactors. When both CLR and WCPR are valid, our simulations suggest that the two methods perform comparably. When CLR is invalid, WCPR continues to have good operating characteristics. For illustration, we apply both WCPR and CLR to a periodontal data set where there is heterogeneity in response to exposure across clusters.

Adult↗
PubMed2002

Analysis of clustered and longitudinal binary data subject to response misclassification.

Misclassified clustered and longitudinal data arise in studies where the response indicates a condition identified through an imperfect diagnostic procedure. Examples include longitudinal studies that use an imperfect diagnostic test to assess whether or not an individual has been infected with a specific virus. This article presents methods to implement both population-averaged and cluster-specific analyses of such data when the misclassification rates are known. The methods exploit the fact that the class of generalized linear models enjoys a closure property in the case of misclassified responses. Data from longitudinal studies of infectious disease will illustrate the findings.

Biometry↗