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 919 records · Page 51Linked to original sources
PubMed2006

Case-cohort designs and analysis for clustered failure time data.

Case-cohort design is an efficient and economical design to study risk factors for infrequent disease in a large cohort. It involves the collection of covariate data from all failures ascertained throughout the entire cohort, and from the members of a random subcohort selected at the onset of follow-up. In the literature, the case-cohort design has been extensively studied, but was exclusively considered for univariate failure time data. In this article, we propose case-cohort designs adapted to multivariate failure time data. An estimation procedure with the independence working model approach is used to estimate the regression parameters in the marginal proportional hazards model, where the correlation structure between individuals within a cluster is left unspecified. Statistical properties of the proposed estimators are developed. The performance of the proposed estimators and comparisons of statistical efficiencies are investigated with simulation studies. A data example from the Translating Research into Action for Diabetes (TRIAD) study is used to illustrate the proposed methodology.

Biometry↗
PubMed2004

A case-control study of sporadic Creutzfeldt-Jakob disease in the United Kingdom: analysis of clustering.

BACKGROUND: The authors investigated whether cases of sporadic Creutzfeldt-Jakob disease (CJD) had lived closer to one another at some time in life than individuals without sporadic CJD. Such a phenomenon would be compatible with some cases resulting from transmission. METHODS: UK sporadic CJD cases occurring from 1990 to 1998 were identified. Age-, sex- and hospital-matched controls were recruited. Lifetime residential histories were obtained by interview, usually with a proxy respondent. With use of Monte Carlo simulation, the residential proximity of cases during various time periods was compared with that expected in the absence of any clustering, using the information collected on the controls. RESULTS: Two hundred twenty sporadic CJD disease cases and 220 controls were included. Cases lived closer together than might be expected in the absence of any disease-clustering mechanism. This evidence became stronger as the critical period during which residential proximity was required to have occurred extended further into the past. CONCLUSIONS: These findings are consistent with some sporadic Creutzfeldt-Jakob disease (CJD) cases resulting from exposure to a common external factor. The rarity of sporadic CJD suggests that repeated point-source outbreaks of infection are more likely to explain our observations than direct case-to-case transmission. Identifying sources of such outbreaks many years after the event will be extremely difficult.

Adult↗
PubMedDate not supplied

An examination of regional migration patterns in Mexico: new and old Mexican regions.

This paper examines Mexican regional patterns. Different regional definitions are utilized to examine in-/out-migration patterns in 4 different periods: 1) 1979-1980, 2) 1975-1979, 3) prior to 1975, and 4) lifetime. 5 regional definitions previously used to delineate state level Mexican regions were compared to new regions by a maximum likelihood clustering technique. Previously defined regions do not compare with the empirically delineated regions developed by the cluster analysis. A cluster analysis of in-/out-migration patterns suggests the following: 1) distinct in-/out-migration patterns for both short- and long-term migration patterns, 2) a central region consisting of Mexico and the Federal District having its own distinct regional characteristics for both in-/out-migration patterns, particularly intraregional migration among those 2 states exceeds any other interregional migration patterns, and 3) the unique role played by Jalisco in mediating long-term inflows prior to 1975, and since 1975, out-migration from the same state. Previous research rarely identified the Central region consisting of Mexico and the Federal District. Using net migration for interregional migration analysis may possibly be misleading since immigration and out-migration phenomena show distinct patterns of geographic mobility at the state level, and such regional differences are consistent for the 4 migration periods. A careful analysis accounting for both distinct migration patterns in the Central region and different patterns in in-/out-migration are necessary to obtain an understanding of regional migration patterns in Mexico.

Americas↗
PubMed1997

Nonparametric analysis of clustered ROC curve data.

Current methods for estimating the accuracy of diagnostic tests require independence of the test results in the sample. However, cases in which there are multiple test results from the same patient are quite common. In such cases, estimation and inference of the accuracy of diagnostic tests must account for intracluster correlation. In the present paper, the structural components method of DeLong, DeLong, and Clarke-Pearson (1988, Biometrics 44, 837-844) is extended to the estimation of the Receiver Operating Characteristics (ROC) curve area for clustered data, incorporating the concepts of design effect and effective sample size used by Rao and Scott (1992, Biometrics 48, 577-585) for clustered binary data. Results of a Monte Carlo simulation study indicate that the size of statistical tests that assume independence is inflated in the presence of intracluster correlation. The proposed method, on the other hand, appropriately handles a wide variety of intracluster correlations, e.g., correlations between true disease statuses and between test results. In addition, the method can be applied to both continuous and ordinal test results. A strategy for estimating sample size requirements for future studies using clustered data is discussed.

Angiography, Digital Subtraction↗
PubMed2004

Sperm subpopulations in Iberian red deer epididymal sperm and their changes through the cryopreservation process.

We have applied a statistical protocol based on principal component analysis, clustering methods, and discriminant analysis for the identification of sperm subpopulations in computer-assisted sperm analysis (CASA) data. Samples were obtained from the cauda epididymis of 11 Iberian red deer and cryopreserved following a standard protocol. Motility by CASA was analyzed just after sperm recovery, just before freezing, and after thawing, and eight motility descriptors for each individual spermatozoon were recorded. Sperm viability and acrosomal status were also assessed. Subpopulation analysis was performed in four sequential steps: principal component analysis using the eight motility descriptors; nonhierarchical clustering analysis (k-means) using the first two principal components; hierarchical clustering analysis (UPGMA); and selection of the final number of clusters. Three clusters were obtained for each motility analysis: slow and nonlinear; rapid and linear; and rapid, high ALH, nonlinear. We detected variations in the clusters between treatments (initial, prefreezing and postthawed). Indeed, motility increased and linearity decreased in the prefreezing analysis. A discriminant analysis isolated three descriptors that were used again in the same statistical analysis, giving four clusters that resembled the pattern found in the first classification. We also performed a clustering analysis of the males according to prefreezing/postthawed variation of total motility, viability, and acrosomal status. The proportion of the linear subpopulations in the prefreezing treatment, in both clustering analyses, correlated positively with postthawed viability recovery. Our results show that clustering analysis of CASA data gives useful and practical information that is not obtained by conventional sperm analysis.

Acrosome↗
PubMed2006

Source apportionment of PM2.5 in urban area of Hong Kong.

A monitoring program for PM(2.5) had been performed at two urban monitoring stations in Hong Kong from November 2000 to February 2001 and June 2001 to August 2001. PM(2.5) samples were collected once every 6 days at PolyU and KT stations with the sampling duration of 24-h. A sum of 25 chemical species in PM(2.5) were determined and selected for receptor models. Enrichment factors relative to earth crust abundances were evaluated and it was noted that most crustal elements including Al, Ti, Mg, Ca and K have small enrichment factors. Correlation and multivariate analysis technique, such as principal components analysis (PCA)/absolute principal components analysis (APCA) and cluster analysis (CA) are used for source apportionment to identify the possible sources of PM(2.5) and to determine their contribution. Six factors at each site were isolated by using PCA/APCA and cluster analysis. Similar sources (crustal matter, automobile emission, diesel emission, secondary aerosols, tire wear, and non-ferrous smelter) are identified by the PCA/APCA and cluster analysis.

Aerosols↗
PubMed2000

Analysis of cluster randomized trials in primary care: a practical approach.

BACKGROUND: Cluster randomized trials increasingly are being used in health services research and in primary care, yet the majority of these trials do not account appropriately for the clustering in their analysis. OBJECTIVES: We review the main implications of adopting a cluster randomized design in primary care and highlight the practical application of appropriate analytical techniques. METHODS: The application of different analytical techniques is demonstrated through the use of empirical data from a primary care-based case study. CONCLUSION: Inappropriate analysis of cluster trials can lead to the presentation of inaccurate results and hence potentially misleading conclusions. We have demonstrated that adjustment for clustering can be applied to real-life data and we encourage more routine adoption of appropriate analytical techniques.

Cluster Analysis↗
PubMed1994

Analysis of clustered data in community psychology: with an example from a worksite smoking cessation project.

Although it is common in community psychology research to have data at both the community, or cluster, and individual level, the analysis of such clustered data often presents difficulties for many researchers. Since the individuals within the cluster cannot be assumed to be independent, the use of many traditional statistical techniques that assumes independence of observations is problematic. Further, there is often interest in assessing the degree of dependence in the data resulting from the clustering of individuals within communities. In this paper, a random-effects regression model is described for analysis of clustered data. Unlike ordinary regression analysis of clustered data, random-effects regression models do not assume that each observation is independent, but do assume data within clusters are dependent to some degree. The degree of this dependency is estimated along with estimates of the usual model parameters, thus adjusting these effects for the dependency resulting from the clustering of the data. Models are described for both continuous and dichotomous outcome variables, and available statistical software for these models is discussed. An analysis of a data set where individuals are clustered within firms is used to illustrate features of random-effects regression analysis, relative to both individual-level analysis which ignores the clustering of the data, and cluster-level analysis which aggregates the individual data.

Cluster Analysis↗
PubMed1995

Identification of proteolytic rumen bacteria isolated from New Zealand cattle.

The protease activities of 212 strains of rumen bacteria isolated from New Zealand cattle grazing pasture were measured. Thirty-seven per cent of strains had activity greater than or equal to the proteolytic rumen bacterium Prevotella ruminicola and 43 of these isolates were identified by morphology, carbon source utilization, Gram stain, biochemical tests and fermentation end-product analysis. Hierarchical Cluster Analysis showed that the strains formed four clusters: cluster A contained 26 strains and clustered with a reference strain of Streptococcus bovis; cluster C contained three strains and clustered with a reference strain of Butyrivibrio fibrisolvens, while clusters B (10 strains) and D (three strains) did not cluster with any of the remaining rumen bacterial type strains. Further tests identified strains of cluster B as Eubacterium budayi, while cluster D strains most closely resembled B. fibrisolvens and were described as B. fibrisolvens-like. An unclustered strain, C21a, was identified as P. ruminicola. The significance of these proteolytic bacterial populations is discussed in relation to protein breakdown in New Zealand ruminants.

Anaerobiosis↗
PubMed2002

Volatile organic compounds in the area of Madrid: a chemometrical approach.

Multivariate techniques have been applied to the set of data obtained after one year sampling of volatile organic compounds (VOCs), including volatile aldehydes in the area of Madrid in order to evaluate the possible correspondence among groups of analysed compounds, as far as modelling of different emission sources in relation to location and season. The measurements were carried out at four sites in Madrid, characteristic for urban and suburban areas. Additionally, as reference, a rural area 100 km far from the city was considered. Results of correlation analysis, factor and cluster analysis are presented. Higher correlations were found between variables related with traffic emissions. Factor analysis results showed two main significant variables related to anthropogenic and biogenic emissions respectively. In relation to cluster analysis, samples were grouped according to sampling site and seasonal variations.

Air Pollutants↗
PubMed2006

Classification of patterns of delirium severity scores over time in an elderly population.

OBJECTIVES: To describe and classify individual trajectories of 15-day changes in delirium severity. METHODS: A longitudinal hospital-based study was carried out with 230 medical inpatients aged 65 and over admitted to St Mary's Hospital in Montreal, Canada, between 1996 and 1999, diagnosed with delirium at enrollment, and who had at least four measurements of delirium severity during the next 15 days. Delirium severity was assessed using the Delirium Index (DI). To classify patients' individual trajectories, we applied a new method that relies on principal factor analysis and cluster analysis. We used multiple linear regression to investigate if clusters were associated with DI scores measured at an 8-week follow-up. Multivariable Cox's proportional hazards regression was used to assess whether the clusters were associated with survival over the next 12 months. RESULTS: Individual patterns were classified into five clusters: Steady (n = 89, 38.9%), Fluctuating (n = 36, 15.7%), Worsening (n = 15, 6.6%), Fast Improve-ment (n = 26, 11.3%), and Slow Improvement (n = 63, 27.5%). The Fast Improvement cluster had much lower prevalence of dementia (38.5% vs. 55.6% to 77.8% in other clusters, p = 0.003). Subjects whose 2-week patterns were classified as Fast or Slow Improvement had a significantly lower DI at 8 weeks than those in the Steady or Fluctuating clusters. The Worsening cluster had the largest percentage of deaths. The Fast Improvement and Worsening clusters initially had a high risk of death in the first 2 weeks (adjusted relative risks of approximately 3 and 6, respectively) but that risk decreased rapidly thereafter. CONCLUSION: Two-week trajectories of delirium severity were associated with short-term mortality and delirium severity at 8-week follow-up.

Aged↗
PubMed1995

A controlled multivariate chart review of multiple complex developmental disorder.

OBJECTIVE: The primary aim of the study was to ascertain the usefulness and the validity of the set of criteria proposed to define a subgroup within the DSM-III-R category of pervasive developmental disorder-not otherwise specified under the name of multiple complex developmental disorder (MCDD). METHOD: A multivariate analysis (cluster and principal-components analysis) was performed on the characteristics, reliably extracted from the charts of 105 children with MCDD, 32 with autistic disorder, 51 with externalizing disorders, and 56 with internalizing disorders, all with an IQ greater than 70, fully assessed in our department between 1984 and 1991. RESULTS: The main finding was a strong correspondence between the classification of the cases by DSM-III-R categories and the subdivision by means of a multivariate cluster analysis. The cluster analysis did not discriminate between children with emotional and disruptive disorders. Furthermore, children with MCDD and autistic disorder were significantly different both on symptom factors ("psychotic thinking/anxiety," "aggression," "deficient interaction/communication," "stereotyped and rigid behavior," and "suspiciousness/odd interaction") and on factors that reflected developmental and environmental background variables. CONCLUSION: The results of this study add to the nosology of autistic spectrum disorders and lend additional support to the need for a separate subcategory of MCDD within DSM-V. Further corroboration of these results in independent (multicenter) samples will be required.

Autistic Disorder↗
PubMed1996

Multivariate statistical analysis of Golgi stained neurons.

The multivariate statistical analysis provides a useful method to study neuronal populations. It allows both the objective classification of neuronal types and the study of the morphological variation within a neuronal population. We report a particular example of the use of these techniques on a Golgi study of a complex telencephalic structure, the reptilian anterior dorsal ventricular ridge (aDVR). We present a R-mode factor analysis and a cluster analysis on the results of the factor analysis. Sixteen original variables were chosen for the study in order to obtain the greatest information about the cell body, the dendritic field and the location of 96 Golgi-stained cells. Six factors were obtained after the R-mode factor analysis, the interpretation of which was clear in five of them. This contributed to explain the morphological variation of the neuronal types within the aDVR. The cluster analysis classified the 96 cells into eight groups. Some groups could be ascribed to specific regions of the aDVR.

Animals↗
PubMed2005

Advancing the molecular diagnosis of thyroid nodules: defining benign lesions by molecular profiling.

BACKGROUND: Thyroid nodules are common and most are benign. Previous data from our laboratory and others has suggested that gene profiling can accurately distinguish between benign and malignant thyroid nodules and provide new leads in the study of thyroid tumorigenesis. Current preoperative techniques do not permit distinction between neoplastic and hyperplastic follicular neoplasms. These studies were undertaken to determine whether benign follicular tumors could be subcategorized by molecular profiling. METHODS: Molecular profiles of 8 follicular adenomas and 8 hyperplastic nodules were analyzed by oligonucleotide microarray analysis. A list of 402 differentially expressed genes was produced based on a comparison of these two groups. Seven additional benign follicular lesions were then added to the analysis. A hierarchical clustering analysis was performed on all 23 samples, utilizing the gene list generated from the test set, to examine the groups for potential differences and the ability of the gene list to distinguish tumor types. RESULTS: Cluster analysis of all 23 samples produced two distinct groups, one containing the adenomas and one containing the hyperplastic lesions. The analysis was able to identify follicular adenomas with a sensitivity of 84.6% and a specificity of 100%. CONCLUSIONS: These data indicate that benign thyroid lesions can be separated into distinct groups through molecular profiling. Analysis of the gene list may help further the understanding of thyroid tumorigenesis. Expression profiling may ultimately allow us to distinguish potentially malignant from benign follicular nodules.

Biomarkers↗
PubMed2003

Gene expression patterns in human embryonic stem cells and human pluripotent germ cell tumors.

Remarkably little is known about the transcriptional profiles of human embryonic stem (ES) cells or the molecular mechanisms that underlie their pluripotency. To identify commonalties among the transcriptional profiles of different human pluripotent cells and to search for clues into the genesis of human germ cell tumors, we compared the expression profiles of human ES cell lines, human germ cell tumor cell lines and tumor samples, somatic cell lines, and testicular tissue samples by using cDNA microarray analysis. Hierarchical cluster analysis of gene expression profiles showed that the five independent human ES cell lines clustered tightly together, reflecting highly similar expression profiles. The gene expression patterns of human ES cell lines showed many similarities with the human embryonal carcinoma cell samples and more distantly with the seminoma samples. We identified 895 genes that were expressed at significantly greater levels in human ES and embryonal carcinoma cell lines than in control samples. These genes are candidates for involvement in the maintenance of a pluripotent, undifferentiated phenotype.

Carcinoma, Embryonal↗
PubMed1990

Patterns of functioning in families with a chronically ill parent: an exploratory study.

Findings from an assessment of the pattern of functioning of families with dependent children in which one parent was chronically ill are presented. The Moos Family Environment Scale scores of 67 chronically ill individuals and their spouses were subjected to cluster analysis procedures. Four clusters of families were identified and described: cohesive, moral-religious oriented, structured conflict, and unstructured conflict. Structured conflict families possessed lower socioeconomic status and perceived greater impact of illness than cohesive families. Cluster analysis proved particularly useful because it allowed consideration of how groups of families vary from each other, as well as how specific dimensions of family functioning may covary with one another within groups.

Adaptation, Psychological↗
PubMed2005

Genetic evaluation of the efficacy of in situ and ex situ conservation of Parashorea chinensis (Dipterocarpaceae) in Southwestern China.

The majority of research in genetic diversity yields recommendations rather than actual conservation achievements. We assessed the efficacy of actual in situ and ex situ efforts to conserve Parashorea chinensis (Dipterocarpaceae) against the background of the geographic pattern of genetic variation of this species. Samples from seven natural populations, including three in a nature reserve, and one ex situ conservation population were studied. Across the natural populations, 47.8% of RAPD loci were polymorphic; only 20.8% on average varied at the population level. Mean population genetic diversity was 0.787 within natural populations and 1.410 for the whole species. Significant genetic differentiation among regions and isolation by distance were present on larger scales (among regions). AMOVA revealed that the majority of the among-population variation occurred among regions rather than among populations within regions. Regression analysis, Mantel test, principal coordinates analysis, and cluster analysis consistently demonstrated increasing genetic isolation with increasing geographic distance. Genetic differentiation within the region was quite low compared to that among regions. Multilocus spatial autocorrelation analysis of these three populations revealed random distribution of genetic variation in two populations, but genetic clustering was detected in the third population. The ex situ conserved population contained a medium level of genetic variation compared with the seven natural populations; it contained 77.1% of the total genetic variation of this species and 91% of the moderate to high frequency RAPD fragments (f > 0.05). Exclusive bands were detected in natural populations, but none were found in the ex situ conserved population. The populations protected in the nature reserve contained most of the genetic variation of the whole species, with 81.4% of the total genetic variation and 95.7% of the fragments with moderate to high frequency (f > 0.05) of this species conserved. The results show that the ex situ conserved population does not contain enough genetic variation to meet the need of release in the future, and that more extensive ex situ sampling in natural populations TY, NP, HK, and MG is needed. The in situ conserved population contains representative genetic variation to maintain long-term survival and evolutionary processes of P. chinensis.

Animals↗