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 37 records · Page 2Linked to original sources
PubMed2005

Serum 1H-nuclear magnetic spectroscopy followed by principal component analysis and hierarchical cluster analysis to demonstrate effects of statins on hyperlipidemic patients.

Use of statins for prevention of coronary heart disease is based on the decrease of serum cholesterol and LDL cholesterol. To better investigate the changes in lipid profile after statin treatment, we propose here to use an analysis of serum by proton nuclear magnetic resonance (NMR) spectroscopy associated with a multivariate analysis of the main spectral components. Sera were obtained from 60 male patients treated for 6 weeks with simvastatin (30 patients) or atorvastatin (30 patients) for who LDL cholesterol decreased by over 45% in all selected patients. Proton nuclear magnetic resonance spectra were obtained and the region of methyl resonance from lipids was separated into six consecutive lines attributed to lipids which were analyzed by principal component analysis (PCA) and clustering by hierarchical cluster analysis (HCA) based on Euclidian distance coupled with the Ward's minimum variance method. PCA and HCA gave a map discriminating the 120 samples into five clusters, three clusters containing samples obtained at baseline and two others containing samples obtained after treatment. Both statins produced a decrease in lower-density lipoprotein components and an increase in higher density lipoprotein components. Patients with a coronary heart disease history could be discriminated after treatment by the increase in the component containing the highest proportion of HDL. Proton NMR spectroscopy of sera coupled with a PCA and an HCA was able to detect variations in the metabolism of lipids resulting from statin treatments.

Aged↗
PubMedDate not supplied

Study of prognosis in acute myeloid leukemias (AML) by cluster analysis.

BACKGROUND: Cluster analysis is particularly effective in detecting homogeneous subgroups among large series of observations. We applied this relatively uncommon approach to the study of prognosis in 137 patients affected by acute myeloid leukemia (AML). METHODS AND RESULTS: Employing simple presentation parameters (age, WBC, splenomegaly, hepatomegaly) we used cluster analysis to define 3 groups with different overall survival (p = 0.0019). This classification was obtained following a rescaling of the variables and principal component analysis. Validation was performed through random definition of a control group. With the same variables, univariate analysis demonstrated age was the only prognostic factor, while Cox's model was not significant. CONCLUSIONS: In our series cluster analysis allowed a better definition of prognosis than Cox's analysis. Since the 3 groups are well identifiable, each patient can be rapidly classified and his allocation confirmed by discriminant functions. For cluster 2 we were able to project a possible myelodysplastic evolution, while cluster 3 was more frequently associated with a monocytic blastic component. We think that cluster analysis deserves consideration as an alternative statistical approach in the analysis of large series of data; its usefulness lies in its power to define homogeneous prognostic or biologic subgroups and to elaborate further hypotheses for new studies.

Acute Disease↗
PubMed1989

Testing for course patterns in Crohn's disease using clustering analysis.

Using clustering analysis, we sought to identify groups of patients on the basis of the disease course among a population of 177 patients with Crohn's disease and followed for 3 years or more, starting from the first frank exacerbation of the disease. The first 36 values of a monthly clinical score represented the active variables of the clustering analysis. This method yielded 2 course groups, A and B, of 95 and 82 patients respectively. The unfavorable course in group A was characterized by the persistence of the clinically active disease at 3 years, whereas group B individuals achieved complete clinical remission within 2 years of onset on the average. Among the initially known clinical data which could explain the course, only the incidence of an occlusive syndrome was higher in group B, which showed a more favorable course. Although we applied clustering analysis to a patient sample over a period of only 3 years, our results do suggest the existence or 2 primary course groups within the population of patients with Crohn's disease. It would appear that the disease course cannot be predicted from the clinical parameters present at the time of onset, but rather becomes apparent during the course of the first 2 years.

Adult↗
PubMed2005

fMRI temporal clustering analysis in patients with frequent interictal epileptiform discharges: comparison with EEG-driven analysis.

Temporal clustering analysis (TCA) is an exploratory data-driven technique that has been proposed for the analysis of resting fMRI to localise epileptiform activity without need for simultaneous EEG. Conventionally, fMRI of epileptic activity has been limited to those patients with subtle clinical events or frequent interictal epileptiform EEG discharges, requiring simultaneous EEG recording, from which a linear model is derived to make valid statistical inferences from the fMRI data. We sought to evaluate TCA by comparing the results with those of EEG correlated fMRI in eight selected cases. Cases were selected with clear epileptogenic localisation or lateralisation on the basis of concordant EEG and structural MRI findings, in addition to concordant activations seen on EEG-derived fMRI analyses. In three, areas of activation were seen with TCA but none corresponding to the electro-clinical localisation or activations obtained with EEG driven analysis. Temporal clusters were closely coincident with times of maximal head motion. We feel this is a serious confound to this approach and recommend that interpretation of TCA that does not address motion and physiological noise be treated with caution. New techniques to localise epileptogenic activity with fMRI alone require validation with an appropriate independent measure. In the investigation of interictal epileptiform activity, this is best done with simultaneous EEG recording.

Cluster Analysis↗
PubMed1996

The symptom structure of panic disorder: a trial using factor and cluster analysis.

Using cluster analysis of 207 patients with panic disorder (PD), we investigated the relationships between several panic symptoms at the time of panic attacks, which included anticipatory anxiety, agoraphobia, and 13 clinical symptoms based on the Diagnostic and Statistics Manual-III-Revised. Cluster analysis revealed three panic symptom clusters: cluster A (dyspnea, choking, sweating, nausea, flushes/chills); cluster B (dizziness, palpitations, trembling or shaking, depersonalization, agoraphobia, and anticipatory anxiety); and cluster C (fear of dying, fear of going crazy, paresthesias, and chest pain or discomfort). Generally, cluster A was comprised exclusively of physiological symptoms, among which respiratory symptoms were prominent, cluster B included both panic and non-panic symptoms such as agoraphobia and anticipatory anxiety, and cluster C was comprised chiefly of fear symptoms.

Adult↗
PubMed1984

Hospitals and the provision of care to the aged: a cluster analysis.

As the American population ages, the hospital industry will undergo substantial restructuring to meet the increased demand for geriatric and long-term care services. Understanding this important trend, however, has been inhibited by limited research and the vast range of services that currently exists. This investigation develops empirically a classification schema of hospitals that reflects the mix of geriatric services they provide. The study also identifies the organizational and environmental characteristics of hospitals providing these geriatric service categories. Factor analysis, clustering, and analysis of variance were performed on a sample of 416 hospitals. Seven distinct groupings of hospitals that differed systematically on geriatric service mix and other contextual factors were identified.

Aged↗
PubMed1994

The identification of pathological subtypes of Alzheimer's disease using cluster analysis.

A cluster analysis was performed on 78 cases of Alzheimer's disease (AD) to identify possible pathological subtypes of the disease. Data on 47 neuropathological variables, including features of the gross brain and the density and distribution of senile plaques (SP) and neurofibrillary tangles (NFT) were used to describe each case. Cluster analysis is a multivariate statistical method which combines together in groups, AD cases with the most similar neuropathological characteristics. The majority of cases (83%) were clustered into five such groups. The analysis suggested that an initial division of the 78 cases could be made into two major groups: (1) a large group (68%) in which the distribution of SP and NFT was restricted to a relatively small number of brain regions, and (2) a smaller group (15%) in which the lesions were more widely disseminated throughout the neocortex. Each of these groups could be subdivided on the degree of capillary amyloid angiopathy (CAA) present. In addition, those cases with a restricted development of SP/NFT and CAA could be divided further into an early and a late onset form. Familial AD cases did not cluster as a separate group but were either distributed between four of the five groups or were cases with unique combinations of pathological features not closely related to any of the groups. It was concluded that multivariate statistical methods may be of value in the classification of AD into subtypes.

Aged↗
PubMed1990

Identifying subclasses of patients with rheumatoid arthritis through cluster analysis.

Nonhierarchical cluster analysis was used to classify 92 patients with rheumatoid arthritis drawn from a community rheumatology practice into 5 groups on the basis of biochemical measures and disease indices. The major differentiating variables were the number of active joints, number of damaged joints, overall disease activity, extraarticular complications, and history of joint surgery. Although the 5 subclasses were equivalent on measures of psychological functioning, they differed systematically on such health outcome measures as mobility, physical activity, and dexterity. Relationships between the taxonomy produced through cluster analysis and conventional classifications are discussed, and directions for further investigation are noted.

Adult↗
PubMedDate not supplied

Classification of environmental estrogens by physicochemical properties using principal component analysis and hierarchical cluster analysis.

A structurally diverse assortment of 60 environmental estrogens was divided into two main clusters ("A", "B") and a pair of subclusters ("C1", "C2") by applying principal component analysis to selected 1D and 2D molecular descriptors and subjecting the PCs to hierarchical cluster analysis. Although clustering was predicated solely on physicochemical properties, the dependence on particular physicochemical parameters of xenoestrogen binding affinities (pK(i)) to murine uterine cytosolic estrogen receptor (ER) proved greater for compounds within (sub)clusters than for compounds between (sub)clusters. Quantitative structure-binding affinity relationships derived using molecular descriptors and PCs suggested differences in the driving forces for xenoestrogen-ER binding for different (sub)clusters. The modeling power for xenoestrogen-ER binding affinities of a combination of TLSER and WHIM 3D indices was much greater than that of combinations of 1D and 2D molecular descriptors or the PCs derived therefrom. The clusterings obtained using PCs also proved applicable to the 3D-QSARs.

Chemical Phenomena↗
PubMed2005

Image analysis of irregularity of cluster shape in cytological diagnosis of breast tumors: cluster analysis with 2D-fractal dimension.

To establish diagnostic criteria using comparison of cell cluster shapes, between benign and malignant tumors, breast tumors demonstrating weak cellular atypia in low grade invasive ductal carcinoma (IDC) were compared. Fine-needle aspiration (FNA) specimens of breast tumors were obtained from 37 patients. Among these, 16 were histologically diagnosed as IDC low-grade and the other 21 as benign fibroadenoma (FA). For evaluation, we examined 740 clusters from these 37 FNA specimens. Nine image morphometric parameters were studied, including the cluster area, circumference, maximal length, maximal breadth, ratio of length to breadth, cluster roundness, cluster size, and the edge and distribution image fractal dimensions for cluster analysis. We evaluated the irregularity in cell cluster shape using fractal dimension analysis, and determined the correlation to cluster size. The irregularity in the IDC cluster shape was higher than that in the FA cluster shape. However, six cases (28.5%) of 21 FA clusters showed high fractal dimensions similar to those for IDC. The clusters were classified by cluster analysis into three types: IDC clusters, FA with irregular cluster shape, and FA with no irregular clusters. The average cell cluster area of the FA with irregular shape was found to be about three times larger than that of IDC clusters. When the differential diagnosis between IDC and FA is difficult, it is important to focus on irregularities in the shape and on overall size of the cell clusters. For accurate diagnosis, the cell cluster shape is as important as the individual cellular atypia.

Adenofibroma↗
PubMed1992

Detection of secondary structure elements in proteins by hydrophobic cluster analysis.

Hydrophobic cluster analysis (HCA) is a protein sequence comparison method based on alpha-helical representations of the sequences where the size, shape and orientation of the clusters of hydrophobic residues are primarily compared. The effectiveness of HCA has been suggested to originate from its potential ability to focus on the residues forming the hydrophobic core of globular proteins. We have addressed the robustness of the bidimensional representation used for HCA in its ability to detect the regular secondary structure elements of proteins. Various parameters have been studied such as those governing cluster size and limits, the hydrophobic residues constituting the clusters as well as the potential shift of the cluster positions with respect to the position of the regular secondary structure elements. The following results have been found to support the alpha-helical bidimensional representation used in HCA: (i) there is a positive correlation (clearly above background noise) between the hydrophobic clusters and the regular secondary structure elements in proteins; (ii) the hydrophobic clusters are centred on the regular secondary structure elements; (iii) the pitch of the helical representation which gives the best correspondence is that of an alpha-helix. The correspondence between hydrophobic clusters and regular secondary structure elements suggests a way to implement variable gap penalties during the automatic alignment of protein sequences.

Amino Acid Sequence↗
PubMed2002

Improved detection of time windows of brain responses in fMRI using modified temporal clustering analysis.

Temporal clustering analysis (TCA) has been proposed recently as a method to detect time windows of brain responses in functional MRI (fMRI) studies when the timing and location of the activation are completely unknown. Modifications to the TCA technique are introduced in this report to further improve the sensitivity in detecting brain activation. The modified TCA is based on the integrated signal intensity of a temporal cluster at each time point, while the original TCA is based only on the size of a temporal cluster at each time point. A temporal cluster at each time point is defined, in both TCA methods, as a group of pixels reaching their maximum (or minimum) values at the same time. Both computer simulation and in vivo fMRI experiments have been performed. Compared with the original TCA, the modified TCA shows a significant improvement in the sensitivity to detect activation peaks for determining time windows of brain responses.

Brain↗
PubMed2002

Cluster analysis of Wisconsin Breast Cancer dataset using self-organizing maps.

This work deals with multidimensional data analysis, precisely cluster analysis applied to a very well known dataset, the Wisconsin Breast Cancer dataset. After the introduction of the topics of the paper the cluster analysis concept is shortly explained and different methods of cluster analysis are compared. Further, the Kohonen model of self-organizing maps is briefly described together with an example and with explanations of how the cluster analysis can be performed using the maps. After describing the data set and the methodology used for the analysis we present the findings using textual as well as visual descriptions and conclude that the approach is a useful complement for assessing multidimensional data and that this dataset has been overused for automated decision benchmarking purposes, without a thorough analysis of the data it contains.

Breast Neoplasms↗
PubMed1987

Guidelines for maintenance treatment of childhood asthma: development of a score card system by multivariate cluster analysis.

Multivariate cluster analysis of data on 128 asthmatic children resulted in the identification of 8 major discriminating variables. Stepwise divisions by this computer programme resulted in the formation of 6 grades of severity. There was significant correlation between higher grades of severity and early onset of the disease (P less than 0.02). There was also significant correlation between higher grades of severity and greater use of interval medications (P less than 0.002). However, 27.3% were receiving inadequate interval medications in respect of their grade of severity. Assignation of a 5-point scale to each of the 8 major discriminating variables resulted in the generation of computer-designated scores commensurate with each grade of severity. This was coupled to current recommendations for stepwise maintenance medications appropriate for each grade. This Score Card system for maintenance management of childhood asthma may prove useful in busy clinical settings.

Adolescent↗
PubMed2002

Identification of the most relevant factors that affect and reflect the quality of granules by application of canonical and cluster analysis.

The production of granules by wet granulation in a fluidized bed was assessed according to two statistical techniques to identify the most relevant factors that affect the quality of the granules. The statistics used include Canonical Analysis and Cluster Analysis. The factors studied, according to a center of gravity design, included the solubility of a model drug, different grades of polyvinylpirrolidone (PVP), the polarity and the rate of administration of the granulation solution, the atomizing air pressure, the inlet air pressure and rate. The properties of the granules considered were the yield, the assay of the drug, the size, the densities (true, bulk and tapped), the friability, the flowability and one compressibility index. Statistical analysis of the factors evaluated has shown that the solubility of the materials and the pressure of the atomizing air in the nozzle were the most critical parameters affecting the quality of the granules. Less relevant were the granulation solution and the grade of PVP. The properties of the granules that best described their quality were the yield and the densities. From the Cluster Analysis it was possible to divide the granules in two clusters, where cluster 1 was identifiable by the yield, the assay, the flowability, and the friability, whereas cluster 2 was better identified by the size of the granules.

Chemistry, Pharmaceutical↗
PubMed2001

Three-dimensional cluster analysis identifies interfaces and functional residue clusters in proteins.

Three-dimensional cluster analysis offers a method for the prediction of functional residue clusters in proteins. This method requires a representative structure and a multiple sequence alignment as input data. Individual residues are represented in terms of regional alignments that reflect both their structural environment and their evolutionary variation, as defined by the alignment of homologous sequences. From the overall (global) and the residue-specific (regional) alignments, we calculate the global and regional similarity matrices, containing scores for all pairwise sequence comparisons in the respective alignments. Comparing the matrices yields two scores for each residue. The regional conservation score (C(R)(x)) defines the conservation of each residue x and its neighbors in 3D space relative to the protein as a whole. The similarity deviation score (S(x)) detects residue clusters with sequence similarities that deviate from the similarities suggested by the full-length sequences. We evaluated 3D cluster analysis on a set of 35 families of proteins with available cocrystal structures, showing small ligand interfaces, nucleic acid interfaces and two types of protein-protein interfaces (transient and stable). We present two examples in detail: fructose-1,6-bisphosphate aldolase and the mitogen-activated protein kinase ERK2. We found that the regional conservation score (C(R)(x)) identifies functional residue clusters better than a scoring scheme that does not take 3D information into account. C(R)(x) is particularly useful for the prediction of poorly conserved, transient protein-protein interfaces. Many of the proteins studied contained residue clusters with elevated similarity deviation scores. These residue clusters correlate with specificity-conferring regions: 3D cluster analysis therefore represents an easily applied method for the prediction of functionally relevant spatial clusters of residues in proteins.

Adenosine Triphosphate↗
PubMed2004

Improving binding potential analysis in [11C]raclopride PET studies using cluster analysis.

To calculate binding potentials (BP) in [11C]raclopride brain PET studies a reference tissue model is widely used. The aim of the present study was to improve the determination of time activity curves (TAC) of reference tissue regions using cluster analysis. In four patients with Huntington disease TACs of a cerebellar reference region were calculated either from manually placed circular ROIs within the cerebellum or by cluster analysis. BP estimates derived from cluster analysis are independent from inter- and intraobserver variations and show an improved reproducibility combined with a low variability compared to manually placed cerebellar ROIs. This is of high value in longitudinal studies.

Adult↗