SEARCH · PubMed Health

Results for “Principal Component 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 199 records · Page 11Linked to original sources

PubMed2005

Use of principal component analysis and the GE-biplot for the graphical exploration of gene expression data.

This note is in response to Wouters et al. (2003, Biometrics 59, 1131-1139) who compared three methods for exploring gene expression data. Contrary to their summary that principal component analysis is not very informative, we show that it is possible to determine principal component analyses that are useful for exploratory analysis of microarray data. We also present another biplot representation, the GE-biplot (Gene Expression biplot), that is a useful method for exploring gene expression data with the major advantage of being able to aid interpretation of both the samples and the genes relative to each other.

Algorithms↗

PubMed2002

Permutation-validated principal components analysis of microarray data.

BACKGROUND: In microarray data analysis, the comparison of gene-expression profiles with respect to different conditions and the selection of biologically interesting genes are crucial tasks. Multivariate statistical methods have been applied to analyze these large datasets. Less work has been published concerning the assessment of the reliability of gene-selection procedures. Here we describe a method to assess reliability in multivariate microarray data analysis using permutation-validated principal components analysis (PCA). The approach is designed for microarray data with a group structure. RESULTS: We used PCA to detect the major sources of variance underlying the hybridization conditions followed by gene selection based on PCA-derived and permutation-based test statistics. We validated our method by applying it to well characterized yeast cell-cycle data and to two datasets from our laboratory. We could describe the major sources of variance, select informative genes and visualize the relationship of genes and arrays. We observed differences in the level of the explained variance and the interpretability of the selected genes. CONCLUSIONS: Combining data visualization and permutation-based gene selection, permutation-validated PCA enables one to illustrate gene-expression variance between several conditions and to select genes by taking into account the relationship of between-group to within-group variance of genes. The method can be used to extract the leading sources of variance from microarray data, to visualize relationships between genes and hybridizations and to select informative genes in a statistically reliable manner. This selection accounts for the level of reproducibility of replicates or group structure as well as gene-specific scatter. Visualization of the data can support a straightforward biological interpretation.

Animals↗

PubMed1997

Mapping of ventricular repolarization potentials in patients with arrhythmogenic right ventricular dysplasia: principal component analysis of the ST-T waves.

BACKGROUND: Nonuniform recovery of ventricular excitability has been demonstrated to facilitate the reentry circuits leading to the development of ventricular tachyarrhythmias. This can also occur in arrhythmogenic right ventricular dysplasia (ARVD). In fact, in patients with ARVD, abnormalities of ventricular repolarization are often observed on 12-lead ECGs, but their predictive value for the occurrence of malignant arrhythmias is yet to be established. Because body-surface potential mapping has been proved to be useful for the detection of heterogeneities in ventricular recovery even though they are not revealed by conventional 12-lead ECGs, we attempted to analyze repolarization potentials on the entire chest surface to find abnormalities that can be predictive of ventricular arrhythmias. METHODS AND RESULTS: Body-surface potential maps were recorded from 62 anterior and posterior thoracic leads in 22 patients affected by ARVD, 9 with episodes of sustained ventricular tachycardias (VT) and 13 without. Thirty-five healthy subjects were also studied as control subjects. The 62 chest ECGs were simultaneously recorded, digitally converted at a rate of 2000 Hz, and stored on a hard disk of a body-surface mapping computer system. In each subject, the QRST integral map was obtained by calculating at each lead point the algebraic sum of all instantaneous potentials, from the QRS onset to the T-wave end, multiplied by the sampling interval. In most ARVD patients, we observed a larger-than-normal area of negative values on the right anterior thorax. This abnormal pattern could be explained by a delayed repolarization of the right ventricle. Nevertheless, it was not related to the occurrence of VT in our patient population. To detect minor heterogeneities of ventricular repolarization, the principal component analysis was applied to the 62 ST-T waves recorded in each subject. We assumed that a low value of the first or of the first three components (components 1, 2, and 3) indicates a greater-than-normal variety of the ST-T waves, a likely expression of a more complex recovery process. The mean values of the first three components were not significantly different in ARVD patients and control subjects. Nevertheless, considering the two subsets of patients with and without VT, the values of component 1, components 1 + 2, and component 1 + 2 + 3 were significantly lower in the group of ARVD patients with VT. Values of component 1 < 69% (equal to 1 SD below the mean value for control subjects) were found in 6 of 9 VT patients and in 1 patient without VT (sensitivity, 67%; specificity, 92%). A low value of component 1 was the only variable significantly associated with the occurrence of VT. CONCLUSIONS: Principal component analysis provides a better quantitative assessment of the complexity of repolarization than other ECG measurements. When applied to ARVD patients, principal component analysis of the ST-T waves recorded from the entire chest surface revealed abnormalities not detected by conventional ECG that can be considered indexes of arrhythmia vulnerability.

Adolescent↗

PubMed2004

Adaptive multiscale principal component analysis for on-line monitoring of a sequencing batch reactor.

In recent years, multiscale monitoring approaches, which combine principal component analysis (PCA) and multi-resolution analysis (MRA), have received considerable attention. These approaches are potentially very efficient for detecting and analyzing diverse ranges of faults and disturbances in chemical and biochemical processes. In this work, multiscale PCA is proposed for fault detection and diagnosis of batch processes. Using MRA, measurement data are decomposed into approximation and details at different scales. Adaptive multiway PCA (MPCA) models are developed to update the covariance structure at each scale to deal with changing process conditions. Process monitoring by a unifying adaptive multiscale MPCA involves combining only those scales where significant disturbances are detected. This multiscale approach facilitates diagnosis of the detected fault as it hints to the time-scale under which the fault affects the process. The proposed adaptive multiscale method is successfully applied to a pilot-scale sequencing batch reactor for biological wastewater treatment.

Algorithms↗

PubMed2001

One-carbon metabolism and other biochemical correlates of cognitive impairment as visualized by principal component analysis.

In the present report, 101 ambulatory elderly patients complaining about cognitive disturbances were investigated using the Mini-Mental State Examination (MMSE). Laboratory investigations, brain imaging, and electroencephalography were performed. Twelve patients were diagnosed with subjective memory complaints (SMC), 32 with mild cognitive impairment (MCI), 43 with dementia of the Alzheimer type (DAT), and 14 with vascular dementia (VAD). Thirty-three percent of the SMC group, 31% of the MCI group, 45% of the DAT group, and 62% of the VAD group had increased serum homocysteine (s-HCY). Principal component analysis of 19 variables showed 3 significant principal components by cross-validation. The cognitive impairment in the patients (MMSE) was explained to 50%. According to the principal component analysis, the population followed two different routes to cognitive impairment: one correlated with disturbance of one-carbon metabolism (cerebrospinal fluid vitamin B12, plasma B12, plasma folate, and s-HCY) and the other correlated with more classic dementia, as marked by cerebrospinal fluid tau, vascular risk factors, atrophy on brain imaging, possession of the apolipoprotein E4 allele, and age. There was poor discrimination between DAT and VAD.

Aged↗

PubMed2000

Principal component analysis of large layer density in Compton scattering measurements

A multivariate approach based on Principal Component Analysis (PCA) was used to analyze the energy distribution of n Monte Carlo simulated Compton scattered photon spectra describing the electron density of large layers. Three to five layers with different density distribution were used to test the algorithm; each layer was obtained by collecting 25 Compton spectra coming from sensitive volumes (SVs) where the complementary conditions of high and low density were realized (respectively full and void SV). The density variation inside a single layer is described by a two principal components (PCs) linear model that depicts the electron density of each SV: the layer density distribution appears to be correctly described even in the presence of very low signal-to-noise Compton spectra. Density profiles for layers at different depths were comparatively analyzed in order to show that, at least within one mean-free-path distance, it is possible to describe the layer density distribution by the PCA without any correction for the beam attenuation.

Journal Article↗

PubMed2006

Principal components analysis of obsessive-compulsive disorder symptoms in children and adolescents.

BACKGROUND: Obsessive-compulsive disorder (OCD) has a broadly diverse clinical expression that may reflect etiologic heterogeneity. Several adult studies have identified consistent symptom dimensions of OCD. The purpose of this study was to conduct an exploratory principal components analysis of obsessive-compulsive (OC) symptoms in children and adolescents with OCD to identify improved phenotypes for future studies. METHODS: This study examined lifetime occurrence of OC symptoms included in the 13 symptom categories of the Yale-Brown Obsessive Compulsive Scale (Y-BOCS) and the Children's Yale-Brown Obsessive-Compulsive Scale (CY-BOCS). Principal components analysis with promax rotation was performed on 231 children and adolescents with OCD and compared with results of similar adult studies. RESULTS: A four-factor solution emerged explaining 59.8% of symptom variance characterized by 1) symmetry/ordering/repeating/checking; 2) contamination/cleaning/aggressive/somatic; 3) hoarding; and 4) sexual/religious symptoms. All factors included core symptoms that have been consistently observed in adult studies of OCD. CONCLUSIONS: In children and adolescents, OCD is a multidimensional disorder. Symptom dimensions are predominantly congruent with those described in similar studies of adults with OCD, suggesting fairly consistent covariation of OCD symptoms through the developmental course. Future work is required to understand changes in specific symptom dimensions observed across the life span.

Adolescent↗

PubMed2004

[Application of PCA (Principal Components Analysis) for the estimation of smoking effect on the occurrence of trace elements in women's gallstones].

The PCA (Principal Components Analysis) was used to estimation of the role of smoking in the changes of elements contents in gallstones. The concentration of given elements were determined by ICP-AES method. It was stated that smoking regardless of sex, influence on the occurrence of elements in hydroxyapatites of gallstones, in particular it concerns changes of As, Pb, Zn, Se, Ti contents. PCA method let to describe the role of selected elements in entire chemical composition of gallstones coming from smoking women.

Arsenic↗

PubMed1993

[Internal validation of a measurement scale: relation between principal component analysis, Cronbach's alpha coefficient and intra-class correlation coefficient].

The objective is to establish a simple relationship between two frequently used validation techniques which have been developed in the literature along the same lines: Principal Component Analysis and Cronbach's alpha. We have shown that under certain conditions, it is possible to estimate the reliability by using the results of a Principal Component Analysis only. Moreover, we report the relation between Cronbach's alpha and intraclass correlation coefficient, which are both used to estimate the reliability of continuous measures.

Data Interpretation, Statistical↗

PubMed2006

Clustering of cardiovascular risk factors associated with the insulin resistance syndrome: assessment by principal component analysis in young hyperandrogenic women.

OBJECTIVE: Hyperinsulinemia is often associated with several metabolic abnormalities and increased blood pressure, which are risk factors for cardiovascular disease. It has been hypothesized that insulin resistance may underlie all these features. However, recent data suggest that some links between insulin resistance and these alterations may be indirect. The aim of our study was to further investigate this issue in a sample of young hyperandrogenic women, who often show insulin resistance and other metabolic abnormalities typical of the insulin resistance syndrome. RESEARCH DESIGN AND METHODS: We tested the hypothesis of a single factor underlying these features by principal component analysis, which should recognize one component if a single mechanism explains this association. The analysis was carried out in a sample of 255 young nondiabetic hyperandrogenic women. Variables selected for this analysis included the basic features of the insulin resistance syndrome and some endocrine parameters related to hyperandrogenism. RESULTS: Principal component analysis identified four separate factors, explaining 64.5% of the total variance in the data: the first included fasting and postchallenge insulin levels, BMI, triglycerides, HDL cholesterol, and uric acid; the second, BMI, blood pressure, and serum free testosterone; the third, fasting plasma glucose, postchallenge glucose and insulin levels, serum triglycerides, and free testosterone; and the fourth, postchallenge plasma insulin, serum free testosterone, and gonadotropin-releasing hormone agonist-stimulated 17-hydroxyprogesterone. CONCLUSIONS: These results support the hypothesis of multiple determinants in the clustering of abnormalities in the so-called insulin resistance syndrome.

Adult↗

PubMed2001

Principal component analysis of mass spectra of peptides generated from the tryptic digestion of protein mixtures.

Principal component analysis (PCA) has been used to analyse mass spectral peptide profiles obtained from the enzymatic digestion of standard protein mixtures. Scores and loadings plots clearly revealed peptide fragments that differentiated one protein mixture from another. Peptide map search results identified with a high degree of certainty any additional proteins in these mixtures. As a proof-of-concept this methodology was applied to hepatic protein mixtures obtained from rats treated with two hepatotoxic compounds: methapyriline and SB-219994. Liver proteins were extracted, pre-separated by one-dimensional polyacrylamide gel electrophoresis, subjected to tryptic digestion and analysed by mass spectrometry. Two up-regulated proteins, glutathione S-transferase with methapyrilene and peroxisomal bifunctional enzyme with SB-219994, were identified in this manner.

Amino Acid Sequence↗

PubMed1999

A new approach for clinical biological assay comparison and standardization: application of principal component analysis to a multicenter study of twenty-one carcinoembryonic antigen immunoassay kits.

BACKGROUND: Principal component analysis (PCA) is a powerful mathematical method able to analyze data sets containing a large number of variables. To our knowledge, this method is applied here for the first time in the field of medical laboratory analysis. METHODS: PCA was used to evaluate the results of a blind comparative study of 21 carcinoembryonic antigen (CEA) reagent kits used to determine CEA concentration in a panel of sera from 80 patients. RESULTS: The mathematical technique first eliminated the variations attributable to the use of different calibrators. The PCA representation then gave a global view of the dispersion of the kits and allowed the identification of a main homogeneous group and of some discrepant kits. CONCLUSIONS: PCA applied to the in vitro diagnostic reagent field could contribute to the standardization process and improve the quality of medical laboratory analyses. A standardization method using a panel of patient sera is proposed.

Biomarkers, Tumor↗

PubMed1990

Intergroup and intrasubject principal component analysis of event-related potentials.

The purpose of this paper is to show that the familiar principal component analysis (PCA) of event-related potentials is identical to an easily formulated least squares method. This correspondence permits interpretation of several criticisms of PCA and clearer presentation of its strengths and shortcomings. Because data analysis based on PCA compares amplitudes of empirically derived components, it is necessary that the shape of the components be similar under the experimental conditions. We present and illustrate a statistical method for comparison of principal components across groups and between conditions within subjects.

Acoustic Stimulation↗

PubMed2006

Metabolomic differentiation of deer antlers of various origins by 1H NMR spectrometry and principal components analysis.

The metabolomic analysis of various types of deer antler was performed by 1H NMR spectrometry and principal components analysis (PCA). The PCA of the 1H NMR spectra of the aqueous fractions allowed a clear discrimination between antler samples according to their origins by the first three principal components (PC1, PC2, and PC3), which cumulatively accounted for 93.5% of the variation in all variables. In particular, the score plots by the combination of PC1 and PC3 allowed an excellent separation of the antler samples. In addition, the major peaks in 1H NMR spectra contributing to the discrimination were assigned to lactate, alanine, acetic acid, choline, glycine, valine, tyrosine, and phenylalanine. This metabolomic-analysis-based method allows various types of deer antler to be efficiently differentiated without any pre-purification steps.

Animals↗

PubMed2006

Using supervised principal components analysis to assess multiple pollutant effects.

BACKGROUND: Many investigations of the adverse health effects of multiple air pollutants analyze the time series involved by simultaneously entering the multiple pollutants into a Poisson log-linear model. This method can yield unstable parameter estimates when the pollutants involved suffer high intercorrelation; therefore, traditional approaches to dealing with multicollinearity, such as principal component analysis (PCA), have been promoted in this context. OBJECTIVES: A characteristic of PCA is that its construction does not consider the relationship between the covariates and the adverse health outcomes. A refined version of PCA, supervised principal components analysis (SPCA), is proposed that specifically addresses this issue. METHODS: Models controlling for longterm trends and weather effects were used in conjunction with each SPCA and PCA to estimate the association between multiple air pollutants and mortality for U.S. cities. The methods were compared further via a simulation study. RESULTS: Simulation studies demonstrated that SPCA, unlike PCA, was successful in identifying the correct subset of multiple pollutants associated with mortality. Because of this property, SPCA and PCA returned different estimates for the relationship between air pollution and mortality. CONCLUSIONS: Although a number of methods for assessing the effects of multiple pollutants have been proposed, such methods can falter in the presence of high correlation among pollutants. Both PCA and SPCA address this issue. By allowing the exclusion of pollutants that are not associated with the adverse health outcomes from the mixture of pollutants selected, SPCA offers a critical improvement over PCA.

Air Pollutants↗

PubMed2007

Assessing local influence in principal component analysis with application to haematology study data.

In many medical and health studies, high-dimensional data are often encountered. Principal component analysis (PCA) is a commonly used technique to reduce such data to a few components that includes most of the information provided by the original data. However, PCA is known to be very sensitive to some abnormal observations. Therefore, it is essential to assess such sensitivity in PCA. In this paper, the assessments of local influence based on generalized influence function are developed under the case-weights and additive perturbation schemes, along with a discussion of the perturbation scheme and the generalized influence function approach. When perturbing different variables of the data, it is noted that the directions of the largest joint local influence for the eigenvalues are all the same. Moreover, these directions are completely determined by the score values of the observations, to which an approximate cut-off point is given. The proposed methods are applied to analyse a set of haematology study data for illustration. Results add new insights in finding influential observations in the studied data set.

Health Status↗

PubMed2000

Symptom dimensions in recent-onset schizophrenia and mania: a principal components analysis of the 24-item Brief Psychiatric Rating Scale.

Previous four- and five-factor solutions of the 18-item Brief Psychiatric Rating Scale (BPRS) suggested the possibility of an affective dimension in psychosis. A principal components analysis was used to analyze psychiatric symptom data rated on an expanded 24-item version of the BPRS. BPRS data were collected during a period of acute psychotic and affective illness with 114 young adult, recent-onset schizophrenia and schizoaffective patients and 27 bipolar manic patients. Principal components analyses of the 18-item and 24-item BPRS indicated a four-factor solution was the most interpretable. Principal components analysis of the 24-item BPRS produced a clear mania factor characterized by high loadings from items added to the 18-item BPRS, which included elevated mood, motor hyperactivity, and distractibility. This factor solution suggests that the 24-item BPRS allows for an expanded assessment of affective symptoms relating to a manic dimension. Potentially important symptoms that were added to the traditional 18-item version, namely suicidality, bizarre behavior, and self-neglect, also make clear contributions to other factors.

Adult↗

PubMed2005

Chemometric treatment of vanillin fingerprint chromatograms. Effect of different signal alignments on principal component analysis plots.

This study describes the chemometric treatment of vanillin fingerprint chromatograms to distinguish vanillin from different sources. Prior to principal component analysis, which is used to discriminate vanillin from different origins, the fingerprints are aligned. Three alignment algorithms are tested, correlation optimized warping (COW), target peak alignment (TPA) and semi-parametric time warping (STW). The performance of the three algorithms is evaluated and the effect of the different alignments on the PCA score plots is investigated. The alignment obtained with STW differs somewhat from that with COW and TPA. However, equivalent score plots were obtained regarding the different vanillin groups.

Algorithms↗