Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Principal component”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,495 records · Page 83Linked to original sources
PubMed1997

Development of outcome indicators for monitoring the quality of public mental health care.

OBJECTIVE: The study attempted to develop a brief and integrated set of reliable and valid outcome measures that could be used by both consumers and providers to assess the quality of public mental health care. METHODS: A model of outcomes in four domains-consumer satisfaction, functioning, quality of life, and clinical status-was developed from the literature and from the priorities expressed by members of an advisory group of stakeholders. Based largely on extant measures, a consumer survey and a case manager survey were then created to assess these domains. A total of 236 adult consumers of mental health services from six community mental health centers in Washington State were surveyed. The four-item case manager survey to rate consumers' clinical status was completed by 163 of the participants' case managers. Scores and ratings on the survey were analyzed using correlational analysis and principal components analysis to determine whether the data provided empirical support for the four-domain model. RESULTS: Principal components analysis demonstrated support for the four-domain model. Internal consistency of the outcome indicators was adequate, and their concurrent validity was partly supported. CONCLUSIONS: The described outcome measures provide a practical, empirically supported structure for monitoring and improving public mental health services.

Activities of Daily Living↗
PubMed1996

[The evaluation of therapeutic effect on partial splenic embolization (PSE) for liver cirrhosis patients].

Partial splenic embolization (PSE) was performed on fifty cases with liver cirrhosis underwent no therapy. We evaluated changes of platelet count, ICGR15, GPT and Child-Pugh score which were significantly recovered by PSE. About liver cirrhosis before PSE, K.ICG, GPT, Alb, platelet count and splenic volume were selected as total characteristic factors by principal component analysis. We showed predicting formulas after PSE by multiple regression analysis between five factors selected by principal component analysis and platelet count, HPT, PT, Alb, ICGR15, K.ICG, GOT, GPT and Child-Pugh score after PSE. In conclusion, it is suggested that PSE is useful for recovering of platelet count and liver function. We made it possible to estimate therapeutic effect by predicting formulas before PSE.

Aged↗
PubMed1996

Spectroscopic diagnosis of cervical intraepithelial neoplasia (CIN) in vivo using laser-induced fluorescence spectra at multiple excitation wavelengths.

BACKGROUND AND OBJECTIVE: The diagnostic contribution of cervical tissue fluorescence spectra acquired in vivo at 380 and 460 nm excitation were analyzed using a general multivariate statistical algorithm. MATERIALS AND METHODS: The primary steps of the algorithm are to: (1) preprocess data to reduce interpatient and intrapatient variation of tissue spectra from the same diagnostic category, without a priori information, (2) dimensionally reduce the pre-processed spectral data using Principal Component Analysis, and (3) develop a probability based classification scheme based on logistic discrimination using the diagnostically useful principal components. The algorithm was tested on cervical tissue spectra acquired from 165 sites at 380 nm excitation and from 147 sites at 460 nm excitation. A retrospective and prospective estimate of the algorithm's performance was determined. RESULTS: At 460 nm excitation, (1) SILs can be differentiated from normal squamous tissues with an average sensitivity and specificity of 91% +/- 1.3 and 75.5% +/- 1, respectively; furthermore, (2) high grade SILs can be differentiated from low grade SILs with an average sensitivity and specificity of 80% +/- 4 and 76% +/- 5, respectively. In addition, using tissue spectra at 380 nm excitation, SILs can be differentiated from normal columnar epithelia and inflammation with an average sensitivity and specificity of 77% +/- 1 and 72% +/- 9, respectively. CONCLUSIONS: Fluorescence spectra at multiple excitation wavelengths are essential for the detection and differential diagnosis of SILs at colposcopy.

Algorithms↗
PubMed1998

Pattern recognition analysis of 1H NMR spectra from perchloric acid extracts of human brain tumor biopsies.

Pattern recognition techniques (factor analysis and neural networks) were used to investigate and classify human brain tumors based on the 1H NMR spectra of chemically extracted biopsies (n = 118). After removing information from lactate (because of variable ischemia times), unsupervised learning suggested that the spectra separated naturally into two groups: meningiomas and other tumors. Principal component analysis reduced the dimensionality of the data. A back-propagation neural network using the first 30 principal components gave 85% correct classification of meningiomas and nonmeningiomas. Simplification by vector rotation gave vectors that could be assigned to various metabolites, making it possible to use or to reject their information for neural network classification. Using scores calculated from the four rotated vectors due to creatine and glutamine gave the best classification into meningiomas and nonmeningiomas (89% correct). Classification of gliomas (n = 47) gave 62% correct within one grade. Only inositol showed a significant correlation with glioma grade.

Biomarkers, Tumor↗
PubMed1997

The role of habitat shift in the evolution of lizard morphology: evidence from tropical Tropidurus.

We compared morphology of two geographically close populations of the tropical lizard Tropidurus hispidus to test the hypothesis that habitat structure influences the evolution of morphology and ecology at the population level. T. hispidus isolated on a rock outcrop surrounded by tropical forest use rock crevices for refuge and appear dorsoventrally compressed compared with those in open savanna. A principal components analysis revealed that the populations were differentially distributed along an axis representing primarily three components of shape: body width, body height, and hind-leg length. Morphological divergence was supported by a principal components analysis of size-free morphological variables. Mitochondrial DNA sequences of ATPase 6 indicate that these populations are closely related relative to other T. hispidus, the rock outcrop morphology and ecology are derived within T. hispidus, and morphological and ecological divergence has occurred more rapidly than genetic divergence. This suggests that natural selection can rapidly adjust morphology and ecology in response to a recent history of exposure to habitats differing in structure, a result heretofore implied from comparative studies among lizard species.

Animals↗
PubMed2004

Development of a comprehensive dietary antioxidant index and application to lung cancer risk in a cohort of male smokers.

In many observational studies, a higher intake of individual antioxidants is inversely associated with lung cancer risk. Data from in vitro and animal experiments suggest that there are biochemical interactions among antioxidant nutrients; therefore, consideration of multiple antioxidants simultaneously may be important in terms of risk estimation. The authors constructed a dietary antioxidant index and evaluated its ability to predict lung cancer risk within the Alpha-Tocopherol, Beta-Carotene Cancer Prevention Study cohort. At baseline (1985-1988), 27,111 Finnish male smokers aged 50-69 years completed a dietary questionnaire that assessed usual frequency of consumption and portion sizes for the previous 12 months. A total of 1,787 incident cases of lung cancer were identified during a follow-up period of up to 14.4 years (1985-1999). Principal components analyses were individually applied to the carotenoid, flavonoid, and vitamin E nutrient groups, and summation of retained principal component scores, plus selenium and vitamin C, yielded the composite antioxidant index. In multivariate proportional hazards models, the relative risks for lung cancer according to increasing quintiles of the antioxidant index were 1.00 (referent), 1.00 (95% confidence interval (CI): 0.87, 1.14), 0.91 (95% CI: 0.79, 1.05), 0.79 (95% CI: 0.68, 0.92), and 0.84 (95% CI: 0.72, 0.98) (p for trend = 0.002). These findings support the hypothesis that a combination of dietary antioxidants reduces lung cancer risk in male smokers.

Aged↗
PubMed2004

Mapping cortical thickness and gray matter concentration in first episode schizophrenia.

We mapped regional changes in cortical thickness and intensity-based cortical gray matter concentration in first episode schizophrenia. High-resolution magnetic resonance images were obtained from 72 (51 male, 21 female) first episode patients and 78 (37 male, 41 female) healthy subjects similar in age. Cortical pattern matching methods allowed comparisons of cortical thickness and gray matter concentration at thousands of homologous cortical locations between subjects in three dimensions. Principal components analyses reduced measures obtained across the cortex to identify global differences in cortical thickness/gray matter concentration. First principal component factor scores showed significant effects of diagnosis, sex and age for both cortical measures. Diagnosis and age effects remained significant after brain size correction. Cortical thickness and gray matter concentration values were highly correlated. Statistical maps showed significant regional gray matter thinning in frontal, temporal and parietal heteromodal association cortices bilaterally in first episode patients. Regional reductions in cortical gray matter concentration were similar but pronounced in the superior temporal lobe. Regional reductions in cortical thickness and gray matter concentration are present at disease onset in brain regions linked with functional disturbances in schizophrenia. Cortical thickness and gray matter concentration mapping produce similar results, although the concentration metric may be influenced by diagnostic differences in extra-cortical cerebrospinal fluid and surface curvature/complexity.

Adult↗
PubMed2006

A metabonomic study of transgenic maize (Zea mays) seeds revealed variations in osmolytes and branched amino acids.

The aim of the research was to investigate metabolic variations associated with genetic modifications in the grains of Zea mays using metabonomic techniques. With this in mind, the non-targeted characteristic of the technique is useful to identify metabolites peculiar to the genetic modification and initially undefined. The results obtained showed that the genetic modification, introducing Cry1Ab gene expression, induces metabolic variations involving the primary nitrogen pathway. Concerning the methodological aspects, the experimental protocol used has been applied in this field for the first time. It consists of a combination of partial least square-discriminant analysis and principal component analysis. The most important metabolites for discrimination were selected and the metabolic correlations linking them are identified. Principal component analysis on selected signals confirms metabolic variations, highlighting important details about the changes induced on the metabolic network by the presence of a Bt transgene in the maize genome.

Amino Acids, Branched-Chain↗
PubMed1982

Evidence for an autosomal recessive gene regulating the persistence of the insulin response to glucose in man.

The significance of genetic factors for insulin release after glucose infusion was studied in 155 nuclear families of which 59 were control families and 96 had been ascertained through a parent with onset of diabetes after 30 years of age. Fasting insulin and glucose as well as three principal components of the insulin and glucose curves were submitted to path analysis and complex segregation analysis. The three principal components were considered to reflect the magnitude, the degree of response and the persistence of the curves. The genetic heritability of the insulin variables varied between 0.47-0.93 and that of the glucose variables between 0.20-0.54. There were considerable intergenerational differences in the genetic heritability for the persistence of the glucose curve and for the degree of response and persistence of the insulin curve. The cultural heritability was found to be of minor importance, while the non-transmitted sibling environment was large. There was significant evidence for a major locus for the persistence of the insulin curve. The best fit was for a completely recessive autosomal gene with the gene frequency 0.21. The phenotype distribution of this variable showed significant kurtosis which could simulate a major locus. However, the significant evidence for such a locus remained after an analysis using partial quantitation. The diabetics were significantly different from the non-diabetics for all the variables studied, but a complete discrimination between the diabetics and non-diabetics could not be obtained. There was no significant difference between the children of the diabetics and non-diabetics for any of the variables studied.

Adult↗
PubMed2003

[Quality of life and well-being of elderly people: an exploratory study in the Portuguese population].

OBJECTIVES: To characterize elderly people's perception of quality of life and well-being. METHODS: A sample of 1,665 elderly aged 75 years or more living in 13 districts in Portugal were studied. Of them, 311 subjects were excluded because they were not able to convey their opinions. The EASYcare (Elderly Assessment System) was used to collect data from 1,354 (81.3%) of 1,665 subjects. Statistical analysis was based on principal components analysis and cluster analysis. RESULTS: EASYcare's showed to have good psychometric proprieties (Cronbach a =0.92). The principal component analysis identified 4 factors: mobility, communication competencies, well-being and daily living activities. Cluster analysis showed 4 groups of elderly people: autonomous (62.8%), almost autonomous (8.5%), almost dependent (4.3%) and dependent (3.2%). CONCLUSIONS: Quality of life for most of the elderly is quite positive, and only a small group presents problems related to severe cognitive impairment or some degree of dependence.

Activities of Daily Living↗
PubMedDate not supplied

[Study of psychometric properties of two new questionnaires assessing beliefs in hypochondriasis in a non-clinical population].

Most instruments focussing on hypochondriasis symptoms do not have for goal to assess beliefs specifically. Instead, these instruments are used to measure specific behaviors. To assess underlying beliefs with these kinds of instruments, you have to extract false beliefs by deduction. In cognitive therapy, it is important to target erroneous beliefs in order to change them. On the other hand, existing instruments are not really suitable to target erroneous health beliefs. Even if some questionnaires are built to assess beliefs directly, it seems that they only measure the conviction of having an illness and do not assess the general health beliefs present in excessive health worriers. However, many researchers argue that this other kind of beliefs are the ones responsible in maintaining hypochondriasis symptoms. Presently, researchers assume that erroneous beliefs can maintain worries about illness among people with hypochondriasis symptoms like false beliefs about worry maintain worries in people with General Anxiety Disorder (GAD). Even if the importance of false beliefs in the maintenance of pathological worries is now recognized, most instruments on hypochondriasis symptoms do not have for goal to assess erroneous beliefs concerning worry about health. For instance, although the questionnaire Why do people worry? (WW) shows good psychometric properties and measures beliefs related to general worries, this questionnaire is not specific enough to correctly evaluate beliefs associated to health worry. A new questionnaire has to emerge in order to assess false beliefs associated to worry about health. This manuscript presents the development and the validation of a new questionnaire: the General Health Beliefs Questionnaire (GHBQ) that assesses general health beliefs, and also presents the development and the validation of a new questionnaire assessing beliefs associated to worry about health: the Why do people Worry about Health? (WW-H) . In this study, the GHBQ's and the WW-H's psychometric qualities and the factorial structure were assessed. More precisely, this study examined the factorial structure, the temporal stability, the convergent, divergent and criteria validities of the GHBQ and the WW-H. Four hundred and twenty nine French-speaking university students (non-clinical participants) completed a battery of questionnaires at the beginning of a class. The questionnaires were: The General Health Beliefs Questionnaire (GHBQ), the Why do people Worry about Health (WW-H), the Illness Worry Scale (IWS), the Beck Depression Inventory-short form (BDI-short form) and the Beck Anxiety Inventory (BAI). A second administration took place three weeks later with the same sample to test the temporal stability of the GHBQ and the WW-H. The principal component analysis with orthogonal rotation (varimax) supports a five components solution for the GHBQ: 1) magical thinking, 2) health, 3) consequences, 4) responsibility, and 5) vulnerability. The principal component analysis with oblique rotation (direct oblimin) (d=0) found a two components solution for the WW-H: 1) utility and 2) magical thinking associated to worries about health. The internal consistency of the GHBQ and the WW-H is excellent (a=.80 and a=.90, respectively). A correlation of 0.49 was found between the GHBQ and the WW-H. The correlation between the GHBQ and the IWS who evaluates the tendency to worry (r=.50) and between the WW-H and the IWS (r=.49) showed that the convergent validity of these questionnaires is adequate. On a three weeks interval, the GHBQ (r=.70) and the WW-H (r=.71) showed a satisfying temporal stability. The means of the high worriers (80 superior percentile at the IWS) (M=38.8, ET=8.93) and the means of the moderate worriers (between the 40 and the 60 percentile at the IWS) (M=32.8, ET=8.00) on the GHBQ have been compared. A significant difference has been found between the two groups [F(1,181)=23,129, p<0,001]. Also, the means of the high worriers (M=27.3, ET=8.59) and the means of the moderate worriers (M=23.8, ET=8.56) on the WW-H haveave been compared. An ANOVA has found a significant difference between these two groups [F(1,180)=7,396, p=0,007]. These results show that general health beliefs and false beliefs associated to worry about health are more often present in high worriers than in moderate worriers. The GHBQ and the WW-H allow psychologists, physicians and psychiatrists to do a quicker and more exhaustive evaluation of general health beliefs and false beliefs associated to worry about health, in less costs. These questionnaires will improve the chances of success of the hypochondriasis' treatment by helping clinicians to detect and correct false beliefs more easily.

Adolescent↗
PubMed1999

Familial analysis of event related potentials.

This report summarizes our analysis of the auditory and visual event related evoked potentials. These data were collected as a component of the Collaborative Study on the Genetics of Alcoholism and distributed as a part of the data available for the Genetic Analysis Workshop 11. For this analysis, we collapsed the data collected from eight leads using principal components methods. Using four collapsed variables derived from the principal components, we used regression analysis to adjust for environmental and demographic variables. We then fit the best fitting regression model and calculated the residuals. Using the residuals, we performed segregation analysis using S.A.G.E. Finally, we applied Markov chain Monte Carlo reverse jump methods to identify areas with potential quantitative trait loci. Our findings indicate that there may be an underlying genetic component to the potentials.

Alcoholism↗
PubMed1997

[Medical and pharmaceutical applications of principle component analysis].

Medical and pharmaceutical research leads to a collection of data that are presented in the form of tables. Examples from several fields in the medical and pharmaceutical sciences show that principal component analysis allows to visualise the information, present in the tables, and thereby to more easily interpret this information. The method is explained algebraically and geometrically. The possibility to apply principal components to develop models, and thereby relate certain measurable quantities, is shortly indicated.

Data Interpretation, Statistical↗
PubMed2006

Metabolomic analysis of methyl jasmonate treated Brassica rapa leaves by 2-dimensional NMR spectroscopy.

The metabolomic analysis of Brassica rapa leaves treated with methyl jasmonate was performed using 2-dimensional J-resolved NMR spectroscopy combined with multivariate data analysis. The principal component analysis of the J-resolved NMR spectra showed discrimination between control and methyl jasmonate treated plants by principal components 1 and 2. While the level of glucose, sucrose and amino acids showed a decrease after methyl jasmonate treatment, hydroxycinnamates and glucosinolate were highly increased. Methyl jasmonate treatment resulted in a long-term accumulation of indole glucosinolate and indole-3-acetic acid, lasting up to 14 days after treatment. Malate conjugated hydroxycinnamates also exhibited an increase until 14 days after methyl jasmonate treatment, these compounds might play an important role in plant defence responses mediated by methyl jasmonate.

Acetates↗
PubMed2006

Phenotypic characterization of Class III patients.

OBJECTIVE: The objective of this study is to characterize the convergences of dentofacial form of skeletal Class III malocclusion in individuals to test the fundamental hypothesis that there are distinct subtypes of Class III malocclusion. MATERIALS AND METHODS: A detailed phenotypic characterization was performed on a retrospective cohort of 309 subjects using cluster and principal component analyses on 67 cephalometric variables. RESULTS: The results indicated that there are five clusters representing distinct subphenotypes. The principal component analysis suggested that the groupings of variables reflect anteroposterior and vertical dimensions rather than specific craniofacial structures. This may ultimately suggest that different genes are involved in controlling dimension vs structures. CONCLUSIONS: Our phenotypic dissection of Class III malocclusion established distinct subtypes in a large sample of patients and will ultimately provide the basis for future familial studies to identify a causative gene.

Adult↗
PubMed1986

Measurement in speed skating tournaments.

Twenty principal components analyses were performed on the results of 10 European and 10 World male speed skating championships. The first principal component obtained was defined as 'the ability to skate well at all tournament distances'. Therefore the rank order of the participants' skating ability could be estimated in an alternative way to allow validation of the scoring method currently in force. This validity coefficient turned out to be so high (r = 0.967) that it does not seem necessary to adopt a more sophisticated method, despite a few demonstrable shortcomings of the one in use. However, there remains a considerable proportion of variance (10-34%) that can not be explained by systematic aspects of skating ability.

Humans↗
PubMedDate not supplied

Analysing normal and partial glossectomee tongues using ultrasound.

The present study aimed at identifying underlying parameters that govern the shape of the tongue. A functional topography of the tongue surface was developed based on three-dimensional ultrasound scans of sustained speech sounds in ten normal subjects. A principal component analysis extracted three components that explained 89.2% of the variance at 33 measurement points on the tongue surface. The results from the principal component analysis supported a physiologically plausible three-component model of tongue movement. This model breaks tongue movement down into a protrusion and retraction component that is represented by the measurement points on the posterior tongue, a tongue tip control component that is represented by the measurement points on the tongue blade, and a dorsal height and position control component that is represented by the measurement points on the tongue dorsum. A case series of three patients with partial glossectomies illustrates how this measurement system can be applied to surgically altered tongues to allow a detailed analysis of post-surgical function.

Adult↗
PubMed2006

Modulated Hebb-Oja learning rule--a method for principal subspace analysis.

This paper presents analysis of the recently proposed modulated Hebb-Oja (MHO) method that performs linear mapping to a lower-dimensional subspace. Principal component subspace is the method that will be analyzed. Comparing to some other well-known methods for yielding principal component subspace (e.g., Oja's Subspace Learning Algorithm), the proposed method has one feature that could be seen as desirable from the biological point of view--synaptic efficacy learning rule does not need the explicit information about the value of the other efficacies to make individual efficacy modification. Also, the simplicity of the "neural circuits" that perform global computations and a fact that their number does not depend on the number of input and output neurons, could be seen as good features of the proposed method.

Algorithms↗