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 1,765 records · Page 98Linked to original sources
PubMed1998

The Swedish SF-36 Health Survey II. Evaluation of clinical validity: results from population studies of elderly and women in Gothenborg.

The validity of the Swedish SF-36 Health Survey was examined, replicating techniques used in the U.S. validation. Principal components analysis was used to test the internal structure of the eight SF-36 scales in relation to hypothesized associations with the two major dimensions of health--physical and mental. Hypothesized relationships between scales and external criteria were also examined by means of clinical group contrasts. Both the principal components analysis and clinical group contrasts largely replicated U.S. findings, which supported the cross-cultural stability of the SF-36 in Sweden. As expected, the Physical Functioning and Mental Health scales were most sensitive to clinical manifestations of medical and mental health, respectively. The General Health scale was associated more with physical than mental health. However, the Social Functioning scale and particularly the Vitality scale were more related to mental health in Sweden than in the corresponding U.S. study. Cultural differences and variation in study samples and selection criteria were suggested as possible explanatory factors for these differences.

Adult↗
PubMed1990

Acoustic dimensions of hearing-impaired speakers' intelligibility: segmental and suprasegmental characteristics.

Regression and principal components analyses were employed to study the relationship between 28 segmental and suprasegmental acoustic parameters of speech production and measures of speech intelligibility for 40 severely to profoundly hearing-impaired persons in an effort to extend the findings of Metz, Samar, Schiavetti, Sitler, and Whitehead (1985). The principal components analysis derived six factors that accounted for 59% of the variance in the original 28 parameters. Consistent with the findings of Metz et al., a subsequent regression analysis using these six factors as predictor variables revealed two factors with strong predictive relationships to speech intelligibility. One factor primarily reflected segmental production processes related to the temporal and spatial differentiation of phonemes, whereas the other primarily reflected suprasegmental production processes associated with contrastive stress. However, the predictive capability of the present factor structure was somewhat reduced relative to the findings of Metz et al. (1985). Data presented indicate that the populations sampled in the two studies may have differed on one or more dimensions of subject characteristics. Considered collectively, the present findings and the findings of Metz et al. support the tractability of employing selected acoustic variables for the estimation of speech intelligibility.

Adult↗
PubMed2003

Psychometric properties of the Blood-borne Virus Transmission Risk Assessment Questionnaire (BBV-TRAQ).

AIMS: To develop a standard measure of blood-borne virus transmission risk behaviour, and examine the underlying psychometric properties. DESIGN: The Blood-borne Virus Transmission Risk Assessment Questionnaire (BBV-TRAQ) was developed over three consecutive phases of the original BBV-TRAQ study in adherence to classical scale development procedures, culminating in the recruitment of a development sample of current injecting drug users via convenience and snowball sampling. SETTING: Needle and syringe programmes (NSPs), medical clinics, alcohol/drug agencies, peer-based and outreach organizations across inner and outer metropolitan Melbourne. PARTICIPANTS: Two hundred and nine current injecting drug users. The mean age was 27 years, 68% were male, 65% unemployed, 36% with prison history and 25% in methadone maintenance. MEASUREMENTS: BBV-TRAQ items cover specific injecting, sexual and skin penetration risk practices. BBV-TRAQ characteristics were assessed via measures of internal and test-retest reliability; collateral validation; and principal components analyses. FINDINGS: The BBV-TRAQ has satisfactory psychometric properties. Internal (a=0.87), test-retest (r=0.84) and inter-observer reliability results were high, suggesting that the instrument provides a reliable measure of BBV risk behaviour and is reliable over time and across interviewers. A principal components analysis with varimax rotation produced a parsimonious factor solution despite modest communality, and indicated that three factors (injecting, sex and skin penetration/hygiene risks) are required to describe BBV risk behaviour. CONCLUSIONS: The BBV-TRAQ is reliable and represents the first risk assessment tool to incorporate sufficient coverage of injecting, sex and other skin penetration risk practices to be considered truly content valid. The questionnaire is indicated for use in addictions research, clinical, peer education and BBV risk behaviour surveillance settings.

Adolescent↗
PubMed2005

Coping strategy use: does it predict adjustment to chronic back pain after controlling for catastrophic thinking and self-efficacy for pain control?

OBJECTIVE: To explore whether coping strategy use predicted levels of adjustment in chronic low back pain after controlling for the influence of catastrophic thinking and self-efficacy for pain control. METHODS: Eighty-four patients with chronic low back pain completed the Coping Strategies Questionnaire, a pain VAS and the Roland Disability Questionnaire. To derive composite measures of coping, the Coping Strategies Questionnaire subscales, excluding the Catastrophizing subscale and 2 single-item scales, were entered into a principal components analysis. The extent to which scores on the coping measures predicted levels of adjustment after controlling for catastrophic thinking (Catastrophizing subscale) and self-efficacy for pain control (2 single-item scales) was explored using sequential multiple regression analysis. RESULTS: Two coping dimensions emerged from the principal components analysis, which were labelled Distraction and Praying or Hoping, and Denial of Pain and Persistence. Scores obtained on these coping measures explained an additional 5% and 13% of the variance in pain intensity and disability, respectively. Interestingly, however, the scores on the coping measures did not predict pain intensity or disability after controlling for the influence of catastrophic thinking and self-efficacy for pain control. CONCLUSION: Coping strategy use might only be related to levels of adjustment via the effect it has on catastrophic thinking and self-efficacy for pain control.

Adaptation, Psychological↗
PubMed1998

Classification of dyspepsia. Identification of independent symptom components in 7270 consecutive, unselected dyspepsia patients from general practice.

BACKGROUND: Several attempts to classify dyspepsia into subgroups have been proposed as a basis for empirical treatment and research. However, subgrouping has proved difficult due to overlap of symptoms between subgroups, and the response to empirical therapy is difficult to predict. We aimed to study whether natural symptom combinations occur in patients seeing general practitioners because of dyspepsia and whether symptom presentation could predict the effect of proton pump inhibitor treatment. METHODS: The symptom presentation of 7270 consecutive, unselected patients with dyspepsia in general practice was studied by using principal-components analysis. The relation to the effect of omeprazole was studied in a subsample (n=471) with predominantly reflux-like or ulcer-like dyspepsia being included in a controlled clinical trial of omeprazole versus placebo. RESULTS: Four principal components (factors), explaining 36% of the total variance, were found. They describe four independent dimensions in the symptoms of dyspepsia that can be interpreted meaningfully as representing A) acid-related disease of the upper gastrointestinal tract, B) irritable bowel disorder, C) dysmotility of the stomach/duodenum, and D) dysmotility of the esophagus. In the subsample the response to proton pump inhibition therapy was associated with high component-A scores, low component-B scores, and low component-C scores. A pocket chart was devised to obtain the component scores easily in new patients. CONCLUSION: The analysis identified four characteristic, biologically meaningful dyspepsia components that express independent dimensions in the symptoms of patients with dyspepsia. The symptom scores corresponding to the four components may improve symptom-based diagnosis and thereby empirical therapy. In particular, the association between component scores and the effect of omeprazole suggests that classifying dyspepsia on the basis of these components may focus empirical omeprazole therapy even more.

Adult↗
PubMed1993

Distribution patterns of polychlorinated biphenyl congeners in harbor seal (Phoca vitulina) tissues: statistical analysis.

Tissue samples from five harbor seals (Phoca vitulina) have been analyzed for coplanar and other polychlorinated biphenyl (CB) congeners, in order to measure variations in levels and patterns of the CBs. Blubber samples contained the highest levels of CBs in all animals; kidney and liver were relatively high-level tissues. CB-153 and CB-138 were the most abundant CB congeners in all samples analyzed. Variations in the patterns of CB congeners in tissues were studied by principal component analyses and multivariate analysis of variance. The CB congener patterns in seals from different geographical regions had distinctly different patterns, whereas the patterns appeared quite similar in tissues within each seal. Based on multivariate analysis of variance, it was, however, possible to detect some systematic variation of the principal components with individual seals and with tissue type within the seals. The assessment of differences in CB congener patterns was possible by comparison to results obtained by repeated analyses of a quality control sample. The calculated dioxin toxic equivalents of the CB congeners followed the levels of the CB congeners, with the highest levels being found in the blubber samples.

Animals↗
PubMed1997

Determination of extent of formaldehyde-induced crosslinking in hard gelatin capsules by near-infrared spectrophotometry.

PURPOSE: To predict the degree of crosslinking from formaldehyde-stressed hard gelatin capsules (HGCs) using near-infrared spectrophotometry (NIR). METHODS: HGCs were exposed to a 150 ppb atmosphere of formaldehyde for 2.25, 4.60, 9.42, 16.0 and 24.0 hours. The capsules were filled with fresh amoxicillin, placed in a 90 degrees conical reflector cone, and scanned in a NIR spectrophotometer. Principal component regression (PCR) was employed to analyze the spectra of the intact capsules. Dissolution profiles were then obtained for each experimental group. RESULTS: The dissolution of amoxicillin from the capsules at pH 1.2 was found to decrease with increasing time of exposure to the formaldehyde atmosphere. A set of principal components (PCs) was formed by a linear combination of the absorbance values at each wavelength scanned. A good correlation was established (r2 = 0.963) when PC values from the NIR spectra of the HGCs were regressed against percentage of amoxicillin dissolved at 45 minutes, at pH 1.2. Water content of the capsules was found to be the largest determinant in the variation between HGC spectra at each exposure time. CONCLUSIONS: NIR spectrophotometry, combined with PCR, was successful at not only predicting dissolution of HGCs exposed to formaldehyde, but also at determining which wavelengths contributed most to spectral variation of these stressed HGCs.

Amoxicillin↗
PubMed1999

A unifying review of linear gaussian models.

Factor analysis, principal component analysis, mixtures of gaussian clusters, vector quantization, Kalman filter models, and hidden Markov models can all be unified as variations of unsupervised learning under a single basic generative model. This is achieved by collecting together disparate observations and derivations made by many previous authors and introducing a new way of linking discrete and continuous state models using a simple nonlinearity. Through the use of other nonlinearities, we show how independent component analysis is also a variation of the same basic generative model. We show that factor analysis and mixtures of gaussians can be implemented in autoencoder neural networks and learned using squared error plus the same regularization term. We introduce a new model for static data, known as sensible principal component analysis, as well as a novel concept of spatially adaptive observation noise. We also review some of the literature involving global and local mixtures of the basic models and provide pseudocode for inference and learning for all the basic models.

Algorithms↗
PubMedDate not supplied

[Grouping of countries according to basic and economic indicators].

"Countries are grouped according to a collection of basic and economic indicators published by UNICEF, in 1990. Two multivariate statistical methods were used: Principal Component Analysis and Cluster Analysis. The study [covers] 36 countries of the Americas, Europe (including the USSR), the Middle East, Asia and the other continents; they were chosen to include countries having complete information (for the 16 variables used) and in the most varied stages of development. The first principal component was interpreted as a measure of the degree of development...with emphasis on the position occupied by Brazil (13th place among the 25 American countries). In general, the most discriminative variables were the mortality rates of infants and children under five, and life expectancy...." (SUMMARY IN ENG)

Americas↗
PubMed2003

[Development of disease burden score concerning bone and joint diseases: comparison between rheumatoid arthritis and osteoarthritis].

OBJECTIVES: To develop disease burden score concerning bone and joint diseases by evaluating the burdens of rheumatoid arthritis (RA) and osteoarthritis (OA) based on two quantitative measures of quality of life (QOL). METHODS: In a questionnaire, the qualified doctors of Japan Rheumatism Foundation were asked to evaluate patients' QOL, including 6 items of physical functions, 7 items of daily living activities and 3 items of social activities, for three severity levels defined by treatment status. The burdens of RA and OA were determined based on two quantitative measures of QOL, that is, 'principal component score' and '0-0.5-1 score'. RESULTS: In the two-way ANOVA of severity level and doctor's specialism, two quantitative measures of QOL showed significant differences by severity level, having approximately the same F-statistics each other. The burden of RA was 1.4-times (for 'principal component score') and 1.6-times (for '0-0.5-1 score') as great as that of OA. The differences in burden between RA and OA were observed especially in daily living activities and social activities. CONCLUSIONS: Our methodology may be applicable to examining differences in burden between bone and joint diseases.

Adult↗
PubMed1986

The correlation between craniofacial and long bone growth: an experimental investigation in normal rabbits.

The present study was undertaken to elucidate the relationships between craniofacial and long-bone growth. Nine male New Zealand white rabbits received spherical tantalum bone markers in the tibial epiphyses and in the nasal, frontal, and parietal bones. The animals were followed from 30 to 143 days of age. Growth changes were calculated with a roentgen stereometric system, and the results statistically evaluated. Except for the final interval when all variables varied at random, high correlations between tibial and frontonasal or coronal sutural growth were demonstrated; and the respective linear regression lines were homogeneously assembled. The relationship between the tibia and the sagittal suture displayed great variations between individual animals as well as between the suture's parts, although growth at the interfrontal suture was clearly correlated to tibial growth upon exclusion of the time factor. The first principal component of the three neurocranial sutures was calculated and seemed accurately correlated to long-bone growth. The present study concluded that growth at the frontonasal and coronal sutures normally seems to parallel general somatic development, while growth at the sagittal suture appears individually displaced in time. Nevertheless, when the principal component of the combination of the coronal suture and the neurocranial section of the sagittal suture was computed, this was highly correlated to body growth.

Age Factors↗
PubMed1989

Computerised tomography of chickens.

1. The use of computerised tomography (CT) to predict body composition of chickens has been evaluated. Prediction equations were constructed by regression analyses with CT-observations as independent variables. The accuracy of prediction was evaluated on separate sets of birds, not included in the regression analyses. 2. Different methods of generating CT-observations were evaluated. The most robust CT-variables for prediction purposes were obtained from a principal component analysis of the distribution of CT-values. The accuracy of prediction depended on the traits and the material analysed. 3. The correlation between observed and predicted values for the amount of abdominal fat or breast cut in grams were in the range of 0.70 and 0.90 where the principal component method was applied. The bias was 1 to 2% of the standard deviation for the trait. 4. The amount of abdominal fat relative to carcase weight was predicted with similar accuracy, whereas the relative amount of breast cut seemed to be more difficult to predict. The increase in accuracy of prediction for amount of abdominal fat was considerable when compared to an equation including only body weight and sex. 5. The results from a small scale experiment, where a wide range of compositional traits were determined by more laborious and precise methods, indicated that the accuracy of prediction may be increased further and that CT-observations may in addition provide important information about the chemical composition of the tissues analysed.

Abdomen↗
PubMedDate not supplied

Chemical fingerprinting of Gardenia jasminoides fruit using direct sample introduction and gas chromatography with mass spectrometry detection.

A rapid, rugged, and inexpensive approach is described to develop chemical fingerprints of volatile and semivolatile fractions in herbal medicine. The method is based on the combination of direct sample introduction and gas chromatography (GC) analysis with mass spectrometry detection. In comparison with routine methods, the proposed approach provides the most informative fingerprint and does not demand time-consuming extraction, pretreatment, and cleanup procedures. The approach was applied to establish the GC fingerprint of gardenia fruit (Gardenia jasminoides Ellis), in which 39 components were identified. With the help of principal components analysis, the obtained fingerprint could reveal the variation in and within different herb samples as affected by season and developmental state (wild or cultivated). The results indicated that the proposed approach could serve as a rapid, simple, and effective technique for the quality control of herbal medicines.

Chemistry Techniques, Analytical↗
PubMed1982

Relationships among ontogenetic, static, and evolutionary allometry.

The relationship between ontogenetic, static, and evolutionary levels of allometry is investigated. Extrapolation from relative size relationships in adults to relative growth in ontogeny depends on the variability of slopes and intercepts of ontogenetic vectors relative to variability in length of the vector. If variability in slopes and intercepts is low relative to variability in length, ontogenetic and static allometries will be similar. The similarity of ontogenetic and static allometries was tested by comparing the first principal component, or size vector, for correlations among 48 cranial traits in a cross-sectional ontogenetic sample of rhesus macaques from Cayo Santiago with a static sample from which all age- and sex-related variation had been removed. The vector correlation between the components is high but significantly less than one while two of three allometric patterns apparent in the ontogenetic component are not discernable in the static component. This indicates that there are important differences in size and shape relationships among adults and within ontogenies. Extrapolation from intra-or interspecific phenotypic allometry to evolutionary allometry is shown to depend on the similarity of genetic and phenotypic allometry patterns. Similarity of patterns was tested by comparing the first principal components of the phenotypic, genetic, and environmental correlation matrices calculated using standard quantitative genetic methods. The patterns of phenotypic, genetic, and environmental allometry are dissimilar; only the environmental allometries show ontogenetic allometric patterns. This indicates that phenotypic allometry may not be an accurate guide to patterns of evolutionary change in size and shape.

Aging↗
PubMed1990

Anti-Hebbian learning in a non-linear neural network.

The Hebbian rule (Hebb 1949), coupled with an appropriate mechanism to limit the growth of synaptic weights, allows a neuron to learn to respond to the first principal component of the distribution of its input signals (Oja 1982). Rubner and Schulten (1990) have recently suggested the use of an "anti-Hebbian" rule in a network with hierarchical lateral connections. When applied to neurons with linear response functions, this model allows additional neurons to learn to respond to additional principal components (Rubner and Tavan 1989). Here we apply the model to neurons with non-linear response functions characterized by a threshold and a transition width. We propose local, unsupervised learning rules for the threshold and the transition width, and illustrate the operation of these rules with some simple examples. A network using these rules sorts the input patterns into classes, which it identifies by a binary code, with the coarser structure coded by the earlier neurons in the hierarchy.

Brain↗
PubMed2000

Multivariate statistical analysis of flat vowel spectra with a view to characterizing dysphonic voices.

The aim of this article is to show how dysphonic voices can be characterized by means of a multivariate statistical analysis of flat vowel spectra. The spectral contour was obtained by means of a wavelet transform of the logarithmic magnitude spectrum, which was subsequently flattened to remove interspeaker variability related to the excitation and vocal tract filter functions. The results of the statistical analysis of flat spectra were the following. Firstly, principal components analysis produced markers that separated noisy from clean spectra. Secondly, the heuristic search for harmonic peaks or interharmonic dips could be omitted. Thirdly, conventional spectral markers of noise appeared as special instances of the markers that were derived statistically. Fourthly, the levels of visually assigned hoarseness and the first two principal components were significantly correlated. The assignment of different levels of (visual) hoarseness to different vowel timbres could be explained by the variability associated with the spectral contour.

Algorithms↗
PubMed2005

Phenotypic variation in functional disorders of defecation.

BACKGROUND & AIMS: Although obstructed defecation is generally attributed to pelvic floor dyssynergia, clinical observations suggest a wider spectrum of anorectal disturbances. Our aim was to characterize phenotypic variability in constipated patients by anorectal assessments. METHODS: Anal pressures, rectal balloon expulsion, rectal sensation, and pelvic floor structure (by endoanal magnetic resonance imaging) and motion (by dynamic magnetic resonance imaging) were assessed in 52 constipated women and 41 age-matched asymptomatic women. Phenotypes were characterized in patients by principal components analysis of these measurements. RESULTS: Among patients, 16 had a hypertensive anal sphincter, 41 had an abnormal rectal balloon expulsion test, and 20 had abnormal rectal sensation. Forty-nine patients (94%) had abnormal pelvic floor motion during evacuation and/or squeeze. After correcting for age and body mass index, 3 principal components explained 71% of variance between patients. These factors were weighted most strongly by perineal descent during evacuation (factor 1), anorectal location at rest (factor 2), and anal resting pressure (factor 3). Factors 1 and 3 discriminated between controls and patients. Compared with patients with normal (n = 23) or reduced (n = 18) perineal descent, patients with increased (n = 11) descent were more likely (P < or = .01) to be obese, have an anal resting pressure >90 mm Hg, and have a normal rectal balloon expulsion test result. CONCLUSIONS: These observations demonstrate that functional defecation disorders comprise a heterogeneous entity that can be subcharacterized by perineal descent during defecation, perineal location at rest, and anal resting pressure. Further studies are needed to ascertain if the phenotypes reflect differences in the natural history of these disorders.

Adult↗
PubMed2004

Development of a new measure to assess trunk impairment after stroke (trunk impairment scale): its psychometric properties.

OBJECTIVE: The purpose of this study was to investigate reliability, validity, internal structure, and responsiveness of our newly developed Trunk Impairment Scale (TIS) for patients with stroke. DESIGN: A total of 73 patients with stroke participated in this prospective study. Interrater reliability (weighted kappa statistics), content validity (principal component analysis), concurrent validity (Spearman's rank correlation with the Trunk Control Test), predictive validity (prediction of discharge FIM scores), and responsiveness (standardized response mean values) were examined. Internal consistency and item difficulties were analyzed with Rasch analysis. RESULTS: The weighted kappa of each TIS item ranged from 0.66 to 1.0. Principal component analysis revealed that the TIS measured a domain similar to the Stroke Impairment Assessment Set trunk items but different from the Stroke Impairment Assessment Set motor and visuospatial items. The TIS correlated with the Trunk Control Test (r = 0.91). To predict discharge FIM motor scores, addition of the TIS as one of the predictors to age, time from onset, and admission FIM score increased the adjusted R2 from 0.66 to 0.75. With Rasch analysis, the misfit was acceptable, except for the abdominal muscle strength item. The difficulty patterns were similar at admission and discharge, except for the abdominal muscle strength item. The responsiveness of the TIS was satisfactory and comparable with that of the Trunk Control Test (standardized response mean values, 0.94 and 1.06). CONCLUSIONS: Our newly developed TIS is reliable, valid, and responsive for use in stroke outcome research.

Adult↗