SEARCH · PubMed Health

Results for “collinearity 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 55 records · Page 3Linked to original sources

PubMed2004

Identification of criteria for the prioritisation of patients for elective general surgery.

OBJECTIVE: A single visual analogue scale is used in New Zealand to prioritise patients for elective general surgery. Although it reflects clinical judgement, it has been criticised for its lack of transparency. We wished to elicit generic criteria used by surgeons for prioritisation of patients for elective general surgery in order to improve the transparency of the visual analogue scale. METHODS: Semi-structured interviews were undertaken with 15 general surgeons. Using the repertory grid method, surgeons were asked to explain their rationale for distinguishing between patients they considered a high, medium or low priority for treatment. Interviews were audiotaped, transcribed and analysed for themes. The accuracy of the thematic analysis was checked using a five-point Likert scale to assess surgeons' agreement with the identified themes. Further testing to check for face, content and construct validity was undertaken with a purposive sample of six surgeons prioritising patient vignettes. RESULTS: Eight major themes were deduced: diagnosis; treatment; patient characteristics; symptomatology and sequelae to date; future complications; quality of life; psychological/emotional impact; and socio-political/logistic factors. The utilisation of these themes by surgeons was confirmed. Tests of collinearity indicated good content validity. Factor analysis confirmed the hypothesis of one underlying construct, namely priority. CONCLUSION: Seven of the themes became the basis for a new clinical priority assessment criteria tool using visual analogue scales to determine priority of patients for elective general surgery. Further testing of reliability and validity is needed.

Attitude of Health Personnel↗

PubMed1992

Multivariate population-based analysis of the association of county trauma centers with per capita county trauma death rates.

UNLABELLED: The purpose of this study was to utilize a large population-based data base to determine the association of trauma centers with per capita county trauma death rates. METHODS: Per capita county trauma death rate, the dependent variable in the model, was obtained from a well-validated state Medical Examiner's data base. Over 200 county demographic, prehospital, and hospital trauma care resource variables were obtained from a variety of sources for multivariate modeling. Bivariate analysis identified candidate variables for multivariate modeling, excluding highly correlated independent variables to avoid problems of collinearity. Multivariate linear regression, logistic regression, and stepwise discriminant analysis were used to determine the relative association of the candidate variables with per capita county trauma death rates. RESULTS: Bivariate analysis identified multiple factors associated with per capita county trauma death rates. These included, among others: county rurality, percentage of unemployment, percentage nonwhite, 911 access, and ALS certified EMS. Per capita trauma death rates were significantly lower in counties with trauma centers compared with counties without trauma centers (4.0 +/- 0.5 and 5.0 +/- 1.1 deaths per 10,000 population, p = 0.0001, respectively). Multivariate analysis demonstrated that the presence of a trauma center in the county and ALS were the best medical system factors predicting decreased per capita county trauma death rates. CONCLUSIONS: This study is unique in utilizing a regional population-based data base of all trauma deaths in a large state to analyze the association of trauma centers and trauma death rates. Multivariate modeling controlling for other county variables demonstrated that the presence of a trauma center and Advanced Life Support training were the best predictors of per capita county trauma death rates. These findings are consistent with the hypothesis that trauma centers decrease trauma death rates.

Adult↗

PubMed2001

The reliability of multiple regression and an alternative method for extracting task-specific exposure estimates from time-weighted average data.

The reliability of multiple regression analysis as a method for determining task-specific exposures from multi-task time-weighted average data was evaluated in comparison with the alternative P-screen method. The performances of the two methods were tested using simulated sample data that were calculated as averages over six tasks, where task-specific concentrations drawn randomly from lognormal distributions were weighted by randomly generated task time-weights. Data sets consisted of 20 or 100 simulated samples. The simulated data sets conformed to requirements inherent in the P-screen method that at least one task be absent from each sample and each task be absent from at least one sample. In thousands of Monte Carlo trials under various conditions, the two methods were found to perform equally well when dichotomous task measures (occurrence/ nonoccurrence) were used. Combining the two methods did not improve reliability appreciably, suggesting that the methods are effectively equivalent when dichotomous task measures are used. When task durations were used as the regressors or time-weights, multiple regression was found to be more reliable than P-screen. It is well recognized that incidental or fundamental collinearities between regressors may undermine multiple regression analyses. The P-screen-related restrictions on the task structure of data sets reduces the potential for problems arising from such collinearities. However, the use of multivariate analysis of multiple-task samples will always be an imperfect substitute for single-task sampling.

Air Pollution, Indoor↗

PubMed1999

Hemorrhage after an acute ischemic stroke.MAST-I Collaborative Group.

BACKGROUND AND PURPOSE: Hemorrhagic transformation is frequently seen on CT scans obtained in the subacute phase of ischemic stroke. Its prognostic value is controversial. METHODS: We analyzed 554 patients with acute ischemic stroke enrolled in the Multicenter Acute Stroke Trial-Italy (MAST-I) study in whom a second CT scan was performed on day 5. Presence of 1) intraparenchymal hemorrhages (hematoma or hemorrhagic infarction), 2) extraparenchymal bleeding (intraventricular or subarachnoid) and 3) cerebral edema (shift of midline structure, sulcal effacement or ventricular compression) alone or in association were evaluated. Death or disability at 6 months were considered as "unfavorable outcome." RESULTS: Patients who developed intraparenchymal hemorrhages, extraparenchymal bleeding, or cerebral edema had unfavorable outcome (83%, 100%, and 80%, respectively), but multivariate analysis demonstrated that only extraparenchymal bleeding (collinearity) and cerebral edema (OR=6.8; 95% CI, 4.5 to 10.4) were significant independent prognostic findings. Unfavorable outcome correlated with size of intraparenchymal hemorrhage (chi2 for trend=30.5, P<0.0001). Nevertheless, when a large hematoma was present the negative effect was mostly due to concomitant extraparenchymal bleeding (chi2=51.6, P<0.0001), and when hemorrhagic infarction was detected the negative effect was mostly explained by the association with cerebral edema (chi2=36.6, P<0.0001). CONCLUSIONS: Extraparenchymal bleeding and cerebral edema are the main prognostic CT scan findings in the subacute phase of ischemic stroke. Stroke patients with a high risk for developing these 2 types of brain damage should be identified. Measures to prevent and adequately treat their development should be implemented.

Acute Disease↗

PubMed2005

Assessing the effects of environmental toxicant exposure in developmental epidemiological studies: issues for risk assessment.

Epidemiological studies have been of critical importance to the understanding of the effects of environmental chemical exposure during development on the behavior of infants and children. The ultimate goal of these studies should be to provide information that may be used directly for the protection of public health. The strategies for the assessment endpoints include development of domain-specific tests based on knowledge concerning effects of the chemicals being assessed, or use of standard clinical instruments that sample a range of functions. Discussion of an overall strategy for choice of endpoints would allow more straightforward comparisons across studies. There is increasing recognition of the importance of measuring a number of chemicals relevant to the population under study; however, different investigators make different decisions concerning which and how many chemicals to measure, as well as how to include them in the statistical analysis, particularly when there is a high degree of collinearity. Chemicals that are highly correlated with the "chemical of interest" are sometimes not included in the statistical analysis, resulting in missed opportunity to derive important information from the study. In addition, the shape of the relationship between exposure and effect is usually not explored in epidemiological studies, even though such information is critical for risk assessment. Opportunity for discussion among investigators, statisticians, and risk assessors potentially would result in human developmental toxicity studies being maximally useful for public health decisions.

Child↗

PubMed1997

Relationship between body condition scores and milk yield in a large dairy herd of high yielding Holstein cows.

This study investigated the relationship between body condition and milk yield of dairy cows. Holstein cows (n = 779) on a commercial dairy farm were scored for body condition weekly beginning at dry-off and continuing until 120 d of lactation. Multiple linear regression and principal component analysis were used to characterize relationships. Mean body condition scores were 2.77 and 2.66 at dry-off and parturition, respectively. Principal component analysis was used to reduce the collinearity among independent variables, to calculate new parameter estimates, and to rank the relationship of each variable with milk yield. Results indicated that change in body condition during the dry period was ranked first, followed by lactation number, and then body condition score at dry-off for multiparous cows. A one-point increase in body condition score between dry-off and parturition was associated with 545.5 kg more milk in the first 120 d of lactation. Each additional point of body condition at dry-off was associated with 300 kg less milk at 120 d of lactation. Results suggested that cows that gained condition during the dry period yielded more milk in the first 120 d of lactation and had an accelerated rate of increase in milk yield. The results of this study indicate that body condition score is an important tool for monitoring dairy herds.

Adipose Tissue↗

PubMed2002

Correlation between serum lipid profiles and the ratio and count of the CD16+ monocyte subset in peripheral blood of apparently healthy adults.

BACKGROUND AND PURPOSE: Deposited vascular oxidized low-density lipoproteins (LDLs) are important triggers of the transformation of circulatory monocytes into macrophages. CD16+ monocytes have been reported to be the precursors of tissue macrophages. In this study, we sought to determine the relationship between serum LDL-cholesterol and the percentage and count of the CD16+ monocyte subset in the peripheral blood of healthy adults. METHODS: We studied the correlations between serum lipid profiles and both peripheral CD16+ and CD36+ monocyte subset ratios and counts in apparently healthy adults (50 men and 50 women). Monocyte surface antigens CD16 and CD36 on CD14+ monocytes were detected using fluorescent triple staining and flow-cytometry. Surface staining was performed by incubating 1 x 10(6) blood mononuclear cells with phycocrythrin-conjugated anti-CD14, fluorescein isothiocyanate-conjugated anti-CD36, and respective control isotopes (mouse IgGs). A total of 5,000 cells were counted and the frequency of surface antigens was determined by FACscan. RESULTS: A significant positive link between LDL-cholesterol and the CD16+ subset ratio was found by linear correlation analysis (p < 0.05) but not by multivariate regression analysis. Both linear correlation analysis and ANOVA revealed a significant inverse link between high-density lipoprotein (HDL)-cholesterol and the CD16+ subset ratio (both p < 0.01). By multivariate regression analysis, gender was the main significant determinant for the CD16+ subset ratio. When serum total cholesterol (TC) was excluded from the analysis to avoid the interference from collinearity between serum TC and LDL (r = 0.84), HDL-cholesterol became independently and inversely linked to the CD16+ subset ratio. There were independent inverse links between HDL-cholesterol and the counts of all monocytes, CD16+ monocytes, and CD36+ monocytes. CONCLUSIONS: Our results suggest that circulating HDL-cholesterol may be much more important than LDL-cholesterol in affecting the transformation of circulatory monocytes into macrophages. The inverse link between HDL-cholesterol and the number of macrophage precursors in peripheral blood might contribute partly to the well-known antiatherogenic effect of HDL-cholesterol.

CD36 Antigens↗

PubMed1994

Quantitative nuclear morphometry, Markovian texture descriptors, and DNA content captured on a CAS-200 Image analysis system, combined with PCNA and HER-2/neu immunohistochemistry for prediction of prostate cancer progression.

One hundred and twenty-four localized prostate cancer patients operated on at Johns Hopkins Hospital (JHH) since 1975 were identified. The sample was optimized for evaluation of prostate cancer progression. Based upon accurate clinical histories, these radical prostatectomy patients included 50 progressors and 74 non-progressors using appearance of serum PSA as an indication of recurrence (mean follow-up = 8.6 +/- 1.8 years, range 7-15 years). All patients included in the study had no involvement of their seminal vesicles or lymph nodes at the time of prostatectomy. Average time to progression was 3.6 +/- 2 years, range of 1-8 years. Using paraffin-embedded specimens, several five micron sections were cut and placed on Probe-On slides; one slide was H&E-stained and the other was Feulgen-stained. The H&E and Feulgen-stained slides were screened and "dotted" by pathologists at JHH and CytoDynostics, Inc. A CAS-200 Image analysis system (Cell Image Systems, Elmhurst, IL) equipped with a Cell Measurement Program version 1.2 beta, was used to capture the Feulgen-stained images and to perform the calculations. From the "dotted" areas, 150 cancer cells were selected for measurement of DNA content and 27 nuclear morphometric shape and size factors, including 21 Markovian chromatin texture variables. Additional sections were used for immunochemistry staining with an alkaline phosphatase streptavidin-biotin complex stain to detect and quantitate cancer cells binding monoclonal antibodies directed against proliferating cell nuclear antigen (PCNA) and HER-2/neu antigen. All data were entered into a statistical program (STATA) for further analysis and univariate and multivariate statistical analysis was performed using logistic regression and its stepwise variant. The biomarkers of greatest utility to detect progressors when analyzed univariately included post-operative Gleason score (p = < 0.0001), HER-2/neu antigenicity (p = 0.0147), CAS-200 DNA ploidy (p = 0.008), and twelve Markovian nuclear texture and shape features (p = < 0.0001), whereas PCNA (p = 0.160) failed. The optimal set of nuclear morphometry progression tumor features were selected using backward stepwise logistic regression estimate analysis which drops variables due to collinearity. Although post-operative Gleason score is a strong univariate predictor of progression, DNA ploidy and HER-2/neu contributed significantly to further stratification of higher risk groups within the low Gleason score subpopulation. The best Markovian features combined with post-operative Gleason score generated sensitivity = 90%, specificity = 96%, positive predictive value = 94%, negative predictive value = 93% and the area under the receiver operator curve was 0.975.

Biomarkers, Tumor↗

PubMed1994

Triplex-forming oligonucleotide binding represses transcription of the human c-erbB gene in glioma.

Mixed purine-pyrimidine oligodeoxynucleotides were designed to form collinear DNA triplexes with pyrimidine-rich elements in the EGFR gene promoter. Their effects as mediators of human epidermal growth factor receptor (EGFR) gene transcription and subsequent gene expression were evaluated using human squamous cell carcinoma (A431) and human glioma cell line (U251MG and U87MG). Gel shift analysis indicated that the oligonucleotide forms a collinear triplex within the duplex Sp-1 binding site. An in vitro assay system revealed a correlation between triplex formation and the repression of EGFR transcription. We postulate that guanine residues are not always optimum in apposition to G-C pairs to form triple helices in the target. Site-specific oligodeoxynucleotides binding to a DNA duplex may serve as the basis for an alternative program of gene control in vitro.

Base Sequence↗

PubMed2003

3D-MEDNEs: an alternative "in silico" technique for chemical research in toxicology. 1. prediction of chemically induced agranulocytosis.

A novel approach to molecular negentropy from the point of view of Markov models is introduced. Stochastic negentropies (MEDNEs) are used to develop a linear discriminant analysis. The discriminant analysis produced a set of two discriminant functions, which gave rise to a very good separation of 93.38% of 151 chemicals (training series) into two groups. The total predictability (86.67%, i.e., 52 compounds out of 60) was tested by means of an external validation set. Randić's orthogonalization procedures allowed interpretation of the model while avoiding collinearity descriptors. On the other hand, factor analysis was used to suggest the relation of MEDNEs with other molecular descriptors and properties into a property space. Three principal factors (related to three orthogonal MEDNEs) can be used to explain approximately 90% of the variance of different molecular parameters of halobenzenes including bulk, energetic, dipolar, molecular surface-related, and hydrophobic parameters. Finally, preliminary experimental results coincide with a theoretical prediction when agranulocytosis induction by G-1, a novel microcidal that presents Z/E isomerism, is not detected.

Agranulocytosis↗

PubMed2006

A retinoic acid-Hox hierarchy controls both anterior/posterior patterning and neuronal specification in the developing central nervous system of the cephalochordate amphioxus.

Retinoic acid (RA) mediates both anterior/posterior patterning and neuronal specification in the vertebrate central nervous system (CNS). However, the molecular mechanisms downstream of RA are not well understood. To investigate these mechanisms, we used the invertebrate chordate amphioxus, in which the CNS, although containing only about 20,000 neurons in adults, like the vertebrate CNS, has a forebrain, midbrain, hindbrain, and spinal cord and is regionalized by RA-signaling. Here we show, first, that domains of genes with expression normally limited to diencephalon and midbrain are generally not affected by altered RA-signaling, second, that contrary to previous reports, not only Hox1, 3, and 4, but also Hox2 and Hox6 are collinearly expressed in the amphioxus CNS, and third, that collinear expression of all these Hox genes is controlled by RA-signaling. Finally, we show that Hox1 is involved in mediating both the role of RA-signaling in regionalization of the hindbrain and in specification of hindbrain motor neurons. Thus, morpholino knock-down of the single amphioxus Hox1 mimics the effects of treatments with an RA-antagonist. This analysis establishes RA-dependent regulation of collinear Hox expression as a feature common to the chordate CNS and indicates that the RA-Hox hierarchy functions both in proper anterior/posterior patterning of the developing CNS and in specification of neuronal identity.

Animals↗

PubMed2004

Collinearity in linear regression is a serious problem in oral health research.

The aim of this article is to encourage good practice in the statistical analysis of dental research data. Our objective is to highlight the statistical problems of collinearity and multicollinearity. These are among the most common statistical pitfalls in oral health research when exploring the relationship between clinical variables using multiple regression analysis. We hope that this article will show why these problems arise and how they can be avoided and overcome. Examples from the periodontal literature will be used to illustrate how collinearity and multicollinearity can seriously distort the model development process as a result of the phenomenon of mathematical coupling. Knowledge of these problems can help to eliminate misleading results and improve any subsequent interpretations. Regression analyses are useful tools in oral health research when their limitations are recognized. However, care is required in planning and it is worthwhile seeking statistical advice when formulating the study's research questions.

Algorithms↗

PubMed2000

Joint effects of nine polychlorinated biphenyl (PCB) congeners on breast cancer risk.

BACKGROUND: Polychlorinated biphenyls (PCB) have been a major environmental health concern because of their wide distribution and persistence in the environment. Estimating joint effects of all congeners in a single analysis is complicated by correlation among exposure levels, and the resulting collinearity makes the results difficult to interpret. METHODS: Patients with breast-related surgery at Yale-New Haven Hospital were interviewed using a standardized questionnaire, and breast adipose tissue samples were analysed for nine PCB congeners (74, 118, 138, 153, 156, 170, 180, 183, 187). The study recruited 490 women (304 cases and 186 controls) between 1994 and 1997. Logistic ridge regression was used to analyse the instability caused by collinearity. RESULTS: Although total PCB did not appear to be associated with breast cancer risk, significant differences in effect were observed among the nine congeners. Logistic ridge regression demonstrated a protective effect on breast cancer risk for a potentially anti-oestrogenic and dioxin-like congener, 156, while two phenobarbital, CYP1A and CYP2B inducers had an adverse effect, 180 and 183. This analysis also suggested that a protective effect for another phenobarbital congener, 153, was largely explained by instability caused by collinearity. CONCLUSIONS: These results indicate that studies of PCB congeners and health require an in-depth statistical analysis in order to better understand the complex issues related to their collinearity.

Adipose Tissue↗

PubMed2005

[A novel light-emitting diode-induced fluorescence detector for micro-scale flow analysis system].

A compact light-emitting diode-induced fluorescence detector based on collinear scheme is described. The detector was assembled by all-solid-state optical-electronic components and easily coupled with micro-scale flow analysis system by on-column detection mode. Fluorescein isothiocyanate (FITC) and FITC-labeled amino acids were used as test analytes to evaluate the detector performance by capillary electrophoresis and flow injection analysis techniques. The concentration limit of detection was 10(-8) mol x L(-1) for FITC-labeled phenylalanine at a signal-to-noise ratio (S/N) of 3 (on-column, 0.05 mm i.d.). The system exhibited a good linear response in the range of 1 x 10(-7) -2 x 10(-5) mol x L(-1) (r2 = 0.999). The relative standard deviation (RSD) of 6 repetitive injections on peak heights is less than 3%.

English Abstract↗

PubMed2002

Use of a Plackett-Burman design with multivariate calibration for the analysis of polycyclic aromatic hydrocarbons in micellar media by synchronous fluorescence.

This work describes the use of a multilevel Plackett-Burman design (PB) for the creation of a calibration set for partial least square regression (PLS). The PB calibration set was compared to a collinear analogue by testing these two PLS models for the analysis of six polycyclic aromatic hydrocarbons (PAHs). These compounds were analyzed in micellar media by synchronous fluorescence after determination of the experimental conditions (choice of surfactant, analytical conditions such as deltalambda, step, and scan range). The external validation shows that the collinear set is inappropriate to quantify PAH in real samples, but the PB calibration set affords optimal results.

Calibration↗

PubMed1988

Human papillomavirus type 52: a new virus associated with cervical neoplasia.

Analysis of biopsies of cervical intraepithelial neoplasia (CIN) revealed a high percentage of human papillomavirus (HPV) sequences that would hybridize to a mixture of HPV probes only under conditions of relaxed stringency. The DNA sequences of one of these viruses was molecularly cloned and shown to be a new HPV, type 52 (HPV-52). This virus is most closely related to HPV-33. Hybridization analysis with restriction fragments of HPV-52 showed collinearity with the HPV-33 genome. DNA sequencing revealed a high level of conservation between the two viruses within the L1 open reading frame but significant divergence in the non-coding region of the viral genomes. Prevalence studies indicated that HPV-52 sequences were present in three of 137 (2%) CIN and in one of 48 (2%) cervical squamous cell cancers studied in the U.S.A.

DNA, Viral↗

PubMed2006

Comparative genomics of Brassica oleracea and Arabidopsis thaliana reveal gene loss, fragmentation, and dispersal after polyploidy.

We sequenced 2.2 Mb representing triplicated genome segments of Brassica oleracea, which are each paralogous with one another and homologous with a segmentally duplicated region of the Arabidopsis thaliana genome. Sequence annotation identified 177 conserved collinear genes in the B. oleracea genome segments. Analysis of synonymous base substitution rates indicated that the triplicated Brassica genome segments diverged from a common ancestor soon after divergence of the Arabidopsis and Brassica lineages. This conclusion was corroborated by phylogenetic analysis of protein families. Using A. thaliana as an outgroup, 35% of the genes inferred to be present when genome triplication occurred in the Brassica lineage have been lost, most likely via a deletion mechanism, in an interspersed pattern. Genes encoding proteins involved in signal transduction or transcription were not found to be significantly more extensively retained than those encoding proteins classified with other functions, but putative proteins predicted in the A. thaliana genome were underrepresented in B. oleracea. We identified one example of gene loss from the Arabidopsis lineage. We found evidence for the frequent insertion of gene fragments of nuclear genomic origin and identified four apparently intact genes in noncollinear positions in the B. oleracea and A. thaliana genomes.

Arabidopsis↗

PubMed1994

The relationship between micronuclei in human lymphocytes and plasma levels of vitamin C, vitamin E, vitamin B12 and folic acid.

The cytokinesis-block micronucleus assay is increasingly being applied to the study of spontaneous or induced genetic damage in human lymphocytes, but little is known about dietary and other lifestyle factors that could influence this index. As part of a larger study investigating the role of dietary factors on baseline genetic damage in human lymphocytes from 152 non-smoking females and 113 non-smoking males evenly distributed between the ages of 20 and 87 years, we have measured (a) the micronucleus (MN) frequency and (b) the plasma level of the anti-oxidant vitamins C and E and the B vitamins folic acid and B12. Multiple regression analysis indicated that age (beta value = 0.598, P < 0.0001) was the most important factor influencing the variance of micronucleus frequency in females, while micronutrient levels had no apparent significant effects on genetic damage. In males age was also the predominant factor (beta value = 0.505, P < 0.0001) influencing genetic damage, but vitamin-C level also contributed positively and significantly to the observed MN frequency (beta value = 0.220, P < 0.0228). To avoid the potential confounding effect of collinearity between variables we also performed separate simple regression analysis for each plasma micronutrient in relation to age-adjusted micronucleus frequency; the results from this analysis again showed a significant and positive effect of plasma vitamin C on age-adjusted micronucleus frequency in males only (beta value = 0.188, P = 0.0503), while no effect was observed for the other micronutrients in both sexes. In view of the predominant age effect, we also focused on the data obtained in the youngest age groups of both sexes. In view of the predominant age effect, we also focused on the data obtained in the youngest age groups of both sexes (i.e. 20-30 years olds) and found (a) that the MN frequency in young males is significantly and positively correlated with plasma vitamin C levels (r = 0.823, P < 0.001) but negatively correlated with plasma vitamin B12 status (r = -0.799, P < 0.001) and (b) in females the only significant correlation was an inverse relationship between MN frequency and the combined folate and vitamin B12 plasma levels (r = -0.4632, P < 0.030).(ABSTRACT TRUNCATED AT 400 WORDS)

Adult↗