Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Multivariate statistics”

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 433 records · Page 24Linked to original sources
PubMed2006

Associations of changes in exercise level with subsequent disability among seniors: a 16-year longitudinal study.

BACKGROUND: The effect of changes in physical exercise on progression of musculoskeletal disability in seniors has rarely been studied. METHODS: We studied a prospective cohort annually from 1984 to 2000 using the Health Assessment Questionnaire Disability Index (HAQ-DI). The cohort included 549 participants, 73% men, with average end-of-study age of 74 years. At baseline and at the end of the study, participants were classified as "High" or "Low" vigorous exercisers using a cut-point of 60 min/wk. Four groups were formed: "Sedentary" (Low-->Low; N = 71), "Exercise Increasers" (Low-->High; N = 27), "Exercise Decreasers" (High-->Low; N = 73), and "Exercisers" (High-->High; N = 378). The primary dependent variable was change in HAQ-DI score (scored 0-3) from 1984 to 2000. Multivariate statistical adjustments using analysis of covariance included age, gender, and changes in three risk factors, body mass index, smoking status, and number of comorbid conditions. Participants also prospectively provided reasons for exercise changes. RESULTS: At baseline, Sedentary and Increasers averaged little exercise (16 and 22 exercise min/wk), whereas Exercisers and Decreasers averaged over 10 times more (285 and 212 exercise min/wk; p <.001). All groups had low initial HAQ-DI scores, ranging from 0.03 to 0.08. Increasers and Exercisers achieved the smallest increments in HAQ-DI score (0.17 and 0.11) over 16 years, whereas Decreasers and Sedentary fared more poorly (increments 0.27 and 0.37). Changes in HAQ-DI score for Increasers compared to Sedentary were significantly more favorable (p <.05) even after multivariate statistical adjustment. CONCLUSIONS: Inactive participants who increased exercise achieved excellent end-of-study values with increments in disability similar to those participants who were more active throughout. These results suggest a beneficial effect of exercise, even when begun later in life, on postponement of disability.

Aged↗
PubMed2006

Use of unsupervised and supervised artificial neural networks for the identification of lactic acid bacteria on the basis of SDS-PAGE patterns of whole cell proteins.

Conventional multivariate statistical techniques (hierarchical cluster analysis, linear discriminant analysis) and unsupervised (Kohonen Self Organizing Map) and supervised (Bayesian network) artificial neural networks were compared for as tools for the classification and identification of 352 SDS-PAGE patterns of whole cell proteins of lactic acid bacteria belonging to 22 species of the genera Lactobacillus, Leuconostoc, Enterococcus, Lactococcus and Streptococcus including 47 reference strains. Electrophoretic data were pre-treated using the logistic weighting function described by Piraino et al. [Piraino, P., Ricciardi, A., Lanorte, M. T., Malkhazova, I., Parente, E., 2002. A new procedure for data reduction in electrophoretic fingerprints of whole-cell proteins. Biotechnol. Lett. 24, 1477-1482]. Hierarchical cluster analysis provided a satisfactory classification of the patterns but was unable to discriminate some species (Leuconostoc, Lb. sakei/Lb. curvatus, Lb. acidophilus/Lb. helveticus, Lb. plantarum/Lb. paraplantarum, Lc. lactis/Lc. raffinolactis). A 7x7 Kohonen self-organizing map (KSOM), trained with the patterns of the reference strains, provided a satisfactory classification of the patterns and was able to discriminate more species than hierarchical cluster analysis. The map was used in predictive mode to identify unknown strains and provided results which in 85.5% of cases matched the classification obtained by hierarchical cluster analysis. Two supervised tools, linear discriminant analysis and a 23:5:2 Bayesian network were proven to be highly effective in the discrimination of SDS-PAGE patterns of Lc. lactis from those of other species. We conclude that data reduction by logistic weighting coupled to traditional multivariate statistical analysis or artificial neural networks provide an effective tool for the classification and identification of lactic acid bacteria on the basis of SDS-PAGE patterns of whole cell proteins.

Bacterial Proteins↗
PubMed1995

Effects of K(+)-induced depolarization and purinergic receptor activation on elemental content in insulin-producing RINm5F-cells.

X-ray microanalysis was used to detect elemental changes in the insulin-producing tumor cell-line RINm5F. To improve discrimination between mobile ions and ions bound to macromolecules a new approach was employed, consisting of multivariate statistical analysis of correlations between the concentrations of Na, Mg, P, S, Cl, K, and Ca. RINm5F cells, cultured on Formvar-coated titanium grids, were stimulated with high K+ or ATP, that are both known to stimulate insulin release. The buffers used contained Ca2+ or one of the Ca(2+)-analogues Sr2+ and Ba2+, to represent Ca2+ uptake in response to stimulation. After stimulation the cells were shock-frozen and freeze-dried overnight. Incubation for 10-20 seconds in a Ca(2+)-containing buffer did not significantly affect elemental composition, whereas cellular Mg, P and K decreased in a Sr(2+)-containing buffer. Depolarization with high K+ concentration caused an increase in the cellular Na content, both in Ca(2+)- and Sr(2+)-containing buffers, but not in the buffer where Ca2+ had been replaced by Ba2+. X-ray microanalysis is useful for detection of elemental changes subsequent to stimulation of cultured cells. Moreover, multivariate statistical analysis strengthens the idea that stimulation of RINm5F cells causes redistribution of ions possibly due to changes in the state of binding of some elements to cellular proteins.

Adenosine Triphosphate↗
PubMed1994

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

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

Aged↗
PubMed2003

What affects mRNA levels in leaves of field-grown aspen? A study of developmental and environmental influences.

We have analyzed the abundance of mRNAs expressed from 11 nuclear genes in leaves of a free-growing aspen (Populus tremula) tree throughout the growing season. We used multivariate statistics to determine the influence of environmental factors (i.e. the weather before sampling) and developmental responses to seasonal changes at the mRNA level for each of these genes. The gene encoding a germin-like protein was only expressed early in the season, whereas the other tested genes were expressed throughout the season and showed mRNA variations on a day-to-day basis. For six of the genes, reliable models were found that described the mRNA level as a function of weather, but the leaf age was also important for all genes except one encoding an early light-inducible protein (which appeared to be regulated purely by environmental factors under these conditions). The results confirmed the importance of several environmental factors previously shown to regulate the genes, but we also detected a number of less obvious factors (such as the variation in weather parameters and the weather of the previous day) that correlated with the mRNA levels of individual genes. The study shows the power of multivariate statistical methods in analyzing gene regulation under field conditions.

Gene Expression Regulation, Developmental↗
PubMed1986

Effects of altitude, ethnicity-religion, geographical distance, and occupation on adult anthropometric characters of eastern Himalayan populations.

With a view to estimating the effect of altitude on body dimensions vis-à-vis ethnicity-religion, geographical distance, and occupation, a comprehensive multivariate statistical analysis was performed on data pertaining to 16 anthropometric characters collected from 1,103 individuals (643 males and 460 females) belonging to two ethnic groups-Sherpa and Lepcha. Samples were drawn from several locations in the eastern Himalayan region-Darjeeling and Kalimpong in West Bengal (India), and Nepal, situated at low (1,000-2,000 meters) and high (above 3,500 meters) altitudes. The individuals sampled practice different occupations and follow different religions. Significant age and sex effects were observed. The data were age-adjusted, and sexes were treated separately. A test of equality of mean vectors indicated heterogeneity among population groups. Almost all characters were found to contribute significantly to the ability to discriminate between the groups. The overall probability of correctly classifying an individual based on body dimensions into the group in which she or he actually belongs was high (between 0.64 and 0.77). Shape and size factors could be identified that explained about 50% of the total variance and yielded a reasonable separation of the groups. Results of four different types of multivariate statistical analyses were in agreement, and showed that altitude is most highly associated with body dimensions.

Adult↗
PubMed1995

Influence of three factors on the diagnostic effectiveness of transthoracic needle aspiration in pneumonia.

Prior antibiotic therapy, size of the infiltrate, and the person who performed the technique were the three factors that we studied to assess their influence on the effectiveness of transthoracic needle aspiration (TNA). Ninety-one patients with a diagnosis of severe bacterial pneumonia, who underwent TNA, have been included in the study. The technique was carried out with an ultrathin needle gauge 25 and without fluoroscopic control. A univariate (UA) and a multivariate statistical analysis were made. The sensitivity of TNA was 34.1%. Fifty-seven of 91 (62.6%) had received antibiotic therapy prior to TNA; sensitivity was higher in nontreated patients than in treated patients (p = 0.0033; UA). There were 34 patients with an infiltrate that was smaller than a lobe (MINLOB); 39 cases affected a complete lobe (LOB) and 18 more than one lobe (MAJLOB). The TNA sensitivity was higher in LOB cases than in MINLOB cases (p = 0.0004; UA) while when comparing LOB cases and MAJLOB cases, sensitivity was higher in the former (p = NS; UA). In 28 of 91 cases (30.8%), the TNA was performed by A (a trained physician who regularly carries out the technique) and in 63 of 91 cases (69.2%) by B (other physicians, 10 in our study, who sporadically perform the technique). The TNA sensitivity was higher when the technique was performed by A, although this difference was not significant; if we add negative TNA with leukocytes present in Gram stains (which would indicate that aspiration was done in the correct area) to positive TNA, the difference between A and B was higher (p = 0.0248). The multivariate statistical analysis confirmed that there are two variables that are independently connected to a positive TNA (prior antibiotic therapy and size of the infiltrate). As regards the variable "person who carries out the technique," a significant association with a positive TNA was not established, although the estimations we obtained show a possible clinical relevance.

Adult↗
PubMed2000

Topography of clonidine-induced electroencephalographic changes evaluated by principal component analysis.

BACKGROUND: Principal component analysis is a multivariate statistical technique to facilitate the evaluation of complex data dimensions. In this study, principle component analysis was used to reduce the large number of variables from multichannel electroencephalographic recordings to a few components describing changes of spatial brain electric activity after intravenous clonidine. METHODS: Seven healthy volunteers (age, 26 +/- 3 [SD] yr) were included in a double-blind crossover study with intravenous clonidine (1.5 and 3.0 microg/kg). A spontaneous electroencephalogram was recorded by 26 leads and quantified by standard fast Fourier transformation in the delta, theta, alpha, and beta bands. Principle component analysis derived from a correlation matrix calculated between all electroencephalographic leads (26 x 26 leads) separately within each classic frequency band. The basic application level of principle component analysis resulted in components representing clusters of electrodes positions that were differently affected by clonidine. Subjective criteria of drowsiness and anxiety were rated by visual analog scales. RESULTS: Topography of clonidine-induced electroencephalographic changes could be attributed to two independent spatial components in each classic frequency band, explaining at least 85% of total variance. The most prominent effects of clonidine were increases in the delta band over centroparietooiccipital areas and decreases in the alpha band over parietooccipital regions. Clonidine administration resulted in subjective drowsiness. CONCLUSIONS: Data from the current study supported the fact that spatial principle component analysis is a useful multivariate statistical procedure to evaluate significant signal changes from multichannel electroencephalographic recordings and to describe the topography of the effects. The clonidine-related changes seen here were most probably results of its sedative effects.

Adult↗
PubMed2006

Discriminatory classification of natural and anthropogenic waters in two U.K. estuaries.

The ability to distinguish water inputs from both natural and anthropogenic sources was investigated in the complex environment of an urban estuary (Tyne) and a relatively pristine estuary (Tweed). We used a data set from a total of 11 estuarine transects, comprising measurements of bulk dissolved organic matter (dissolved organic carbon and nitrogen), dissolved nitrogen (total dissolved nitrogen, ammonium, nitrate+nitrite and dissolved organic nitrogen), optical absorbance measurements (a350, S290-350) and fluorescence excitation emission matrix measurements (fluorophores A, H, B and T intensity and A and H emission wavelength maxima). In order to investigate trends within the numerous parameters measured, multivariate statistics were employed. Principal components analyses showed 63.4% of the variability in the total data set can be explained by two sets of components and 74.9% of the variability by the spectrophotometric measurements alone. In both analyses the first component correlated to the mixing of terrestrial and marine waters and the second component was correlated to sources of pollution such as domestic sewage. Within the data set, river flow and terrestrially derived DOM were significantly correlated, and situations with high river input showed an increase in terrestrial signature in the estuary. Discriminant analyses were also carried out and indicated that 59.8% (total data set) and 53.3% (solely spectrophotometric data) of the samples can be correctly classified into their respective groups (water categories) assigned on the basis of salinity and sampling location. Overall the results clearly show the potential of spectrophotometric techniques to discriminate distinct water categories with different DOM characteristics. In particular, measurement of the fluorophore H emission maxima, the spectral slope parameter, S290-350, and fluorophores T and B intensity enabled discrimination of DOM from riverine, estuarine, marine, and sewage affected water categories. The results presented here indicate the ability of spectrophotometric data alone to distinguish between marine, anthropogenic and terrestrial DOM and distinguish terrestrial DOM from different catchments (Tyne vs. Tweed). With current advances in the in-situ deployment of absorbance and fluorescence spectroscopy it is anticipated that multivariate statistics will gain importance as a cost effective, powerful and diagnostic approach to assessing the distributions of water types and their associated DOM characteristics and fluxes at the land-ocean interface.

Carbon↗
PubMed1993

Differential activation and classification of cutaneous afferents in the rat.

1. A total of 312 cutaneous afferent units identified in the rat foot as belonging to one of nine major types of sensory receptors were included in the present study. A natural stimulus set was defined to differentiate optimally among those receptor types according to the distinguishing response patterns that it produced. It included air puffs, 30- and 300-Hz sinusoids, 200-mN force indentation of the skin, 1.2- and 6-N compressions of a skin fold, cooling the skin by 5 and 20 degrees C, warming by 5 degrees C, and heating by 15 degrees C. 2. The responses to predefined stimuli of 188 units were subjected to multivariate statistical analyses. The responses of an individual unit were measured as the number of impulses evoked by 10 stimuli, each lasting 10 s. Additionally, the number of impulses occurring for 5 s after withdrawal of a 200-mN indentation (1 of the 10 stimuli) was counted. 3. In discriminant analysis, the 11 stimulus variables predicted fairly correctly the grouping of afferent units into nine predetermined receptor categories (175 of 188, 93.1%), indicating a powerful ability to discriminate among different receptor types. Using hierarchical cluster analysis, afferent unit data described by 11 variables were divided into clusters that well represented prior receptor categories (170 of 188, 90.4%), suggesting the reliable application of this procedure to the classification of newly recorded cutaneous sensory receptors. 4. Eleven variables were then reduced to 7 on the basis of the results of factor analysis (95% of variance accounted for). The seven variables corresponded to 1.2-N compression, heating the skin by 15 degrees C, cooling the skin by 20 degrees C, 30- and 300-Hz sinusoids, withdrawal of a 200-mN indentation, and air puffs. 5. The seven selected variables correctly assigned afferent units into five modality-based categories in the discriminant solution (177 of 188, 94.1%). In the cluster solution, afferent units described by the seven selected variables were divided into clusters, most of whose members were modality specific (176 of 188, 93.6%). 6. The results indicate that cutaneous receptors can be divided into modality-specific groups according to similarities in their responses to seven stimulus variables. It is proposed that the stimulus set developed here and multivariate statistical methods can be used as powerful tools for the functional classification of central somatosensory neurons.

Afferent Pathways↗
PubMedDate not supplied

Use of TLC and multivariate mathematical statistical methods to study the interaction of monoamine oxidase inhibitory drugs with amino acids.

The interaction of 17 monoamine oxidase inhibitory drugs (propargylamine derivatives) with amino acids was studied by charge-transfer chromatography. The data set was evaluated by principal component analysis (PCA). To assess the effect of the information loss caused by normalization, PCA was separately carried out on the covariance and on the correlation matrix. The strength and selectivity of interaction was separated by the spectral mapping technique. Calculation proved that the amino group of the drugs interacted with the second carboxyl group of dicarboxylic amino acids, and that the interaction was of electrostatic character. This finding made probable the direct interaction between the drugs and the target enzyme or enzymes. The results of both PCA methods were similar. However, coordinates of the spectral map showed only slight correlation with the corresponding coordinates of the two-dimensional nonlinear maps proving the different information content of the methods.

Amino Acids↗
PubMed2000

Do undefined sources of hepatitis C transmission exist? The Greek study in General Practice.

A seroepidemiological study was carried out in 15 primary health care (PHC) centres in rural Greece to determine the prevalence of hepatitis C virus (HCV) in the surgeries of Greek General Practitioners (GPs) and to further clarify the transmission of hepatitis C in Greece. Serum samples were obtained from 1961 subjects (1259 females) aged >/= 15 years, who visited GP surgeries between July 1996 and February 1997 in 15 PHC centres located in three large Greek regions (Macedonia, Attika and Crete). Subjects who participated in the study fulfilled the following criteria: history of blood transfusion; hospital admission of > 7 days' duration without surgical or other intervention; use of intravenous drugs (current or previous); or women with a history of medical or paramedical abortion. Nearly 65% (1263 subjects) of the participants in this study reported hospital admission with a length of stay > 7 days. Antibodies to HCV (anti-HCV) were found in 67 participants (3. 5%), 41 of whom were females and 44 of whom were aged >/= 61 years. The highest prevalence (4.8%) of anti-HCV was found in Crete, and differences among the Greek regions were statistically significant (P < 0.05). Multivariate statistical analysis showed that in addition to regional differences, the following variables had a statistically significant effect on the prevalence of anti-HCV: history of dental surgery; use of intravenous drugs; hospital admission for > 7 days; and the high consumption of alcoholic drinks. Hence there is a significant variability in the prevalence of hepatitis C in well-defined PHC areas of Greece. Several risk factors for acquiring HCV infection have been identified. Screening for HCV risk factors may enable Greek GPs to identify HCV-infected patients.

Adolescent↗
PubMed2005

Relationship between HIV viral load and Langerhans cells of the cervical epithelium.

AIM: To determine the relationship between the density of cervical mucosa Langerhans cells, cervical histology, and HIV viral load. METHODS: Eighty-four HIV-infected and 17 women at high risk for HIV had cervical biopsies assessed for squamous intraepithelial lesions and Langerhans cell density. Langerhans cells were identified using the S-100 immunohistochemical stain and were counted manually. Polymerase chain reaction assays were used to detect cervical human papillomavirus (HPV)-DNA. T-cell subsets were determined using immunofluorescent flow cytometry. Plasma HIV RNA levels were measured using a nucleic acid sequence-based amplification technique. The associations between cervical Langerhans cell density, cervical histology, CD4 counts, HIV viral loads, HPV-DNA detection, and smoking status were assessed using multivariate statistical models. RESULTS: In multivariate analysis among women infected with HIV, the mean Langerhans cell density per high-powered field was 4.00 among women with no detectable plasma HIV-RNA, and 1.92 among those with detectable HIV-RNA (P = 0.01). The mean cervical Langerhans cell density was increased in women with high-grade squamous intraepithelial lesions compared with those with low-grade squamous intraepithelial lesions and normal/metaplastic histology (3.87 vs 2.11; P = 0.05). Neither HPV-DNA detection, smoking status, nor CD4 count was significantly associated with Langerhans cell density. CONCLUSIONS: The decrease in cervical Langerhans cell density in women with detectable HIV-RNA suggests an impaired mucosal immune response to local infections, such as HPV. Conversely, HPV infection resulting in high-grade dysplasia might be associated with an enhanced local immune response.

Analysis of Variance↗
PubMed1985

[Long-term prognosis of drug and surgery treated patients with acquired aortic valve diseases: survival statistics and multivariate Cox regression analysis].

Data of 417 patients with advanced chronic aortic valve disease were retrospectively analyzed using a life table and Cox regression analysis. Aortic valve replacement was recommended to all patients based on clinical and hemodynamic findings. While most patients underwent prosthetic aortic valve replacement (n = 349), a minority of patients was treated medically (n = 68). Prognosis was better (p less than 0.01 in the Cox model) in surgically treated as compared to medically treated patients with aortic stenosis (4-year survival rate 82 versus 44%). In patients with aortic insufficiency no significant difference of long-term prognosis was found between surgically and medically treated patients.

Anti-Bacterial Agents↗
PubMed1980

[Reliability of statistical methods in anthropology].

Univariate and multivariate statistical methods are confronted as to their efficiency and objectivity. Similar to the comparison of patients showing chromosomal aberrations or serious diseases with their normal controls, the investigation of various populations can only result in the determination of differences on the basis of features arbitrarily selected, but not in a classification of systematic categories. Objections as to the objectivity of statistical procedures in the field of racial classification are discussed.

Anthropology↗
PubMed2003

[Impact of tumor size on long-term survival of patients with organ-confined renal cell cancer].

PURPOSE: As a result of the observation that the potential biological aggressiveness of even early stage renal cell cancer (RCC) strongly correlates with tumor size, the 5th edition of the TNM system (1997), which classifies all renal tumors up to a maximum diameter of 7 cm as T1, was modified in the current classification to distinguish T1a and T1b tumors based on a cut-off of 4 cm. Only a few larger investigations supporting this cut-off are available in the literature and these are based on univariate statistical analysis. To determine whether this cut-off best reflects the correlation between aggressive potential and tumor size and thus differentiates patients at low or high risk of progression, this investigation was performed using both univariate and multivariate statistical analysis. MATERIALS AND METHODS: Between 1981 and 2000, a total of 652 patients underwent tumor nephrectomy for renal cell carcinoma. Of these, the 243 patients with local RCC not extending beyond the renal capsule were subjected to univariate (log rank test) and multivariate (Cox regression model) statistical analysis. RESULTS: It became evident that, while during univariate analysis the prognostic calue of a cut-off size of 4 cm was confirmed, multivariate analysis identified the highest relative risk of cause-specific death (2.93) in those patients with tumors larger than 5 cm maximum diameter. CONCLUSIONS: The 5 cm cut-off thus appears to best determine the clinical prognosis for patients undergoing tumor nephrectomy for early stage renal call cancer. Taking this into consideration, the present study clearly demonstrates the reed for a multivariate statistical approach when the current modification of the TNM classification system is critically reevaluated.

Adult↗
PubMed1994

[Morphometrical and statistical detection of cancer cells].

Morphometrical and multivariate statistical methods were applied to detection of carcinoma cells in cytologic studies. A total of 70 clumps of epithelial cells were selected from endometrial samples (10 adenocarcinomas, 4 hyperplasias and 56 normal controls), and their cytologic characters were reduced to a combination of five quantitative parameters (nuclear size, degree of anisokaryosis, nuclear from index, homogeneity of nuclear chromatin texture and regularity of cellular arrangement). The 5-variate cluster analysis demonstrated that the 70 clumps could be classified into three definite groups; A(17), B(41), and C(12). Group C, characterized by cells of large nuclear size, marked anisokaryosis, heterogeneous chromatin texture and irregular cellular arrangement, was derived from 10 samples of adenocarcinoma and 2 hyperplasia, while Groups A and B were not derived from any malignant samples. In conclusion, morphometrical-statistical classification can be of great aid in improving the cytodiagnostic validity and reproducibility.

Adenocarcinoma↗