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 379 records · Page 21Linked to original sources
PubMed1993

Malignancy-associated changes in monocytes and lymphocytes in acute leukemias measured by high-resolution image processing.

A number of methods are available for classifying lymphoid and myeloid leukemias in peripheral blood and bone marrow. However, in clinical diagnosis an initial and particularly important step is morphologic analysis. All the cells in this investigation were classified by two hematologic experts. In most cases, immunophenotyping and immunocytochemical analyses were performed. Routinely prepared Romanowsky-Giemsa-stained peripheral blood smears (approximately 23,000 cells) were scanned by a high-resolution color TV/microscope system and analyzed by color and texture algorithms. In addition to blast cells, lymphocytes and monocytes exhibited a leukemia-associated change in morphology. The calculated texture and color features were most significant for the subtyping performed by the statistical program. With multivariate statistical analysis, seven mathematical subtypes of lymphocytes and five of monocytes could be found over all the specimens. Acute myeloblastic leukemia (AML, M1-M2), acute myelomonocytic leukemia (AMMOL, M4) and acute monocytic leukemia (AMOL, M5) could be differentiated by their distributions of monocyte subtypes. However, this was impossible for the lymphocyte subtypes. Acute lymphoblastic leukemias (B-ALL and T-ALL) were discernible with the aid of lymphocyte subtypes and acute myeloid conditions from viral infections, such as with the Epstein-Barr virus. The method increased the relevance of image processing in clinical diagnosis of acute leukemias and showed that the "normal" cell populations were not really normal in malignant leukemias.

Burkitt Lymphoma↗
PubMed2007

Multivariate scan statistics for disease surveillance.

In disease surveillance, there are often many different data sets or data groupings for which we wish to do surveillance. If each data set is analysed separately rather than combined, the statistical power to detect an outbreak that is present in all data sets may suffer due to low numbers in each. On the other hand, if the data sets are added by taking the sum of the counts, then a signal that is primarily present in one data set may be hidden due to random noise in the other data sets. In this paper, we present an extension of the spatial and space-time scan statistic that simultaneously incorporates multiple data sets into a single likelihood function, so that a signal is generated whether it occurs in only one or in multiple data sets. This is done by defining the combined log likelihood as the sum of the individual log likelihoods for those data sets for which the observed case count is more than the expected. We also present another extension, where the concept of combining likelihoods from different data sets is used to adjust for covariates. Using data from the National Bioterrorism Syndromic Surveillance Demonstration Project, we illustrate the new method using physician telephone calls, regular physician visits and urgent care visits by Harvard Pilgrim Health Care members cared for by Harvard Vanguard Medical Associates, a large multi-specialty group practice in Massachusetts. For upper and lower gastrointestinal (GI) illness, there were on average 20 telephone calls, nine urgent care visits and 22 regular physician visits per day. The strongest signal was generated by a single data set and due to a familial outbreak of pinworm disease. The second and third strongest signals were generated by the combined strength of two of the three data sets.

Boston↗
PubMed1990

Lack of useful clinical predictors of response to splenectomy in patients with chronic idiopathic thrombocytopenic purpura.

We set out to identify clinical or analytical variables that might predict the response to splenectomy in patients with chronic idiopathic thrombocytopenic purpura (ITP). We retrospectively examined 138 mostly adult patients with chronic ITP, treated with splenectomy. Information was compiled from five Public Health Hospitals from a questionnaire and chart review. Sixty-one potentially prognostic variables were analysed by univariate and multivariate statistical methods. After multivariate analysis, age (relative risk = 1.02; CI 1-1.03) and a severity of the bleeding diathesis (relative risk = 1.6; CI 1.13-2.22) were independent prognostic factors for a sustained response to splenectomy. An independent analysis of the postsplenectomy counts showed that an early (days 1-3) thrombocyte count exceeding 156 x 10(9)/l cells increases the likelihood of a permanent unmaintained response. Our data indicate that the response to splenectomy in patients with chronic ITP cannot be adequately predicted on the basis of pre-splenectomy clinical or analytical variables.

Adult↗
PubMed2003

Hepatology and the Canadian gastroenterologist: interest, attitudes and patterns of practice: results of a national survey from the Canadian Association of Gastroenterology.

BACKGROUND: Hepatology has emerged as a subspecialty distinct from gastroenterology. Despite this, there is no formal certification examination or accredited training program, and training remains combined with gastroenterology. AIM: To determine attitudes, perceptions and patterns of practice with respect to liver disease among Canadian gastroenterologists. METHODS: A survey questionnaire was distributed to clinician gastroenterologists who are members of the Canadian Association of Gastroenterology. The responses of subgroups of respondents were compared by univariate and multivariate statistical techniques. RESULTS: Hepatologists constituted 20 of 201 respondents, the rest identifying themselves as gastroenterologists. Among gastroenterologists, liver disease constituted 10% of in- and out-patient practice. Despite this, 85% of gastroenterologists maintain an interest in hepatology, 49% perform liver biopsies, 60% treat hepatitis C, and 54% treat hepatitis B. In all of these areas, university-based gastroenterologists were consistently less likely than community-based gastroenterologists to maintain an interest and practice in hepatology, a finding that remained statistically significant on multivariate analysis. With regard to hepatology training, 90% of hepatologists and 94% of gastroenterologists felt that hepatology training should remain combined with gastroenterology, although 55% of hepatologists felt that current training was adequate compared with 79% of gastroenterologists, who were satisfied with the status quo. CONCLUSIONS: Hepatology remains relevant and important to Canadian gastroenterologists, especially those who have community-based practices. Canadian gastroenterologists and hepatologists are not in favour of separating hepatology training from existing gastroenterology training programs, although hepatologists feel that the current level of training is suboptimal.

Attitude of Health Personnel↗
PubMed1988

Simultaneous cleft lip and palate repair: an experimental study in beagles.

This study was designed to test the hypothesis that simultaneous lip and palate repair results in more severe craniofacial growth aberrations than lip repair or palate repair performed separately. Seventy-six purebred beagles were divided into five groups. Two of these groups were controls (unoperated and unrepaired animals); the three remaining groups were experimental (in one group only the lip was repaired, in another only the palate was repaired, and in the last the lip and palate were repaired simultaneously). Cephalometric measurements were analyzed using univariate and multivariate statistical techniques. In multivariate analysis, stepwise multiple regression and discrimination were applied to precisely assess the effects of the various surgical procedures. The results of this study indicate that simultaneous lip and palate repair results in more severe craniofacial growth aberrations than lip repair or palate repair performed separately.

Animals↗
PubMed1999

Multivariate quantitative structure-pharmacokinetic relationships (QSPKR) analysis of adenosine A1 receptor agonists in rat.

The aim of this study was to investigate the feasibility of a quantitative structure-pharmacokinetic relationships (QSPKR) method based on contemporary three-dimensional (3D) molecular characterization and multivariate statistical analysis. For this purpose, the programs SYBYL/CoMFA, GRID, and Pallas, in combination with the multivariate statistical technique principal component analysis were employed to generate a total of 16 descriptor variables for a series of 12 structurally related adenosine A1 receptor agonists. Subsequently, the multivariate regression method, partial least squares, was used to predict clearance (CL), volume of distribution (VdSS) and protein binding (fraction unbound, fU). The QSPKR models obtained could account for most of the variation in CL, VdSS, and fU (R2 = 0.82, 0.61 and 0.78, respectively). Cross-validation confirmed the predictive ability of the models (Q2 = 0.59, 0.41 and 0.62 for CL, VdSS, and fU, respectively). In conclusion, we have developed a multivariate 3D QSPKR model that could adequately predict overall pharmacokinetic behavior of adenosine A1 receptor agonists in rat. This methodology can also be used for other classes of compounds and may facilitate the further integration of QSPKR in drug discovery and preclinical development.

Animals↗
PubMed2002

Environmetric approaches to estimate pollution impacts on a coastal area by sediment and river water studies.

This paper represents an effort to demonstrate the opportunities of some environmetric methods like regression analysis, cluster analysis and principal components analysis. Their role for data modeling is stressed and the basic theoretical principles are given. The application of the multivariate statistical methods is illustrated by two major examples: Assessment of metal pollution based on multivariate statistical modeling of "hot spot" sediments from the Black Sea; and a trend study of Kamchia River water quality. In the first part of the study the environmetric approach makes it possible to separate three zones of the marine environment with different levels of pollution (Bourgas gulf, Varna gulf and lake buffer zone). Further, the extraction of four latent factors offers a specific interpretation of the possible pollution sources and separates the natural factors from the anthropogenic ones, the latter originating from contamination by chemical and steel-works and an oil refinery. In the second part of the study nine sampling sites along Kamchia River were considered as sources for water quality monitoring data. Trends for all parameters are calculated by the use of linear regression analysis and special attention is paid to a specific coastal site. Then five latent factors were extracted from the monitoring data set in order to gain information about some structural characteristics of the set.

Cluster Analysis↗
PubMed2002

A new statistical method for testing hypotheses of neuropsychological/MRI relationships in schizophrenia: partial least squares analysis.

We applied partial least squares (PLS) as a novel multivariate statistical technique to examine neuropsychological correlates of magnetic resonance imaging (MRI) measures of brain volumes in a well studied sample of 15 male patients with chronic schizophrenia. In the current study, because the total number of measures far surpassed the total number of subjects, extant multivariate techniques such as canonical correlation could not be used to examine relationships among simultaneous measures of MRI and neuropsychology. Moreover, because MRI measures were expected to be highly inter-correlated, as would be neuropsychological test scores, extant multivariate statistical techniques would be substantially limited because they typically assume statistical independence among sets of measures. PLS, on the other hand, proved to be especially well suited to examining the relationships among function and anatomy measures in this sample, where statistically significant relationships were demonstrated that were entirely consistent with prior studies using univariate correlation techniques. In particular, statistically significant relationships emerged among sets of MRI temporal lobe measures and neuropsychological tests of verbal memory and categorization as well as among MRI frontal measures and neuropsychological tests of working memory.

Adult↗
PubMed2005

The crash severity impacts of fixed roadside objects.

INTRODUCTION: This study analyzes the in-service performance of roadside hardware on the entire urban State Route system in Washington State by developing multivariate statistical models of injury severity in fixed-object crashes using discrete outcome theory. The objective is to provide deeper insight into significant factors that affect crash severities involving fixed roadside objects, through improved statistical efficiency along with disaggregate and multivariate analysis. METHOD: The developed models are multivariate nested logit models of injury severity and they are estimated with statistical efficiency using the method of full information maximum likelihood. RESULTS: The results show that leading ends of guardrails and bridge rails, along with large wooden poles (e.g. trees and utility poles) increase the probability of fatal injury. The face of guardrails is associated with a reduction in the probability of evident injury, and concrete barriers are shown to be associated with a higher probability of lower severities. Other variables included driver characteristics, which showed expected results, validating the model. For example, driving over the speed limit and driving under the influence of alcohol increase the probability of fatal accidents. Drivers that do not use seatbelts are associated with an increase in the probability of more severe injuries, even when an airbag is activated. IMPACT ON INDUSTRY: The presented models show the contribution of guardrail leading ends toward fatal injuries. It is therefore important to use well-designed leading ends and to upgrade badly performing leading ends on guardrails and bridges. The models also indicate the importance of protecting vehicles from crashes with rigid poles and tree stumps, as these are linked with greater severities and fatalities.

Accidents, Traffic↗
PubMed2005

Application of partial least squares discriminant analysis to two-dimensional difference gel studies in expression proteomics.

Two-dimensional difference gel electrophoresis (DIGE) is a tool for measuring changes in protein expression between samples involving pre-electrophoretic labeling ith cyanine dyes. In multi-gel experiments, univariate statistical tests have been used to identify differential expression between sample types by looking for significant changes in spot volume. Multivariate statistical tests, which look for correlated changes between sample types, provide an alternate approach for identifying spots with differential expression. Partial least squares-discriminant analysis (PLS-DA), a multivariate statistical approach, was combined with an iterative threshold process to identify which protein spots had the greatest contribution to the model, and compared to univariate test for three datasets. This included one dataset where no biological difference was expected. The novel multivariate approach, detailed here, represents a method to complement the univariate approach in identification of differentially expressed protein spots. This new approach has the advantages of reduced risk of false-positives and the identification of spots that are significantly altered in terms of correlated expression rather than absolute expression values.

Analysis of Variance↗
PubMed2004

Levels of total suspended particulate matter and major trace elements in Kosovo: a source identification and apportionment study.

Concentration levels of total suspended particles (TSP) and 27 major, minor and trace elemental components were determined at four sites in Kosovo through a 1-year survey (January-December 2002). Ambient concentrations were evaluated in comparison to limit values. The origin of elemental TSP constituents was investigated by calculating enrichment factors and diagnostic ratios. Multivariate statistics, such as hierarchical cluster analysis and factor analysis, were also employed to identify emission sources. A multivariate statistical receptor model (Absolute Principal Component Analysis, APCA) was applied to quantify source contributions. Soil dust, cement production, vehicular emissions, brake wear, and fuel combustion were identified as major sources with variable contributions at the four sampling sites.

Air Pollutants↗
PubMed1997

[Pathological analysis and clinical importance of invasion and neck nodal metastasis in squamous cell carcinoma of the tongue].

To determine the absolute and relative of histopathological parameters and conventional indicators in correlation with invasion and nodal metastasis, we performed both univariate and multivariate statistical analysis in 92 patients with squamous cell carcinoma of the tongue by spss/pc+ statistical system. Mode of invasion (MI) and peritumoral lymphocytic infiltrating density (PLID) were significant and independent factors by multivariate analysis (P = 0.000, P = 0.009 respectively), although univariate analysis showed that MI, PLID, T-stage and Grading were significantly associated with nodal metastasis. A correlation exists only between T-stage and MI by multivariate statistical test (P = 0.045), while, PLID, T-stage and Grading were significant parameters by univariate analysis. A highly dense PLI around cancer nest was observed which blocked nest from tissue and capillary lymph vessels.

Adult↗
PubMed2006

What are the most powerful determinants of endoscopic vesicoureteral reflux correction? Multivariate analysis of a single institution experience during 6 years.

PURPOSE: As the indications for endoscopic correction of vesicoureteral reflux continue to expand, the emergence of potential predictive variables has been noted. We used univariate and multivariate statistical analyses to find the most significant predictors of correction to improve patient selection. MATERIALS AND METHODS: A consecutive series of patients treated at a single institution was reviewed. Between August 1998 and August 2004, 232 children endoscopically injected with polydimethylsiloxane were identified, representing 351 refluxing units. A total of 23 variables were subjected to statistical analysis to detect predictors of reflux correction after injection. All identified patients with complete data and followup evaluations were included irrespective of anatomical variations, previous interventions or comorbidities. RESULTS: The overall success rate by patient and renal unit was 65% and 72%, respectively. In patients with a single system low grade (1-3) vesicoureteral reflux who did not previously undergo injection this success rate increased to 80%. Univariate analysis demonstrated that higher physician experience, low preoperative vesicoureteral reflux grade, absent renal scars and no previous injections were statistically significant predictors of vesicoureteral reflux correction (p <0.05). A history of febrile urinary tract infections and a duplex system did not attain significance (p = 0.069 and 0.076, respectively). On multivariate statistical evaluation only physician experience, preoperative vesicoureteral reflux grade and the number of previous injections remained significant. CONCLUSIONS: Multivariate analysis of our data showed the most important determinants of vesicoureteral reflux correction after endoscopic injection. Prospective validation will allow us to generate nomograms to better select and counsel patients who would benefit from vesicoureteral reflux treatment.

Child↗
PubMed1996

Prognostic value of psychological testing in patients undergoing spinal cord stimulation: a prospective study.

OBJECTIVE: Associations between psychological and physical states are understood to exist, and the development of standardized psychological tests has allowed quantitative evaluation of this relationship. We tested whether associations exist between psychological test instruments and patients selected for therapeutic trials of spinal cord stimulation (SCS) for chronic, intractable pain. METHODS: Fifty-eight patients selected for SCS were tested prospectively with a battery of standardized psychological tests: Minnesota Multiphasic Personality Inventory with Wiggins content scales, Symptom Check List-90, and Derogatis Affects Balance Scale. Associations between treatment outcomes and preoperative test scores and clinical variables were tested by univariate and multivariate statistical analyses, in which the dependent variables were as follows: 1) the outcome of a therapeutic trial of stimulation (whether the patient derived sufficient reported pain relief with a temporary electrode to proceed with a permanent implant), and 2) long-term outcome of treatment with the permanent implant, as determined by disinterested third-party interview. RESULTS: Significant associations (P < or = 0.01) were observed between the outcome of the therapeutic trial of stimulation and psychological test results; patients with low "anxiety" scores on the Derogatis Affects Balance Scale and with high "organic symptoms" scores on the Wiggins test were significantly more likely to proceed to permanent implants, as determined by multivariate statistical models. There was an elevation in the Minnesota Multiphasic Personality Inventory hypochondriasis scale in these patients by univariate (P = 0.02), but not by multivariate, models. The multivariate model also identified young age, reproduction of leg pain by straight leg raising, and bilateral leg pain as favorable prognostic factors. The only association with favorable long-term outcome of implantation of a permanent device, by univariate analysis, was an elevated "joy" score on the Derogatis Affects Balance Scale. Multivariate analysis revealed no statistically significant predictors of long-term outcome. CONCLUSION: Because our study population was selected on the basis of recognized prognostic factors and long clinical experience, it may not be possible to generalize our findings to the overall pain clinic referral population. In the subpopulation we have chosen for SCS trials, psychological testing is of modest value and explains little of the observed variance in outcome. We find little evidence for selecting patients for SCS on the basis of psychological testing. Because self-reported outcome measures may themselves reflect the patient's psychological state, these findings should be considered carefully, in overall clinical context. A prospective study with additional objective outcome measures is underway, which will address some of these issues.

Adaptation, Psychological↗
PubMed2007

Monitoring diet effects via biofluids and their implications for metabolomics studies.

The effect of diet on metabolites found in rat urine samples has been investigated using nuclear magnetic resonance (NMR) and a new ambient ionization mass spectrometry experiment, extractive electrospray ionization mass spectrometry (EESI-MS). Urine samples from rats with three different dietary regimens were readily distinguished using multivariate statistical analysis on metabolites detected by NMR and MS. To observe the effect of diet on metabolic pathways, metabolites related to specific pathways were also investigated using multivariate statistical analysis. Discrimination is increased by making observations on restricted compound sets. Changes in diet at 24-h intervals led to predictable changes in the spectral data. Principal component analysis was used to separate the rats into groups according to their different dietary regimens using the full NMR, EESI-MS data or restricted sets of peaks in the mass spectra corresponding only to metabolites found in the urea cycle and metabolism of amino groups pathway. By contrast, multivariate analysis of variance from the score plots showed that metabolites of purine metabolism obscure the classification relative to the full metabolite set. These results suggest that it may be possible to reduce the number of statistical variables used by monitoring the biochemical variability of particular pathways. It should also be possible by this procedure to reduce the effect of diet in the biofluid samples for such purposes as disease detection.

Alloxan↗
PubMed2004

Standardless PIXE analysis of thick biomineral structures.

The particle-induced X-ray emission (PIXE) of thick biomineral targets provides pertinent surface analysis, but if good reference materials are missing then complementary approaches are required to handle the matrix effects. This is illustrated by our results from qualitative and semiquantitative analysis of biomaterials and calcified tissues in which PIXE usually detected up to 20 elements with Z > 14 per sample, many at trace levels. Relative concentrations allow the classification of dental composites according to the mean Z and by multivariate statistics. In femur bones from streptozotocin-induced diabetic rats, trace element changes showed high individual variability but correlated to each other, and multivariate statistics improved discrimination of abnormal pathology. Changes on the in vitro demineralization of dental enamel suggested that a dissolution of Ca compounds in the outermost layer results in the uncovering of deeper layers containing higher trace element levels. Thus, in spite of significant limitations, standardless PIXE analysis of thick biomineral samples together with proper additional procedures can provide relevant information in biomedical research.

Animals↗
PubMedDate not supplied

Estimating the accident potential of an Ontario driver.

To run a "demerit point" program, one uses routinely available information about drivers to identify those who are most likely to have an accident in the near future. On the basis of a four-year record for a large sample of Ontario drivers, we have examined several tools for the identification of such drivers and investigated how they perform. Each driver is thought to have an expected number of accidents, m. In a group of drivers with common traits (such as age, gender, record of convictions and accidents) the ms have a mean E(m) and a variance VAR(m). Estimates of E(m) and VAR(m) for all combinations of traits can be obtained within the framework of a multivariate statistical model. The same estimates can then be used to judge how well a model identifies drivers who have a large m. In such a multivariate model it is important to use data about previous accidents and convictions. However, the accuracy with which the m of a driver can be estimated is not improved much by distinguishing between offence type or between accidents as being "at fault" or "not at fault". Without much loss in estimation accuracy, one may attach a weight 1 to a conviction and 2 to an accident. Model performance is described in tangible terms: how many accidents are recorded by the drivers identified by a model, what proportion of identified drivers are "false positives," how many drivers with high m remain unidentified. We conclude that by using a multivariate statistical model one can do substantially better than by using a demerit point scheme in which points are assigned to offenses on the basis of their perceived seriousness. However, even when the best model is used to identify a large group of drivers, many will be false positives.

Accidents, Traffic↗
PubMed2006

Noninvasive diagnostic assessment of brain tumors using combined in vivo MR imaging and spectroscopy.

To determine the potential value of multimodal MRI for the presurgical management of patients with brain tumors, we performed combined magnetic resonance imaging (MRI) and proton MR spectroscopy (MRS) in 164 patients who presented with tumors of various histological subtypes confirmed by surgical biopsy. Univariate statistical analysis of metabolic ratios carried out on the first 121 patients demonstrated significant differences in between-group comparisons, but failed to provide sufficiently robust classification of individual cases. However, a multivariate statistical approach correctly classified the tumors using linear discriminant analysis (LDA) of combined MRI and MRS data. After initial separation of contrast-enhancing and non-contrast-enhancing lesions, 91% of the former and 87% of the latter were correctly classified. The results were stable when this diagnostic strategy was tested on the additional 43 patients included for validation after the initial statistical analysis, with over 90% of correct classification. Combined MRI and MRS had superior diagnostic value compared to MRS alone, especially in the contrast-enhancing group. This study shows the clinical value of a multivariate statistical analysis based on multimodal MRI and MRS for the noninvasive evaluation of intracranial tumors.

Artificial Intelligence↗