SEARCH · PubMed Health

Results for “Multivariate 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 1,621 records · Page 90Linked to original sources

PubMed2005

Safety and effectiveness of olanzapine in monotherapy: a multivariate analysis of a naturalistic study.

BACKGROUND: This study investigated safety and effectiveness of olanzapine in monotherapy compared with conventional antipsychotics in treatment of acute inpatients with schizophrenia. METHOD: This was a prospective, comparative, nonrandomized, open-label, multisite, observational study of Spanish inpatients with an acute episode of schizophrenia. Data included safety assessments with an extrapyramidal symptoms (EPS) questionnaire and the report of spontaneous adverse events, plus clinical assessments with the Brief Psychiatric Rating Scale (BPRS) and the Clinical Global Impressions-Severity of Illness (CGI-S). A multivariate methodology was used to more adequately determine which factors can influence safety and effectiveness of olanzapine in monotherapy. RESULTS: 339 patients treated with olanzapine in monotherapy (OGm) and 385 patients treated with conventional antipsychotics (CG) were included in the analysis. Treatment-emergent EPS were significantly higher in the CG (p<0.0001). Response rate was significantly higher in the OGm (p=0.005). Logistic regression analyses revealed that the only variable significantly correlated with treatment-emergent EPS and clinical response was treatment strategy, with patients in OGm having 1.5 times the probability of obtaining a clinical response and patients in CG having 5 times the risk of developing EPS. CONCLUSION: In this naturalistic study olanzapine in monotherapy was better-tolerated and at least as effective as conventional antipsychotics.

Adult↗

PubMed1995

Nursing home residents: a multivariate analysis of their medical, behavioral, psychosocial, and service use characteristics.

BACKGROUND: Elderly residents of nursing homes often have multiple comorbidities and functional limitations. The status of 4,525 residents of complex and standard care units in 177 nursing homes where the nursing home was determined to provide adequate care, and from 14 specialized Alzheimer's units, was evaluated on 111 measures of medical condition, functional status, psychological well-being and cognitive performance in a demonstration study assessing quality of care in six states. Detailed measurements were also made of the types and amounts of services used (in minutes per day) by the residents. METHODS: Given the number of health measures, and the possibility of assessment error, a multivariate analytic procedure called Grade of Membership (GoM) was used. This procedure identified profiles of health and functioning measures to identify the characteristics of clinically distinct groups of nursing home residents. RESULTS: The analysis identified 11 profiles of health and functioning characteristics which described the 111 resident measurements. The 11 profiles predicted differentials in nursing home length of stay, and service use by various classes of caregivers. The GoM profiles described the data better than several other classification procedures applied to the same data. CONCLUSIONS: In nursing homes, elderly and oldest-old residents often have multiple comorbidities and disabilities. A multivariate procedure was able to identify the fundamental dimensions describing residents' variation on a number of health measures. These profiles predicted differences in service use so they had predictive validity. Thus, multivariate procedures may help identify clinically distinct groups in studies where complex measures are made.

Aged↗

PubMed1988

Multivariate analysis of putative measures of activity, exploration, emotionality, and spatial behavior in the hooded rat (Rattus norvegicus).

Hooded rats were tested in six situations representing the variables of activity, exploration, emotionality, and spatial preference, detection of change, and learning. The activity, exploration, and emotionality variables and spatial variables were analyzed in separate multivariate analyses, followed by an analysis of the entire set. The first of these resulted in four components: activity, exploration and emotionality, reactivity to handling, and autonomic reactivity (defecation). Four components, defined by the following variables, emerged from the spatial analysis: (a) the tendency to circle, circling direction, and spatial learning; (b) heading error in spatial learning and reversal and open-field directional preference; (c) spatial reversal and direction of turn to escape restraint; and (d) detection of change in spatial arrangement and directional preference in the detection task. The final analysis investigated relations between the activity, exploration, and emotionality variables and the spatial variables, finding only two. The clear dimensionality of these behavioral repertoires emphasizes how important it is to recognize the distinctions among them.

Animals↗

PubMed1997

Multivariate analysis of occult lymph node metastasis as a prognostic indicator for patients with squamous cell carcinoma of the oral cavity.

BACKGROUND: The biologic aggressiveness of squamous cell carcinoma of the oral cavity is reflected in its ability to metastasize to regional cervical lymph nodes. Patients with clinically negative cervical lymph nodes are believed to have a good prognosis; however, the prognosis of patients with lymph node metastasis occurring after excision or radiotherapy of the primary tumor is poor. METHODS: Univariate and multivariate analyses for occult lymph node metastasis (ONM) in 172 patients with clinically negative cervical lymph nodes were performed by the authors to elucidate the clinical and histologic tumor risk factors to enhance their ability to predict ONM. A multivariate Cox proportional hazards model and Hayashi's quantification theory type II were used to analyze prognostic factors and to determine the probability of ONM. RESULTS: Using Cox's proportional regression model, the factors linked to cancer specific survival were selected: tumor differentiation (P = 0.0330), mode of carcinoma invasion (P = 0.0175), and ONM (P = 0.0433). Pathologically identified metastatic lymph nodes were found in 21.5% of the cases studied (37 of 172 cases). The 5-year cancer specific survival was 94.0% for patients without lymph node metastasis, and 51.0% for patients with ONM (P < 0.0001, log rank test). The most significant predictors for ONM of each of the clinical and histologic factors, in descending order, were: mode of carcinoma invasion, intensity of lymphocytic infiltration, degree of differentiation, number of mitotic figures, and type of growth by means of Hayashi's quantification theory type II. The presence or absence of ONM in 147 of 172 patients (85.5%) was correctly predicted by the score at the point of intersection of the two curves, which was -0.03. Further investigation revealed that 28 of 32 new cases were differentiated accurately by means of this diagnostic system. CONCLUSIONS: The results of the current study suggest that this method of analysis can establish a reliable predictor of ONM, thereby facilitating correct choices for surgical procedures to enhance the survival rates of patients with clinically negative cervical lymph nodes.

Adult↗

PubMed1979

Multivariate analysis and quantitative structure-activity relationships. Inhibition of dihydrofolate reductase and thymidylate synthetase by quinazolines.

Quantitative structure-activity relationships (QSAR) have been established for the inhibition of dihydrofolate reductase and thymidylate synthetase by 2,4-diaminoquinazoline-glutamic acid analogues. For dihydrofolate reductase from both human acute lymphocytic leukemia cells and murine L1210R cells, QSAR's obtained with 50 quinazolines were similar. On the other hand, for the inhibition of thymidylate synthetase from murine L1210S cells and from Lactobacillus casei, QSAR's formulated on the basis of data measured with 33 compounds were different, indicating that the two enzymes are dissimilar. The use of multivariate statistics including cluster analysis, factor analysis, and discriminant analysis is shown to facilitate the formulation of a satisfactory correlation equation. The procedure is demonstrated by the development of QSAR for the inhibition of thymidylate synthetase.

Analysis of Variance↗

PubMed1995

Prediction of residual retroperitoneal mass histology after chemotherapy for metastatic nonseminomatous germ cell tumor: multivariate analysis of individual patient data from six study groups.

PURPOSE: To develop a statistical model that predicts the histology (necrosis, mature teratoma, or cancer) after chemotherapy for metastatic nonseminomatous germ cell tumor (NSGCT). PATIENTS AND METHODS: An international data set was collected comprising individual patient data from six study groups. Logistic regression analysis was used to estimate the probability of necrosis and the ratio of cancer and mature teratoma. RESULTS: Of 556 patients, 250 (45%) had necrosis at resection, 236 (42%) had mature teratoma, and 70 (13%) had cancer. Predictors of necrosis were the absence of teratoma elements in the primary tumor, prechemotherapy normal alfa-fetoprotein (AFP), normal human chorionic gonadotropin (HCG), and elevated lactate dehydrogenase (LDH) levels, a small prechemotherapy or postchemotherapy mass, and a large shrinkage of the mass during chemotherapy. Multivariate combination of predictors yielded reliable models (goodness-of-fit tests, P > .20), which discriminated necrosis well from other histologies (area under the receiver operating characteristic (ROC) curve, .84), but which discriminated cancer only reasonably from mature teratoma (area, .66). Internal and external validation confirmed these findings. CONCLUSION: The validated models estimate with high accuracy the histology at resection, especially necrosis, based on well-known and readily available predictors. The predicted probabilities may help to choose between immediate resection of a residual mass or follow-up, taking into account the expected benefits and risks of resection, feasibility of frequent follow-up, the financial costs, and the patient's individual preferences.

Analysis of Variance↗

PubMed1986

Sample sizes in the multivariate analysis of repeated measurements.

Determination of sample sizes for comparing two or more treatments in repeated measurements experiments is considered. Multivariate normality of the individual's vector of repeated measures is assumed. Particular emphasis is placed on applications wherein the error variance-covariance matrix is arbitrary positive-definite. Sample size determination is based on power considerations associated with Hotelling's T2 test and the desire to detect a specified difference between any pair of treatment means. Tabulated sample sizes are given in the case of an equal variance-unequal covariance structure. The utility of these sample sizes is also demonstrated for a more general variance-covariance structure. Applications of these sample sizes are illustrated with two examples.

Analysis of Variance↗

PubMedDate not supplied

Prognostic factors of papillary, follicular and medullary carcinomas of the thyroid gland. Retrospective multivariate analysis of 216 patients with a median follow-up of 11 years.

Various prognostic factors have been tested in multivariate analyses of 216 patients with papillary, follicular or medullary thyroid carcinomas without initial distant metastases. The median follow-up time was 11 years. The patient's sex was not found to be a significant predictor. Age at diagnosis seemed to be an important predictor for papillary as well as for follicular carcinomas, but when deaths in intercurrent disease were estimated, marked cellular atypia and tumour invasion beyond the thyroid capsule proved to be more important predictors. For medullary carcinomas tumour invasion beyond the thyroid capsule was the only significant predictor.

Adenocarcinoma↗

PubMed1994

[Multivariate analysis on prognostic factors for acute myocardial infarction during acute period noncondition stepwise logistic model].

The relationship between baseline factors defined at 4.3 +/- 1.8 hr after onset of acute myocardial infarction and 28-day survival in 319 patients admitted into the China Medical University was evaluated. The case fatality rate during acute period was 17.9%. Univariate statistics identified a significant relationship between 5 of these factors and survival. Multivariate noncondition stepwise logistic model analysis identified four factors as being most closely related to survival: (1) heart failure; (2) arrhythmia; (3) age; (4) history of essential hypertension. It is concluded that heart failure during the acute period of acute myocardial infarction is the most important baseline factor for prediction of 28-day survival.

Aged↗

PubMed1983

Multivariate analysis of pacemaker patient survivorship.

Multiple risk factors of patient mortality need to be evaluated and combined to serve practical purposes. A multivariate statistical model is illustrated here with a large data set and a simulated example. The piecewise parametric model is shown to be simple, efficient, and is suggested to be a good tool for routine usage. The approach should provide a more concise characterization of mortality in terms of multiple risk factors. The results of data analysis also provide a good reference for further explorations.

Actuarial Analysis↗

PubMed1996

Prognostic factors for patients with localized primary malignant fibrous histiocytoma: a multicenter study of 216 patients with multivariate analysis.

BACKGROUND: The purpose of this study was to determine the independent prognostic variables in a well documented subset of 216 patients with localized primary malignant fibrous histiocytomas (MFH). METHODS: Between the years 1980 and 1989, 216 patients with localized, primary (International Union Against Cancer [UICC]/American Joint Committee on Cancer [AJCC] Stage I-IVA) MFH were evaluated and treated in 10 participating centers of the sarcoma group of the French Federation of Cancer Centers (FNCLCC). Clinicopathologic factors were collected retrospectively and entered into a cooperative database. Tissue slides of all cases were jointly reviewed microscopically by the pathology subcommittee. Surgical treatment was performed on all but 6 (3%) patients. One hundred ninety-five patients (90%) were free of gross disease, with complete local control at the end of the initial treatment. The adjuvant treatment was radiotherapy in 78 patients (36%), chemotherapy in 19 patients (9%), and both in 61 patients (28%). RESULTS: The median follow-up was 3.5 years (range, 45 days to 12 years). Five-year actuarial rates of disease specific (DSS), metastasis free (MFS), and local recurrence free (LRFS) survival were 70%, 63.3%, and 62.7%, respectively. Multivariate analyses showed that the adverse prognostic factors independently associated with decreased disease specific survival were UICC/AJC Stage III + IVA (P < 0.00001; relative risk [RR], 3.27; 95% confidence interval [CI], 1.6-6.58), residual macroscopic disease following primary local therapy (P = 0.00024; RR, 3.99, CI, 2.04-7.82), deep tumor location (P = 0.0045; RR, 3.37; CI, 1.21-9.38), non-myxoid histology (P = 0.0056; RR, 9.28; CI, 1.03-83.41), and age older than 50 years (P = 0.037; RR, 2.19; CI, 1.04-4.61). Two factors were significantly related to MFS in the patients with the poorest prognosis: histopathologic Grade 3 (P < 0.0001, RR, 3.46; CI, 2.02-5.91) and tumor size greater than 8 cm in largest dimension (P = 0.0012; RR, 2.78; CI, 1.36-3.66). With regard to LRFS, patients who did not undergo radiotherapy had reduced local control (P = 0.0043; RR, 2.36; CI, 1.46-3.83). CONCLUSIONS: Resection of all macroscopic disease was independently associated with improved disease specific survival and adjuvant radiotherapy significantly decreased the local relapse risk. Histopathologic grade was the most important prognostic factor for DSS and MFS.

Actuarial Analysis↗

PubMedDate not supplied

Moors and Christians: an example of multivariate analysis applied to human blood-groups.

Published data on the frequencies of the alleles of the ABO, MNS, and Rh systems for populations in the western Mediterranean region are analysed by the multivariate statistical methods of canonical variates, principal components, principal coordinates, correspondence analysis and discriminant functions. It is shown that there is a 'Moorish substrate' in the eastern and north-eastern parts of Spain and in southern Portugal. Serological effects, such as could derive from the assimilation of a large Jewish population, cannot be identified in the data available. The theory that most Hispano-Moslems and Spanish Jews were of indigenous origin is not gainsaid by the serological data available.

ABO Blood-Group System↗

PubMed1981

The relation of personality characteristics to body image disturbances in juvenile anorexia nervosa: a multivariate analysis.

The relationship between Minnesota Multiphasic Personality Inventory (MMPI) factors and two separate measures of body image-estimation of body size and subjective report of distorted bodily experiences-was investigated using multivariate analyses in adolescent females with anorexia nervosa. A canonical correlational analysis of these data indicated the presence of two orthogonal dimensions defining the relation between personality and body image scores. In the first canonical variate, size overestimation and subjective body image distortion were both associated with MMPI scales reflecting somatization, anxiety, and atypical thinking; in the second variate, size overestimation alone was found to be associated with introversion and depression, while subjective body image distortion aligned with somatization and atypical thinking. The results suggest that different measures of body image disturbance are associated with different personality characteristics. Results are discussed in terms of the importance of personality factors in the pathogenesis of body image disturbances in anorexia nervosa.

Adolescent↗

PubMed2000

Carcinoma of the splenic flexure: multivariate analysis of predictive factors for clinicopathological characteristics and outcome after surgery.

The clinicopathological characteristics and outcome of splenic flexure cancer after surgery have yet to be fully elucidated. The aim of the current study was, therefore, to establish predictive factors related to splenic flexure cancer and outcome after surgery. We compared the clinicopathological characteristics and outcome of 34 patients with splenic flexure cancers (which represents 3.7% of the total number of colon cancers in our series) with those of 418 patients with right colon and 475 patients with left colon cancers by univariate and multivariate analyses, using logistic regression analysis and Cox's proportional hazards model. Splenic flexure cancers had a high risk of obstruction (26.5% of patients), and had a more advanced stage and lower cure rate than left colon cancers. Logistic regression analysis revealed that two independent factors, colonic obstruction and the presence of distant metastases, were related to the splenic flexure tumor site. Splenic flexure cancer patients had a poorer outcome than those with left colon cancer (P = 0.0361). However, there was no difference in survival between patients with splenic flexure, those with right colon cancer and those with left colon cancer who underwent curative surgery. Cox's regression analysis revealed that neither the site of splenic flexure nor colonic obstruction was an independent prognostic factor. In conclusion, splenic flexure cancer is characterized by a high risk of obstruction and the presence of distant metastases. However, after curative resection, splenic flexure cancer has a similar outcome to colon cancer at other sites. In addition, neither the splenic flexure site nor colonic obstruction had an independent influence on patient survival after surgery.

Colonic Neoplasms↗

PubMed1983

[Multivariate analysis of beta activity in clinical material].

Beta activity, as described by a number of parameters extracted from the power spectra, was submitted to several multivariate statistical techniques in search of interpretable subgroups. The difficulties of doing this on heterogeneous clinical material, as well as various shortcomings of the usual cluster analytical techniques, are outlined. Where longitudinal data are available, the analysis of beta activity may help in monitoring the effects of the therapy. Generally, the large variability between individuals and many sources of errors related to the processes of data collection and parameter extraction indicate that much work remains to be done before even a rough and clinically relevant typology of beta activity will become available.

Adolescent↗

PubMed1981

A multivariate analysis of temporal change in Arikara craniometrics: a methodological approach.

We have examined temporal changes in the cranial architecture of Arikara Amerindians from five archaeological sites in South Dakota which span a time period of approximately 230 years (ca. A.D. 1600-1830). We have utilized a multivariate statistical method based on a principal components analysis of the pooled within-groups correlation matrix rather than the more traditional methods of ascertaining morphological relationships, e.g., discriminant functions, Mahalanobis' D2, or Penrose's Size and Shape. Our component structure, based on a regional sample and the mathematically simpler principal components analysis, is very similar to the factor structure obtained by Howells (1973) using a world-wide sample and factor analysis proper. This supports the notion of the "universality" of cranial structure. An axis of temporal variation was introduced into the component space by means of multiple regression. This analysis indicates that a substantial portion of the intergroup variation is temporal in nature and the systematic temporal changes occur along the facial height, transverse frontal flatness, and frontal profile flatness components. Earlier analyses of the same material by more conventional methods either did not detect the temporal trends at all or failed to isolate the specific nature of the temporal changes. The success of the present analysis attests to the value of examining morphological relationships be means of principal components.

Cephalometry↗

PubMed1987

A multivariate analysis of prognostic factors in chronic myelomonocytic leukaemia according to the FAB criteria.

In an attempt to characterize the prognostic significance of the main initial clinical, haematological and biochemical features of chronic myelomonocytic leukaemia according to the FAB criteria, 29 such patients were analysed by means of univariate and multivariate statistical methods. At the time of the analysis 21 patients had died, with a median survival for the overall series of 8.2 months. The univariate analysis identified three parameters associated with poor prognosis: high monocyte counts, low platelet counts and splenomegaly. When all the initial features were included in a multiple regression model, only high monocyte counts and spleen enlargement retained their unfavourable prognostic influence (P = 0.002 and P = 0.02, respectively). Based on the presence or not of these prognostic factors, two populations of patients with different survival (median survival 5.6 and 16.5 months, respectively, P less than 0.005) could be identified. It seems therefore that monocytic proliferation serves not only as the diagnostic marker for chronic myelomonocytic leukaemia but also as the most important feature in the assessment of the patient's prognosis.

Actuarial Analysis↗

PubMed1992

Dating violence, social learning theory, and gender: a multivariate analysis.

The study of violence between dating partners is a logical extension of interest in marital violence. However, little of this research tests explanations of intimate violence using multivariate techniques, and only recently have such tests occurred within a theoretical framework. Drawing on a recent social learning model of courtship violence (Riggs & O'Leary, 1989), this paper empirically examines constructs hypothesized to be predictive of the use of dating violence and investigates possible gender differences in the underlying causal structure of such violence. Logit analysis indicates that parent-child violence, drug use, and knowledge of use of dating violence by others predict the use of courtship violence by females. Belief that violence between intimates is justifiable, drug use, and parental divorce are related to perpetration of dating aggression by males. Explanations for these results and the importance of a multivariate approach to the problem are discussed.

Adolescent↗