PubMed Health⌕ Search

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 1,099 records · Page 61Linked to original sources
PubMed1995

Factors associated with sexual behavior among adolescents: a multivariate analysis.

Multiple factors associated with engaging in sexual intercourse among a sample of adolescents were examined. A self-administered survey was completed by 1,026 high school students in a classroom setting. Discriminant function analyses were performed to discriminate factors most important in predicting the sexual status of the adolescent. Compared to males who had never engaged in sexual intercourse, sexually active males reported more frequent use of alcohol, had higher levels of stress, were less likely to use seat belts, were more likely to engage in physical fights, and were more likely to worry about the spread of AIDS. Sexually active females reported more frequent use of alcohol and cigarettes, and had higher levels of stress than did female adolescents who had never had sexual intercourse. These findings suggest that effective interventions to address teenage pregnancy need to utilize a multifaceted approach to the prevention of high-risk behaviors.

Adolescent↗
PubMed1989

A multivariate analysis of determinants of survival for patients with squamous cell carcinoma of the head and neck.

The prognosis for patients with squamous cell carcinoma of the head and neck remains poor, despite refinements in conventional therapy and experimental protocols using alternative treatment modalities. Clinical characteristics reported to influence survival have included age and sex of the patient, the therapy used, location of the primary tumor, and stage at initial presentation. However, such variables are highly correlated, and previous reports have lacked sufficient statistical analysis to assess the independent influence of these competing variables on survival. To better define the principal determinants of survival, we used a Cox multivariate regression analysis of 542 patients with invasive squamous cell carcinoma of the head and neck treated exclusively at our institution from 1962 to 1976. All patients were followed for a minimum of 5 years after diagnosis, with 98% complete follow-up achieved. Stage at initial presentation was the single-most important factor influencing survival for all tumor locations (p less than 0.0001). Advanced age (p = 0.001) and location of the primary tumor in the tonsillar area (p = 0.01) were also independently associated with an inferior survival. The type of therapy used and sex of the patient did not significantly influence survival after controlling for stage. These data emphasize the need for early diagnosis and treatment of squamous cell carcinoma of the head and neck and underscore the limitations of current therapeutic approaches. Future investigations should incorporate multivariate statistical techniques whenever possible, and additional efforts must be directed at basic research into the biology and immunologic characteristics of these tumors in an attempt to identify innovative therapeutic modalities.

Adult↗
PubMed1977

Multivariate analysis of gametic disequilibrium in the Yanomama.

The gametic disequilibria between all possible pairs of loci were examined for a set of eight codominant loci in each of fifty Yanomama villages, using a multivariate correlation analysis which reduces the results to a single measure of departure from multiple-locus-gametic equilibrium. Thirty-two of the fifty villages departed significantly from multiple-locus gametic equilibrium. The largest contributions to the departure from multiple-locus equilibrium were due to the disequilibria between MN and Ss and between Rh(Cc) and Rh(Ee), indicating the effects of tight linkage. After removing the effects of these obvious sources of disequilibrium, sixteen of the fifty villages still remained significantly out of equilibrium. The disequilibrium between any particular pair of loci was highly erratic from village to village, and (with the exception of the MN-Ss and Cc-Ee disequilibria) averaged out very close to zero overall, suggesting a lack of systematic forces (epistatic selection). The departure from equilibrium in any one village is in excess of that expected from random sampling alone, and is attributed primarily to the fission-fusion mode of village formation operative in the Yanomama and the fact that a single village consists of a few extended lineages. Village allele frequencies are highly correlated across loci, and most of the non-independence is accounted for by large correlations in the average allelic frequencies of different loci for related villages. It is suggested that these correlations also are due to territorial expansion and population growth. For the tribe as a whole, all but the tightly linked markers of the MNSs and Rh complexes are approximately uncorrelated, and large departures from multiple-locus Hardy-Weinberg expectation are primarily due to substantial Wahlund variance within the tribe. There is no need to postulate a role for selection in these disequilibria.

Alleles↗
PubMed1995

Prognostic indicators following enucleation for posterior uveal melanoma. A multivariate analysis of long-term survival with minimized loss to follow-up.

Most previous reports on survival following enucleation for uveal malignant melanoma do not contain cumulative survival rates, do not use a multivariate approach and are liable to a considerable loss to follow-up. In this study, the long-term survival and tumour-related mortality were studied in 340 patients. Archival specimens containing posterior uveal melanomas were initially examined and sectioned by one pathologist. There was no loss to follow-up 6 to 22 years after enucleation. At the end of study, 233 (68.5%) individuals were dead; 137 (40.3%) of melanoma-related causes and 96 (28.2%) of other causes. Melanoma-related deaths appeared from 24 to 6848 days (18 years 8 months) after enucleation. The cumulative 5-year survival proportion based on melanoma-related deaths was 70% and the corresponding 10-year proportion was 56%. Multivariate Cox regression indicated that the largest tumour dimension, cell type, and tumour location all had independent prognostic value, the associated hazard ratios ranged from 1.2 to 1.4, suggesting a moderate increase of the relative risk. Pair-wise comparisons of the parameters indicated that large tumours were more common in the anterior choroid or ciliary body than in the posterior choroid. Similarly, large tumours were more often necrotic, composed of epitheloid cells, or featured extrascleral extension. Tumours with significant scleral invasion or extrascleral extension were more common in elderly patients.

Adult↗
PubMed1978

Enrollment choices in different types of HMOs: a multivariate analysis.

Enrollment decisions of a sample of an employed population choosing among open-panel and closed-panel HMOs and Blue Cross/Blue Shield are analyzed. This report, unlike previous ones, overcomes some of the difficulties of bivariate analysis by the use of the multivariate logistic probability model, logit. The results show that there are four consistent predictors of enrollment choice: previous source of care as the measure of access; family life stage and chronic conditions per family member as indicators of health risk; per capita income as the measure of economic vulnerability; and health concern. Having a private physician as the source of care is the best single predictor, its absence predicting a higher probability of enrollment in the closed, and its presence in the open-panel HMO. Higher risk life stage families, younger and with more children, are more likely to join the open-panel plan than the closed or retain BC/BS; higher incomes and larger numbers of chronic conditions appear to have the same effects. Higher levels of health concern, on the other hand, predict a greater probability of choosing the closed-panel plan. The probability of enrollment in any HMO is predicted with more than 50 per cent accuracy for 60 per cent of the sample. Choice between open and closed-panel plans is predicted with an accuracy in excess of 50 per cent for 80 per cent, and with an accuracy greater than 90 per cent for over 10 per cent of potential enrollees. The applicability of this approach to HMO feasibility analysis and planning is clearly indicated.

Analysis of Variance↗
PubMed2006

Complications of cerebral arteriovenous malformation embolization: multivariate analysis of predictive factors.

OBJECTIVE: Embolization is an important therapeutic modality in the multidisciplinary management of arteriovenous malformations (AVM); however, prior series have reported a wide variability in overall complication rates caused by embolization (10-50% neurological deficit, 1-4% mortality). In this study, we reviewed our experience with AVM embolization and analyzed factors that might predict complications and clinical outcomes after AVM embolization. METHODS: We analyzed our combined neurovascular unit's results with AVM embolization from 1993 to 2004 for the following outcomes measures: 1) clinically significant complications, 2) technical complications without clinical sequelae, 3) discharge Glasgow Outcome Scale score, and 4) death. To determine embolization efficacy, we analyzed perioperative blood transfusion and rate of AVM obliteration. Univariate and multivariate analyses were performed for patient age, sex, history of rupture, history of seizure, associated aneurysms, AVM size, deep venous drainage, eloquent location, Spetzler-Martin grade, number of embolization stages, number of pedicles embolized, and primary treatment modality. RESULTS: Over an 11 year period, 295 embolization procedures (761 pedicles embolized) were performed in 168 patients with embolization as the primary treatment modality (n = 16) or as an adjunct to surgery (n = 124) or radiosurgery (n = 28). There were a total of 27 complications in this series, of which 11 were clinically significant (6.5% of patients, 3.7% per procedure), and 16 were technical complications (9.5% of patients, 5.4% per procedure). Excellent or good outcomes (Glasgow Outcome Scale > or = 4) were observed in 152 (90.5%) patients. Unfavorable outcomes (Glasgow Outcome Scale 1-3) as a direct result of embolization were both 3.0% at discharge and at follow-up, with a 1.2% embolization-related mortality. In the 124 surgical patients, 96.8% had complete AVM obliteration after initial resection, and 31% received perioperative transfusion (mean 1.4 units packed red blood cells per surgical patient). Predictors of unfavorable outcome caused by embolization by univariate analysis were deep venous drainage (P < 0.05), Spetzler-Martin Grade III to V (P < 0.05), and periprocedural hemorrhage (P < 0.0001) and by multivariate analysis were Spetzler-Martin III to V (odds ratio 10.6, P = 0.03) and periprocedural hemorrhage (odds ratio 17, P = 0.004). CONCLUSION: In a single-center, retrospective, nonrandomized study, 90.5% of patients had excellent or good outcomes after AVM embolization, with a complication rate lower than previously reported. Spetzler-Martin grade III to V and periprocedural hemorrhage were the most important predictive factors in determining outcome after embolization.

Adolescent↗
PubMedDate not supplied

Gallbladder opacification 12-24 h after angiography by CT examination: a multivariate analysis.

BACKGROUND: To examine the incidence and predisposing factors of gallbladder opacification in delayed computed tomography (CT) after angiography. METHODS: CT examination 12-24 h after angiography was performed in 389 patients. Univariate and multivariate analyses were made. RESULTS: Two hundred thirty-three of 389 patients (60%) revealed gallbladder opacification. Type of contrast medium (P < 0. 01), total bilirubin (P < 0.01), and serum creatinine (P < 0.01) were significant and independent factors relating to gallbladder opacification. Ioxaglate (70%, relative odds = 2.86) and iohexol (63%, relative odds = 2.03) showed higher gallbladder opacification rates than that of iopamidol (45%, relative odds = 1.43) and diatrizoate (30%). Patients with a lower serum bilirubin level (relative odds = 1.67) and a raised serum creatinine level (relative odds = 2.01) showed higher incidence of gallbladder opacification. CONCLUSION: Gallbladder opacification after angiography is not an abnormal finding on delayed CT in patients with not only abnormal renal function but also normal hepatobiliary and normal renal function, especially for modern contrast media.

Angiography↗
PubMed1991

Factors affecting the patency of stents in malignant biliary obstructive disease: univariate and multivariate analysis.

To investigate the factors affecting the patency of biliary stents, we performed univariate and multivariate analyses in 370 straight stents with diameters of 10- to 12-French gauge which had been inserted singly as palliative treatment in 228 patients with malignant biliary obstructive disease. In the analysis of 226 first stents, advanced age of patients and higher serum bilirubin levels before insertion were found to be significant unfavorable factors limiting the duration of stent function. Overall, older age, male sex, no stent cleaning, and insertion on three or more occasions were significant unfavorable prognostic factors for patency. The risk of occlusion for stents inserted on three or more occasions was 2.32 times that of the first stent insertion. The median duration of patency of first, second, and subsequent stents was 177, 98, and 97 days, respectively. Diagnosis and the area of stenosis were unrelated to patency. No predictive significance of length or size of stent between 10- and 12-French gauge was found in our study.

Actuarial Analysis↗
PubMed1979

[Original method of multivariate analysis, adapted for comparison of mean evoked potentials: E2 test].

This paper describes a multivariate statistical method of analysis for the comparison of 2 paired series. For such paired series, this test, called E2, is analogous to the generalized Hotteling T2 test, as epsilon test (pairing method) is analogous to Student's t test. Here we give an example of its application to a comparison of curves, in this particular case average auditory evoked potentials, picked up at symmetrical points on the scalp.

Acoustic Stimulation↗
PubMedDate not supplied

Genetic and environmental components of adolescent adjustment and parental behavior: a multivariate analysis.

Adolescent adjustment measures may be related to each other and to the social environment in various ways. Are these relationships similar in genetic and environmental sources of covariation, or different? A multivariate behavior-genetic analysis was made of 6 adjustment and 3 treatment composites from the study Nonshared Environment in Adolescent Development, using 674 same-sex adolescent sibling pairs aged 9-11. Cholesky decompositions of the total covariance matrix yielded additive and nonadditive genetic, and shared and nonshared environmental matrices. Factor analyses led to 3 factors for all but shared environment. The first 2 factors resembled Neuroticism and Extraversion factors typically found for personality; the third factor, parental monitoring and control, appeared to have different associations in different matrices.

Adolescent↗