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 775 records · Page 43Linked to original sources

PubMed1989

Clinical patch test data evaluated by multivariate analysis. Danish Contact Dermatitis Group.

The aim of the present study was to evaluate the influence of individual explanatory factors, such as sex, age, atopy, test time and presence of diseased skin, on clinical patch test results, by application of multivariate statistical analysis. The study population was 2166 consecutive patients patch tested with the standard series of the International Contact Dermatitis Research Group (ICDRG) by members of the Danish Contact Dermatitis Group (DCDG) over a period of 6 months. For the 8 test allergens most often found positive (nickel, fragrance-mix, cobalt, chromate, balsam of Peru, carba-mix, colophony, and formaldehyde), one or more individual factors were of significance for the risk of being sensitized, except for chromate and formaldehyde. It is concluded that patch test results can be compared only after stratification of the material or by multivariate analysis.

Adolescent↗

PubMed1993

Multivariate analysis of cholesterol distribution for monitoring the risk of coronary heart disease.

The screening of people for potential coronary heart disease and the monitoring of subjects considered at risk have been performed for some time by measuring total serum cholesterol and its constituent lipoproteins. However, these measurements vary substantially within subjects, making such assessments imprecise. It has been suggested that greater consistency can be achieved by analysing the joint distribution of the individual lipoproteins or of transformed variables derived from them. In this paper we present the results of a laboratory experiment to investigate these ideas with a view to improving current methods of monitoring patients at risk. Nested, random-effects, multivariate analysis of variance and the log-ratio analysis of compositions are used to include information on all three lipoproteins simultaneously, and ratios of generalized variances are used to assess and compare the different response variables. The multivariate approach is seen to be far superior to the usual methods. Recommendations are made for routine monitoring and the practical implications are discussed.

Analysis of Variance↗

PubMed1977

Multivariate analysis of the septal syndrome.

Since recent reviews of the behavioural effects of septal lesions agree that more than one explanatory concept is required, a multivariate analysis of the septal syndrome has been made. A total of 127 rats have been tested 73 with septal lesions and 54 controls. The rats were tested in a standard test battery consisting of a residential maze, spontaneous alternation, spatial learning, approach/avoidance conflict and one-way active avoidance. Factor analyses reveal a complex change in the factor structure after septal lesions. None of the previous explanations of septal functions receives unequivocal support. The findings do not exclude the possibility that septal lesions interfere with a few general behaviour mechanisms or perhaps only one. However, if so, this factor does not explain as much of the variance as expected. Situational or test-dependent factors play a greater role in the variance. This is interpreted as an indication of insufficiency in the theoretical structure, or in conventional test designs.

Animals↗

PubMed1976

Angina pectoris among 10,000 men. II. Psychosocial and other risk factors as evidenced by a multivariate analysis of a five year incidence study.

The major independent role played by anxiety and severe psychosocial problems (especially family ones) is demonstrated by this multivariate analysis of a five year prospective study of the development of new angina pectoris among almost 10,000 adult men (average annual incidence = 5.7/1,000). The independent effect of these two variables is considerably augmented by the other significant risk factors of age, total serum cholesterol, systolic or diastolic blood pressure, certain electrocardiographic abnormalities and diabetes mellitus. The presence of all seven risk factors (at a high level) increases the probability of angina pectoris developing within five years to 289/1,000 from 14/1,000, when these factors are low or absent. The wife's love and support is an important balancing factor, which apparently reduces the risk of angina pectoris even in the presence of high risk factors. The implications of these findings to the pathophysiology and prevention of angina are stressed.

Adult↗

PubMed1993

Spatial processing and emotionality in aged NMRI mice: a multivariate analysis.

The goal of this study was to investigate possible relationships between different aspects of behavioural decline in aged (17 months) NMRI mice by a multivariate analysis. These mice presented defects in spatial processing both in place learning in a Morris-type water maze and in spontaneous alternation in a Y-maze, as well as showing changes in their behaviour in the elevated plus maze test of fear/anxiety and open-field ambulation. Data were first factor analysed and then correlated on the basis of variable factor scores. The results showed clearly that age-related behavioural changes were independent of each other except between open-field activity measured over 6 min and spatial learning indices in the Morris-type water maze, in that mice performing poorly in the latter were more active in the open field, and between the ratio open/total arms visited in the elevated plus maze task and locomotor activity during the first 2 min of the open-field test. It is proposed that the notion of an allocentric or locale system cannot be applied unitarily to both spatial learning and spontaneous alternation defects, and that activity levels in the aged mice are task dependent and reflect different underlying factors.

Aging↗

PubMed1987

Functional and histopathologic correlation in patients with dilated cardiomyopathy: an integrated evaluation by multivariate analysis.

To correlate left ventricular function and histologic features in patients with dilated cardiomyopathy, precise indexes of hemodynamics and semiquantitative histologic data were combined for multivariate analysis. Right endomyocardial biopsy was performed at the time of cardiac catheterization. Five hemodynamic indexes were used for functional assessment: ejection fraction, ratio of end-systolic stress to volume index, end-diastolic stress, time constant (T) of left ventricular pressure fall, and end-systolic stress. Six histologic findings (disarray of myofibers, hypertrophy of myofibers, scarcity of myofibrils, nuclear changes of myofibers, vacuolization of myofibers and proliferation of collagen fibers) were graded from (-) to (4+). Each finding was assigned to category (-) or (+) according to the absence or presence of significant abnormality. Ordinary statistical analysis revealed that, although ejection fraction was lower in category (+) for proliferation of collagen fibers, ratio of end-systolic to volume index was reduced for category (+) of hypertrophy of myofibers. A significant correlation was present between hypertrophy of myofibers and proliferation of collagen fibers by Spearman rank correlation. When principal component analysis was applied to the hemodynamic data, two principal components could be extracted. Fisher's discriminant analysis could clearly differentiate two categories (-) and (+) in the semiquantitative histologic finding of proliferation of collagen fibers. The analysis indicated that contractility was reduced with elevated afterload in that category (+). Thus, proliferation of collagen fibers may play a pivotal role in deteriorating contractility in patients with dilated cardiomyopathy.

Cardiomyopathy, Dilated↗

PubMed1983

The use of multivariate analysis of variance in physiological research: the two-group case.

The advantages of performing simultaneous inferences on the means of several response variables using multivariate analysis of variance are discussed. They include control over the problem of declaring false significant differences and the ability to investigate the effects of treatment on a given response variable after eliminating variations due to other response variables. Computational equivalencies with multiple linear regression in the two-group case are also discussed.

Analysis of Variance↗

PubMed1986

Determinants of survival after intraarterial infusion of 5-fluorouracil for liver metastases from colorectal cancer: a multivariate analysis.

A consecutive series of 73 patients treated with intraarterial infusion of 5-fluorouracil (5-FU) for liver metastases from colorectal primary was studied retrospectively using multivariate analysis in order to find determinants of survival. Nontreatment factors had a great impact on variation in survival with liver tumor volume and metastases to lymph glands in the liver hilum as major prognostic determinants. In addition, survival from onset of treatment varied with the interval between the primary operation and the diagnosis of liver metastases. Treatment with intraarterial 5-FU was more effective when administered at long-term (3 months every 6 months) than at short-term (5 days every 6 weeks). Single temporary dearterialization, used as an adjunct to infusion of 5-FU, had a negative impact on length of survival and was followed by a high frequency of complications. The occurrence of hepatic arterial thrombosis was associated with comparatively good prognosis.

Adult↗

PubMed1984

Comparison of the multivariate analysis and CADENZA systems for determination of the probability of coronary artery disease.

The accuracy of 2 discriminate systems for diagnosis of coronary artery disease (CAD), multivariate analysis (MVA) and Bayesian analysis (CADENZA), was evaluated in 113 patients undergoing electrocardiographic stress testing and coronary angiography. MVA uses weighting factors (F values) generated from our patient data, whereas CADENZA uses probabilities gleaned from an extensive review of the American literature. Overall accuracy was similar. MVA had a higher sensitivity for 1-vessel CAD (75 versus 33%), but CADENZA was better for determining the severity of CAD. The 2 systems provided posterior probabilities for disease that were highly correlated (r = 0.56; p less than 0.001). Both systems suggest the need for further testing based on the probability generated; herein lies their major strength. The application of such systems should help the clinician reach a diagnosis or make a decision as to management in a cost-effective manner.

Bayes Theorem↗

PubMed1994

Pathologic determinants of survival associated with colorectal cancer with lymph node metastases. A multivariate analysis of 579 patients.

BACKGROUND: Patients with colorectal carcinoma found to have regional lymph node metastases after curative resection form a large and prognostically diverse group. This study aims to determine which pathology variables have independent prognostic effects. METHODS: The data from the 579 patients used in this analysis were collected prospectively during a period of 21.5 years. The patients were from one institution, and the pathologic documentation was standardized. Patient follow-up ranged between 6 months and 21.5 years. Survival analysis was by the Kaplan-Meier method. Multivariate models were examined using Cox proportional hazards regression. RESULTS: On univariate analysis, eight pathology variables had a significant association with survival. Six of these variables showed significant independent effects on survival on multivariate analysis. In diminishing potency, these variables were: apical lymph node involvement; spread involving a free serosal surface; invasion beyond the muscularis propria; location in the rectum; venous invasion; high tumor grade. Significant independent effects also were shown for patient age and gender. The number of involved lymph nodes added no significant independent prognostic information. CONCLUSION: Six pathology variables have been identified that act independently in determining the survival of patients with colorectal carcinoma and lymph node metastases. The most potent of these variables, apical lymph node involvement, was used by Dukes to subclassify Stage C tumors. Another variable, direct spread beyond the muscularis propria, defines the Astler-Coller subclassification. It is recommended that all six independent variables be included in any future protocol for stratifying this prognostically diverse group of patients.

Adult↗

PubMed1989

Famotidine therapy for active duodenal ulcers. A multivariate analysis of factors affecting early healing.

OBJECTIVE: To identify factors that influence the rate of healing of duodenal ulcers. DESIGN: A stepwise multivariable statistical analysis of patients with duodenal ulcer in a multicenter, prospective, open-label study. Healing was assessed by endoscopy at 4 or 8 weeks. Antacid use and symptoms were recorded in a daily diary. SUBJECTS: Of 135 patients, ages 19 to 86, 50% had a previous duodenal ulcer, 46.7% smoked, and 34.8% had melena or hematemesis. INTERVENTIONS: Famotidine, 40 mg orally, at bedtime for 4 or 8 weeks depending on endoscopic evaluation of ulcer healing. Limited antacid use was permitted. SETTING: Office practices, hospital practices, and university-based medical centers. MEASUREMENTS AND MAIN RESULTS: Multivariable analysis identified five independent predictors present at the time of diagnosis that influenced ulcer healing. The odds of not healing for each risk factor after simultaneous adjustment of the other risk factors were as follows: alcohol use, 6.5 (CI, 2.0 to 20.7, P less than 0.002); ulcer size greater than 10 mm, 4.2 (CI, 1.5 to 11.6, P less than 0.005), bleeding symptoms. 3.5 (CI, 1.2 to 10.2, P less than 0.03); and a previous duodenal ulcer, 3.1 (CI, 1.05 to 9.0, P less than 0.04). The use of salicylates or nonsteroidal anti-inflammatory drugs before treatment was associated with an improved odds of healing (adjusted odds ratio, 0.2; CI, 0.1 to 0.9, P less than 0.04). The percentage of patients achieving complete ulcer healing after 4 weeks of famotidine decreased inversely with the number of risk factors present, ulcer size, and the quantity of daily alcohol use (P less than 0.001). Fewer than half of those patients who still had severe pain at day 7 achieved healing at 4 weeks (P less than 0.001). In contrast, smoking and 23 other factors had no statistically discernible effect on ulcer healing with famotidine. CONCLUSIONS: Five variables present at the time of diagnosis independently influenced the rate of ulcer healing at 4 weeks: alcohol use, ulcer size, bleeding symptoms, a previous duodenal ulcer, and previous use of salicylates or nonsteroidal anti-inflammatory drugs.

Adult↗

PubMed1987

Guidelines for maintenance treatment of childhood asthma: development of a score card system by multivariate cluster analysis.

Multivariate cluster analysis of data on 128 asthmatic children resulted in the identification of 8 major discriminating variables. Stepwise divisions by this computer programme resulted in the formation of 6 grades of severity. There was significant correlation between higher grades of severity and early onset of the disease (P less than 0.02). There was also significant correlation between higher grades of severity and greater use of interval medications (P less than 0.002). However, 27.3% were receiving inadequate interval medications in respect of their grade of severity. Assignation of a 5-point scale to each of the 8 major discriminating variables resulted in the generation of computer-designated scores commensurate with each grade of severity. This was coupled to current recommendations for stepwise maintenance medications appropriate for each grade. This Score Card system for maintenance management of childhood asthma may prove useful in busy clinical settings.

Adolescent↗

PubMed1985

Grading of prostatic cancer: III. Multivariate analysis of prognostic parameters.

This work is based on the two previous publications which are concerned with grading prostatic carcinoma. In the present communication the technique of multivariate analysis is applied to quantify the prognostic importance of parameters which were earlier identified as contributing in a significant manner to grading. The results of this analysis are used to construct a scoring system which differentiates five significantly different prognostic groups. When compared to the results of grading, the new system is shown to be superior. The large group of 228 patients with G2 tumors can be split into three groups, each with a significantly different prognosis. The correlation of the scoring system to local tumor extension (pT category) is described. Recommendations for grading of prostatic carcinoma resulting from this work are the following: Only three independent parameters are of significance for grading prostatic cancer: tumor architecture, nuclear anaplasia, and the presence or absence of mitoses. The combination of these parameters in a scoring system identifies five separate prognostically different groups. The separation achieved by this new system is superior to conventional grading and is suggested for grading prostatic cancer.

Humans↗

PubMed2002

Simultaneous determination of amiloride hydrochloride and hydrochlorothiazide in synthetic samples and pharmaceutical formulations by multivariate analysis of spectrophotometric data.

The use of multivariate spectrophotometric calibration for the simultaneous analysis of synthetic samples and commercial tablet preparations containing hydrochlorothiazide (HCT) and amiloride hydrochloride (AMH) is reported. Partial least squares (PLS-1) analysis of electronic absorption spectral data allowed the rapid and accurate resolution of mixtures in which the analyte ratios were approximately 10:1, without the need of a previous separation step and without interference from other sample constituents. The method, validated by the analysis of synthetic mixtures of both drugs, where accuracy over the linear working range as well as inter- and intra-assay precision were determined, was used in the concentration ranges of 21.7-30.4 mg l(-1) for HCT and 1.8-3.0 mg l(-1) for AMH. The proposed method was successfully applied to the evaluation of the stability of the stock solutions of the analytes in MeOH-H(2)O and to the elaboration of drug dissolution profiles of commercial tablets, results being concordant with those furnished by the USP technique. The method was also employed for the determination of drug content in two different pharmaceutical formulations, providing results that were in excellent agreement with those obtained by HPLC.

Amiloride↗

PubMed1995

[Multivariate analysis of prognostic factors after resection of ductal pancreatic carcinomas].

At Hanover Medical School 466 patients were operated for ductal pancreatic cancer from 1971 to 1993. In 192 cases the pancreatic tumor could be resected, which amounts to a resection rate of 41%. These patients were subjected to uni- und multivariate factorial analysis in order to evaluate factors of significant prognostic value. Extended pancreatic resection because of vascular involvement or invasion of adjacent organs was performed in 40% (n = 77) of the cases. A curative R0 resection was possible in 85% of patients. The operative lethality dropped with time and from 1985 to 1993 was 3.5%. Patient survival at 5 years was 13.4% with a median survival time of 10.9 months. According to the univariate analysis the prognosis deteriorated with increasing tumor size and lymphatic and hematogenic metastases. There was a significant correlation between tumor stage according to the UICC and prognosis. The prognosis after resection was also significantly influenced by the residual tumor state and tumor grading. Extended pancreatic resections, however, had no significant prognostic impact. The multivariate analysis showed that only three factors were of independent significant relevance: residual tumor state, tumor size and tumor grade. The presence or absence of lymphatic and hematogenic metastases had no independent prognostic significance after resection of ductal pancreatic carcinomas.

Adult↗

PubMed1987

Multivariate analysis of prognostic factors in patients with disseminated nonseminomatous testicular cancer: results from a European Organization for Research on Treatment of Cancer Multiinstitutional Phase III Study.

Univariate and multivariate linear logistic regression analyses of potential prognostic variables have been performed for 163 patients with disseminated nonseminomatous testicular cancer, treated with cisplatin, vinblastine, and bleomycin in a multicenter study of the European Organization for Research on Treatment of Cancer Genito-Urinary Tract Cancer Cooperative Group. With a multivariate analysis, four prognostic groups with complete responder rates of 100, 89, 41, and 18%, respectively, were identified based on three prognostic factors: trophoblastic elements in the primary tumor, serum concentration of alpha-fetoprotein, and lung metastases by size and number. However, with a univariate analysis the logarithm of the beta subunit of human chorionic gonadotrophin (BHCG) was the single most important factor. This model aids the physician in selecting prospectively good risk patients who are candidates for low toxicity chemotherapy and poor risk patients with whom innovative treatment should be attempted.

Analysis of Variance↗

PubMed1979

Short-term prognostic index in acute myocardial infarction. Multivariate analysis by Cox model.

A new multivariate stepwise linear regression analysis (Cox's model) with survival time as prognostic endpoint was utilized in 281 patients with acute myocardial infarction. From 18 prognostic factors occurring during the first 5 days in the Coronary Care Unit a new prognostic index was calculated for the chance of survival in the first 36 days after admission. The significant prognostic variables were heart failure, cardiogenic shock, atrioventricular block and age. The total group of patients was classified in 6 subgroups with different mean indices and prognosis. There were 2 large groups of patients with relative bad and good prognosis (with and without heart failure). Over half of the patients had no prognostic variables. There was a trend of overestimating the expected deaths. A definite cardiac cause of death was shown by 23 patients (82%). This prognostic index based on the 4 variables can for the individual patient predict the chance of survival, which can be the basis of an individualized duration of hospital stay.

Age Factors↗

PubMed1989

[Discrimination attempt between stenoses of the left trunk and tritroncular involvement using univariate and multivariate analysis of the variables of the exercise test].

One hundred and fifty patients with more than 70 p. 100 three vessel (3V) stenosis and 69 patients with more than 50 p. 100 left main (LM) coronary artery stenosis underwent an exercise test at maximum or symptom-limited level, after discontinuing all anti-ischaemic therapies. Three comparative statistical methods were used: 1. Univariate analysis. Among the mean values of the 17 variables studied, 6 differed significantly (p less than 0.05), viz.: cardiac work performed until the appearance, on the CM5 lead, of an ST depression (STd) of 1 mm (W1) (LM = 1,002 Kpm; 3V = 1,461 Kpm) and of 2 mm (W2) (LM = 2,445 Kpm; 3V = 2,904 Kpm); maximum STd/maximum heart rate ratio; rise of systolic pressure during exercise and rise of heart rate associated with a 2 mm STd less pronounced with LM; maximum exercise capacity (W3) (LM = 2,445 +/- 1,514; 3V = 2,904 +/- 2,095 Kpm). 2. Linear discriminant function analysis. No discriminant variable could be obtained (subjects well classified 53 p. 100, ill-classified 47 p. 100). 3. Multivariate analysis, Cox's model. This method demonstrated that stenosis of the LM coronary artery is characterized by the early appearance of ischaemia rather than by its severity. After 4 minutes of exercise, 62 p. 100 of LM patients and only 28 p. 100 of 3V patients had a 1 mm ST depression. It is concluded that exercise tests do not provide a certainty of LM stenosis, but they identify patients with severe ischemia who most probably have this type of stenosis. Such patients can then be selected for coronary arteriography and operated upon as soon as possible.

Aged↗