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 757 records · Page 42Linked to original sources
PubMed1995

The influence of prostate size on cancer detection.

OBJECTIVES: To determine if cancer detection rates vary with prostate size using a sextant core biopsy pattern. METHODS: We reviewed 1021 transrectal ultrasound (TRUS)-guided sextant pattern prostate biopsies to determine if cancer detection varied based on prostate size. Prostate size was determined using a computer generated elliptical estimation method. Sextant core biopsies were taken, and the patients divided into groups based on estimated size of the prostate and biopsy outcome. Large prostates were those that were estimated by TRUS as 50 cc or more. Prostates were considered small if they were less than 50 cc. Groups were compared based on size and biopsy outcome. RESULTS: Adenocarcinoma was detected in 33% (334 of 1021) of the patients. Large prostates were noted in 34% (346 of 1021), of which 23% (80 of 346) had cancer detected by sextant biopsy. Small prostates were noted in 66% (675 of 1021), of which 38% (254 of 675) had cancer detected. The difference in cancer detection in large and small glands using a sextant pattern was statistically significant (P < 0.01). Patients with positive biopsies had significantly smaller prostate sizes (40 cc +/- 26) when compared with those with negative biopsies (51 cc +/- 33) (P < 0.01). Only 14% (8 of 58) of patients with gland sizes 100 cc or greater had positive sextant biopsies while 49% (118 of 239) with prostates 25 cc or less had cancer detected. Multivariate statistical analysis was used to control for differences in age, prostate-specific antigen (PSA), PSA density, TRUS findings, and digital rectal examination between the large and small prostate groups. The difference in cancer detection persisted (P < 0.05) CONCLUSIONS: Currently no evidence exists to support differing cancer rates based on gland size alone. Our cancer detection rate using a sextant pattern was higher in men with prostates less than 50 cc, and patients diagnosed with cancer had significantly smaller prostates than those with a negative sextant biopsy. Our data suggest that significant sampling error may occur in men with large glands, and more biopsies may be needed under these circumstances. The effects of tumor volume, focality, and specimen size in relation to overall gland size may contribute to these findings.

Adenocarcinoma↗
PubMed2004

Integrated environmental assessment of the Mid-Atlantic region with analytical network process.

A decision analysis method for integrating environmental indicators was developed. This was a combination of Principal Component Analysis (PCA) and the Analytic Network Process (ANP). Being able to take into account the interdependency among variables, the method was capable of ranking ecosystems in terms of environmental conditions and suggesting cumulative impacts across a large region. Using data on land cover, population, roads, streams, air pollution, and topography of the Mid-Atlantic Region of the United States, we were able to point out areas which were in relatively poor condition and/or vulnerable to future deterioration regarding various environmental aspects. The method offered an easy and comprehensive way to combine the strengths of conventional multivariate statistics (PCA) and decision-making science tool (ANP) for integrated environmental assessment.

Conservation of Natural Resources↗
PubMed1995

Predictors of 30-day mortality in the era of reperfusion for acute myocardial infarction. Results from an international trial of 41,021 patients. GUSTO-I Investigators.

BACKGROUND: Despite remarkable advances in the treatment of acute myocardial infarction, substantial early patient mortality remains. Appropriate choices among alternative therapies and the use of clinical resources depend on an estimate of the patient's risk. Individual patients reflect a combination of clinical features that influence prognosis, and these factors must be appropriately weighted to produce an accurate assessment of risk. Prior studies to define prognosis either were performed before widespread use of thrombolysis or were limited in sample size or spectrum of data. Using the large population of the GUSTO-I trial, we performed a comprehensive analysis of relations between baseline clinical data and 30-day mortality and developed a multivariable statistical model for risk assessment in candidates for thrombolytic therapy. METHODS AND RESULTS: For the 41,021 patients enrolled in GUSTO-I, a randomized trial of four thrombolytic strategies, relations between clinical descriptors routinely collected at initial presentation, and death within 30 days (which occurred in 7% of the population) were examined with both univariable and multivariable analyses. Variables studied included demographics, history and risk factors, presenting characteristics, and treatment assignment. Risk modeling was performed with logistic multiple regression and validated with bootstrapping techniques. Multivariable analysis identified age as the most significant factor influencing 30-day mortality, with rates of 1.1% in the youngest decile (< 45 years) and 20.5% in patients > 75 (adjusted chi 2 = 717, P < .0001). Other factors most significantly associated with increased mortality were lower systolic blood pressure (chi 2 = 550, P < .0001), higher Killip class (chi 2 = 350, P < .0001), elevated heart rate (chi 2 = 275, P < .0001), and anterior infarction (chi 2 = 143, P < .0001). Together, these five characteristics contained 90% of the prognostic information in the baseline clinical data. Other significant though less important factors included previous myocardial infarction, height, time to treatment, diabetes, weight, smoking status, type of thrombolytic, previous bypass surgery, hypertension, and prior cerebrovascular disease. Combining prognostic variables through logistic regression, we produced a validated model that stratified patient risk and accurately estimated the likelihood of death. CONCLUSIONS: The clinical determinants of mortality in patients treated with thrombolytic therapy within 6 hours of symptom onset are multifactorial and the relations complex. Although a few variables contain most of the prognostic information, many others contribute additional independent prognostic information. Through consideration of multiple characteristics, including age, medical history, physiological significance of the infarction, and medical treatment, the prognosis of an individual patient can be accurately estimated.

Aged↗
PubMed1998

Predicting length of stay in an acute psychiatric hospital.

OBJECTIVE: Multivariate statistical methods were used to identify patient-related variables that predicted length of stay in a single psychiatric facility. The study investigated whether these variables remained stable over time and could be used to provide individual physicians with data on length of stay adjusted for differences in clinical caseloads and to detect trends in the physicians' practice patterns. METHODS: Data on all patients discharged over two six-month periods were collected at an acute psychiatric inpatient facility. Stepwise multiple regression analyses were conducted on the two datasets. RESULTS: The results from both analyses revealed that five variables significantly predicted length of stay and were stable over time. They were a primary diagnosis of schizophrenia, the number of previous admissions, a primary diagnosis of a mood disorder, age, and a secondary diagnosis of an alcohol- or other drug-related disorder. For some physicians, the mean length of stay of their patients differed significantly from the length predicted by the regression model--generally, it was shorter. CONCLUSIONS: The results demonstrate that patient-related predictors of length of stay in a single psychiatric hospital can be identified using relatively simple statistical procedures and can be consistent across a large dataset and over time.

Adult↗
PubMed1990

[Perforated gastroduodenal ulcer. II. Risk analysis in the prognostic evaluation of the postoperative course].

The data of 245 patients of our clinic, which perforation was treated with simple suture, were analysed by uni- and multivariate statistics to estimate risk factors. The aim was to predict the postoperative outcome. In a first step univariate test methods gave some orientation of the relevance of the factors. There was a highly significant correlation of age, preoperative shock, medical illnesses, time interval perforation-operation and clinical diagnosis to postoperative mortality. In a second step a multivariate decision model was used to calculate a prognostic index of the outcome after operation of perforated peptic ulcer. The index was tested in a cohort study. The results of validation were good for all quality parameters, so that the index allows a relatively safer statement about the so-called risk patients.--The prognostic problems of perforated gastroduodenal ulcer, including diagnosis, are also represented with graphic figures in the form of decision trees.

Adolescent↗
PubMed1984

Comparison of heterotopic bone after anterolateral, transtrochanteric, and posterior approaches for total hip arthroplasty.

The effects of anterolateral, transtrochanteric, and posterior surgical approaches for total hip arthroplasty on heterotopic bone formation were studied in 507 consecutive patients with osteoarthritis or avascular necrosis who had not had previous hip surgery. Range of motion, degree of pain, and satisfaction were compared. Although the lowest incidence of ectopic ossification occurred after the posterior approach, there were no statistically significant differences among the three approaches. Extensive ectopic bone, involving more than half the distance between the trochanter and acetabulum, occurred in 29% after anterolateral, 28% after lateral transtrochanteric, and 22% after posterior approaches. Motion was most affected by the lateral approach, whereas relief of pain and general satisfaction were slightly better with the posterior approach. Multivariate statistical analysis suggests that the difference in results (p less than 0.05) with the posterior approach is primarily due to a relatively lower incidence of severe grades of heterotopic bone.

Adult↗
PubMed2004

Determination of trace elements in wines and classification according to their provenance.

Provenance and authenticity of wines can be recognized on the basis of typical mineral and trace element patterns by means of chemometric methods. Therefore analytical methods were developed for the determination of As, Be, Co, Cs, Ga, Li, Nb, Ni, Rb, Te, Ti, W, Y, and Zr as well as Mo, Cd, Sb, Tl, U, and the rare earth elements in wines by inductively coupled plasma mass spectrometry (ICP-MS). For low risk of contamination or loss of analyte as well as depletion of sample amount and an easy sample pretreatment, direct measurement of diluted wines was studied. The accuracy of the analytical results was proven by recovery experiments by method comparison with standard addition methods and measurement of digested wines. In addition to applying statistical methods for characterizing the precision of the methods, the uncertainty of the measurements was estimated. Results for the elements mentioned above and additional 16 elements (Al, B, Ba, Ca, Cr, Cu, Fe, Mn, Mg, P, Pb, Si, Sn, Sr, V, and Zn) were evaluated by data analytical methods. Due to a specific choice of the analytes for multivariate statistical investigation a prediction rate by cross validation of 88.6% could be achieved.

Aluminum↗
PubMed2001

The prognostic value of tumor markers in patients with glioblastoma multiforme: analysis of 32 patients and review of the literature.

Although several studies have examined brain tumor markers for prognostic value, few investigations have stratified analysis based on specific histologic grade. The objective of this study was to evaluate a single histologic grade of glioma, the grade IV glioma or glioblastoma (World Health Organization Classification), with a comprehensive panel of tumor markers in an attempt to identify those with prognostic significance. Tumor samples from a cohort of patients with glioblastoma multiforme (n = 32) were examined for tumor markers, DNA analysis, and clinical variables in an attempt to determine a 'profile' for this tumor. We used univariate and multivariate statistical analysis to determine the prognostic value of tumor cell ploidy, percent S-phase, DNA index, p53, and Ki-67 labeling index, as well as the variables of gender, race, age, location of tumor, history of chemotherapy, and primary versus recurrent tumor. Two additional tumor markers, multidrug resistance gene 1 and glutathione-S-transferase subtype pi, were included in the sample testing, but were not analyzed statistically. Univariate analysis indicated that increasing age had a strong association with decreased survival. Female gender, increasing Ki-67, no chemotherapy before sample collection, and primary glioblastoma showed some association with decreased survival in the univariate model. The univariate results indicated that race, side of tumor, ploidy, S-phase, DNA index, and p53 had no prognostic value. Multivariate modeling demonstrated that age, gender, and Ki-67 were the strongest factors associated with survival. The relevant literature is reviewed.

ATP Binding Cassette Transporter, Subfamily B, Mem↗
PubMed1979

Risk factors for myocardial infarction in the Stockholm prospective study. A 14-year follow-up focussing on the role of plasma triglycerides and cholesterol.

A 14-year follow-up of the Stockholm prospective study is reported. A number of 130 new myocardial infarctions (MI) were found in a prospective group of men (n = 3189) and another 46, i.e. a total of 176 MI, in the total group (n = 3486). Different types of multivariate statistical analyses show that age, blood pressure, smoking, fasting plasma concentrations of cholesterol and triglycerides, ESR and Hb were independent risk factors for MI, while the weight/height index was not. Elevated BP became an important risk factor only after the age of 50. When only age, BP, smoking and the two plasma lipids were entered into the logistic multivariate analysis, plasma triglycerides were more important as a risk factor than cholesterol. Quintile analysis showed that the rate of new MIs increased more with increasing triglyceride than increasing cholesterol levels. In the prospective group, the average rate of new MIs for men below 60 years was 32 per 1000. In the bottom and top quintile these rates were 16 and 65 for plasma triglycerides and 27 and 47 for cholesterol. When the men were divided into 4 groups with regard to both plasma lipids, the rate of new MIs increased successively from group to group along this chain: both lipids normal, only cholesterol high, only triglycerides high and both plasma lipids high.

Adult↗
PubMed1997

[Use of multivariate analysis in medical chemistry].

Alternations in trace elements concentrations are intensively studied because of their possible role in pathogenesis and progress of diseases. Three groups of patients were investigated: haemodialysis patients (HD) (n = 17), continual ambulatory peritoneal dialysis patients (CAPD) (n = 11), and control group of blood donors (n = 12). They were analyzed for Se, Zn and Cu concentration in plasma and erythrocytes by inductively--coupled plasma mass spectroscopy. Distribution of analyzed elements between these blood compartments was found different in all groups of studied patients. Erythrocytes were enriched by Se (twofold higher concentration compared to plasma) and by Zn (10-20 fold higher concentrations compared to plasma). On the other hand, human plasma was enriched by Cu (approximately twofold higher concentration then in erythrocytes). Results of analyses were processed by multivariate analysis of variance (MANOVA). When only results of plasma analysis were involved into MANOVA, differences between HD patients and other two groups were found whereas CAPD and control group were not distinguished each other. However, these two groups were mutually differenced when MANOVA comprised all trace elements concentrations: both plasma and erythrocytes. Methods of multivariate statistic are able to study not only the individual variables but even their mutual relations and their medical applications are very useful.

Blood Donors↗
PubMed2001

Morphological parameters as predictors of successful correction of Class III malocclusion.

The aim of the study was to assess pre-treatment cephalometric parameters and measurements of the size of the apical bases as predictors of successful orthodontic correction of Class III malocclusions. Pre- and post-treatment lateral cephalograms and study models of 80 completed Class III subjects were examined to obtain 23 cephalometric parameters taken mainly from the analyses of McNamara and Schwarz, and to measure the size of the apical bases. Success of occlusal correction was evaluated as the percentage change of peer assessment rating score during treatment, which was used as the dependent variable in multivariate statistical analyses testing the predictive value of the parameters assessed. No improvement in the Class III skeletal pattern occurred during treatment and the treatment effects were confined to dentoalveolar changes. With the exception of the percentage midfacial length/mandibular length ratio, the net sum of maxillary and mandibular length differences, the mandibular ramus height/mandibular body length ratio and the gonion angle, most cephalometric parameters of pre-treatment craniofacial morphology assessed were poor predictors of successful correction of Class III malocclusions. Assessment of the size relationship of the maxillary and mandibular apical bases was the strongest predictor of occlusal correction achieved and may serve as a valuable diagnostic addition in the prediction of successful treatment outcome.

Age Factors↗
PubMed2001

Body mass index and mortality in an insured population.

OBJECTIVE: This study was conducted to explore the relationship between body mass index (BMI) and mortality in an insured population issued policies at standard rates or rated only for build using contemporary analytic techniques. BACKGROUND: Many factors influence the relationship between build and mortality. Recent clinical literature on this subject often employs multivariate statistical techniques to better define this relationship and reduce the influence of confounders. BMI, a common surrogate variable for build in clinical literature, is our variable of choice in studying the relationship between build and mortality. METHODS: We studied internal data on direct and reinsurance business issued between 1975 and 1998 at standard rates or rated only for build. The policies were followed till termination (death or lapse) or to the end of 1999. The average policy duration was 4.7 years. Cox proportional hazards model runs were used to study the multivariate relationship between mortality and BMI in moderately over- and underweight insured individuals. RESULTS: During follow-up, 4105 deaths were observed. Mortality was noted to very with BMI, most significantly in middle-aged male nonsmokers. Consistent with reports from the clinical literature, significant factors influencing the BMI-mortality relationship in this insured population included issue age and smoking status. CONCLUSIONS: BMI is a predictor of statistically significant mortality differentials in insured populations. The strength of the BMI-mortality relationship was found to vary by age, gender, and smoking status. In our study population, the male nonsmoker subgroups tended to exhibit the strongest graded relationship between hazard of death and increasing or decreasing BMI.

Adolescent↗
PubMed1996

Risk factors for postoperative morbidity.

OBJECTIVE: Analysis of outcomes after coronary artery bypass grafting has focused on risk factors for operative mortality. Nonfatal perioperative morbidity is far more costly and more common after operation. To identify the risk factors that lead to postoperative morbidity, we evaluated 938 patients undergoing coronary artery bypass grafting at Albany Medical Center Hospital during 1993. METHODS: Multivariate statistical analysis was performed on preoperative patient variables to identify risk factors for either serious postoperative morbidity or increased hospital length of stay. Variables were considered both individually and in combination. For example, age was considered individually or in combination with other variables, including parameters of blood volume (i.e., age divided by red blood cell volume or Age/RBCVOL). Similar multivariate analysis was performed to identify independent risk factors for hospital mortality. RESULTS: In order of decreasing importance, the following patient variables were significantly associated with increased length of stay by stepwise Cox regression analysis: Age/RBCVOL, history of congestive heart failure, hypertension, femoral-popliteal peripheral vascular disease, chronic obstructive lung disease, and renal dysfunction. The combination variable, Age/RBCVOL, was an important risk factor for both increased length of stay and serious postoperative morbidity. Variables that were significant independent predictors of increased mortality, such as preoperative shock, and redo operation, were not risk factors for either serious morbidity or increased length of stay. CONCLUSIONS: We conclude that risk factors for postoperative morbidity are different from those for postoperative mortality. These results suggest that older patients with preoperative anemia and low blood volume who also have other comorbidities (congestive heart failure, stroke, chronic obstructive pulmonary disease, or hypertension) are at increased risk for postoperative complications. This allows identification of a high-risk cohort of patients who are likely candidates for interventions to lessen postoperative morbidity.

Age Factors↗
PubMed2005

Locally advanced differentiated thyroid carcinoma: a 35-year mono-institutional experience in 280 patients.

AIM: Debate exists in the literature about the optimal treatment to be adopted in patients with locally advanced differentiated thyroid carcinoma. We aimed to better define the most appropriate diagnostic and therapeutic protocol for this type of tumour. METHODS: The clinical and histopathological records of 280 consecutive patients with locally advanced differentiated thyroid carcinoma, studied and operated on by the same surgical team in the period between 1967 and 2002, were reviewed. RESULTS: With regard to overall survival, at univariate statistical analysis, the patient's age at diagnosis (threshold, 45 years), primary tumour size, local cancer extension at diagnosis (subtypes of T4), extent of thyroidectomy, performance of lymph node dissection and performance of post-surgical external radiotherapy were found to be significant prognostic variables. With regard to the appearance of recurrent disease during follow-up, at univariate statistical analysis, the patient's age at initial diagnosis (threshold, 45 years), primary tumour size, local cancer extension at diagnosis (subtypes of T4), extent of thyroidectomy, performance of lymph node dissection, presence of metastatic lymph nodes, performance of post-surgical 131I therapy and performance of post-surgical external radiotherapy were found to be significant prognostic variables. At multivariate statistical analysis, the patient's age at initial diagnosis, extent of tumour, extent of thyroidectomy and performance of lymph node dissection were the only independent prognostic variables. CONCLUSIONS: In our experience, an aggressive surgical approach at first diagnosis appears to offer a better prognosis in terms of both overall survival and disease-free time interval in patients with locally advanced differentiated thyroid carcinoma, especially those over 45 years of age.

Adult↗
PubMedDate not supplied

Chronic lymphocytic leukemia (CLL) in younger adults: a retrospective study of 133 cases.

Clinical and biological data have been evaluated, using both univariate and Cox's multivariate statistical analyses, in a series of 133 Chronic Lymphocytic Leukemia (CLL) patients with a mean age of 46.6 years (range 31-50). In univariate analyses, anemia (Hb less than 13 g/dl), peripheral blood (PB) lymphocytosis (greater than 40 x 10(9)/l) and bone marrow (BM) lymphocytosis (greater than 80 per cent) were shown to be of significant prognostic value. Multivariate analysis, through a forward stepwise procedure, showed that the most important and independent variable is the BM lymphocytosis. These results are different from those obtained in previous studies and particularly in a recent identical study performed by the same Cooperative Group on 1777 patients with a mean age of 64.2 years (Mandelli et al., 1987). No significance can be demonstrated in stratifying this series of younger patients according to different staging methods (Rai et al., 1975; Binet et al., 1981b; Mandelli et al., 1987). Therefore this population of CLL patients, with less than 50 years of age, has risk factors quite different from classical CLL. The results of the present study show that the diagnostic approach to B-CLL in younger adults must be more complete: using the common diagnostic criteria, established staging systems appear to be inadequate in this series of younger patients.

Adult↗
PubMed1992

Prognostic value of progesterone receptor after long-term follow-up in primary breast cancer.

In a previous study of a series of 105 patients with primary breast cancer we found that the progesterone receptor (PgR) status was an important prognostic factor for early recurrences. 95 patients from the same series were followed-up for a median of 9.5 years and reassessed for the prognostic value of PgR status by univariate and multivariate statistical methods. In univariate analysis, the disease-free interval was only related to the lymph-node status. For overall survival, PgR and combined PgR-ER (oestradiol receptor) status had a prognostic value (P = 0.035 and 0.05, respectively). Moreover, PgR status was found to be discriminant for the survival of the node-negative patients (P = 0.017). In multivariate analysis, ER and PgR status were not significant, indicating that receptor status is not a powerful predictor of the course of breast cancer.

Adult↗
PubMed2006

Statistically integrated metabonomic-proteomic studies on a human prostate cancer xenograft model in mice.

A novel statistically integrated proteometabonomic method has been developed and applied to a human tumor xenograft mouse model of prostate cancer. Parallel 2D-DIGE proteomic and 1H NMR metabolic profile data were collected on blood plasma from mice implanted with a prostate cancer (PC-3) xenograft and from matched control animals. To interpret the xenograft-induced differences in plasma profiles, multivariate statistical algorithms including orthogonal projection to latent structure (OPLS) were applied to generate models characterizing the disease profile. Two approaches to integrating metabonomic data matrices are presented based on OPLS algorithms to provide a framework for generating models relating to the specific and common sources of variation in the metabolite concentrations and protein abundances that can be directly related to the disease model. Multiple correlations between metabolites and proteins were found, including associations between serotransferrin precursor and both tyrosine and 3-D-hydroxybutyrate. Additionally, a correlation between decreased concentration of tyrosine and increased presence of gelsolin was also observed. This approach can provide enhanced recovery of combination candidate biomarkers across multi-omic platforms, thus, enhancing understanding of in vivo model systems studied by multiple omic technologies.

Animals↗