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 631 records · Page 35Linked to original sources
PubMed1990

[Kaposi's sarcoma associated with the acquired immunodeficiency syndrome. An analysis of 67 cases with a study of the prognostic factors].

The features and prognostic factors of 67 cases of Kaposi's sarcoma (KS) associated to the acquired immunodeficiency syndrome (AIDS) diagnosed at the Hospital Clinic, Barcelona, are analyzed. All the patients were male; mean age was 39.7 years, ranging from 22 and 62 years. 64 were homosexuals (95.5%), two were homosexual-drug addicts (3%) and one was drug addict (1.5%). Prevalence of cytomegalovirus and herpes virus infections were 91.1% and 89.5% respectively. In 42 cases (62.7%) KS was the initial AIDS presentation. The most common localization was the skin (89.5%), followed by the digestive tract (52.2%) and the lymph nodes (22.4%). Staging distribution was: 20 patients (29.8%) were in stage I, 11 patients (16.4%) in stage II, 7 patients (10.4%) in stage III, and 29 patients (43.2%) in stage IV. Constitutional symptoms associated to KS were found in 37 patients (55%). Overall 39 patients have already died, and the actuarial survival possibility of these 67 cases was 55% after 12 months. Univariant statistical analysis showed the presence of six variables with prognostic significance (p less than 0.05): staging, symptomatology, total white blood count, total lymphocyte count, T helper lymphocyte count and hemoglobin. Multivariant statistical analysis only chose the staging and symptomatology variables as independent (p less than 0.01 and p less than 0.001, respectively).

Acquired Immunodeficiency Syndrome↗
PubMed1981

[Characterization of genetic EEG-variations with the amplitude-interval-analysis. I. Variations of alpha-activity; flat-EEG; borderline flat EEG, occipital slow beta-waves; monotonous alpha-rhythm (author's transl)].

In 121 healthy adult male probands with different variants of alpha-activity (monotonous alpha-waves; low voltage EEG, borderline low voltage EEG; occipital slow beta-waves) a quantitative description of unipolar leads was carried out using a program for amplitude-interval (time-domain) analysis. Statistically significant differences between means of the examined parameters were discovered between the various EEG variants. No single parameter, however, separates these variants reliably. For such a separation, methods of multivariate statistics will have to be used. Significant differences between right and left hemispheres (primarily lower alpha-activity together with higher beta-activity on the left hemisphere) were found in all EEG types examined except the variant with monotonous alpha-waves.

Alpha Rhythm↗
PubMed1993

[Overweight and obesity in Chilean women. A multivariate characterization based on psychophysiologic indicators].

This paper presents a reanalysis of previously collected data using multivariate statistical methods. Aside from confirming the discrimination between obese, and normal-weight women through psychometric indicators including a personality evaluation, and a verbal affective expression assessment, the power of multivariate methods for improving diagnosis is illustrated.

Case-Control Studies↗
PubMed2004

Perioperative neurosensory changes associated with treatment of mandibular fractures.

PURPOSE: The purpose of this study was to document perioperative neurosensory changes in the inferior alveolar nerve (IAN) after mandibular fracture treatment and to identify risk factors associated with these changes. MATERIALS AND METHODS: This was a prospective cohort study composed of patients treated for mandibular fractures. The primary study variable was the change between the postinjury/pretreatment IAN neurosensory examination score and the score after fracture reduction. Risk factors were categorized as demographic, anatomic, and treatment. Appropriate descriptive, bivariate, and multivariate statistics were computed. RESULTS: The cohort was composed of 61 patients with 97 fractured sides. Forty-seven fractures (49%) were located between the lingula and mental foramen, and 50 fractures (51%) were located distal to the mental foramen. Thirty-nine fractures (41%) were displaced by 5 mm or more. Abnormal preoperative IAN neurosensory examinations were documented in 81% of the fractured sides. Fifty-three fractures (54%) were treated by closed reduction and 44 (46%) by open reduction and internal fixation. In 82 fractures (85%), the IAN neurosensory score was unchanged or improved after treatment. In a multivariate model, preoperative neurosensory score, displacement, and treatment were associated with a statistically significant risk (P < or =.05) for postoperative deterioration of IAN sensation. CONCLUSION: Open reduction and internal fixation, fracture displacement of 5 mm or more, and a normal preoperative IAN neurosensory examination were associated with an increased risk for deterioration of the IAN neurosensory score after treatment of mandibular fractures. Additional studies are indicated to determine long-term IAN neurosensory function after mandibular fracture treatment and the factors that affect prognosis.

Adult↗
PubMed1992

Management of local bacillus Calmette-Guerin failures in superficial bladder cancer.

We attempt to define the treated natural history of patients with superficial bladder tumors (stages Ta, TIS and T1) managed with intravesical bacillus Calmette-Guerin (BCG) to determine the best form of treatment for locally recurrent tumors. The management and survival of 41 patients who failed BCG within the bladder or prostatic urethra and who subsequently were treated with a variety of secondary therapies are reviewed. Our aim was to assess the role of several independent clinical variables on the rate of death from bladder cancer. Of the 41 patients 6 (15%) died. Univariate statistical analysis identified early involvement of the prostatic urethra and the presence of superficially invasive (stage T1) tumor at initial treatment with BCG as factors having an adverse effect on survival. A multivariate statistical model revealed that patients with early prostatic urethral involvement and the presence of superficially invasive (stage T1) tumor at diagnosis had the highest risk of death from bladder cancer. The reason for change in therapy at failure of BCG, stage of the tumor at BCG failure, occurrence of upper tract tumors and early versus delayed radical cystectomy had no impact on survival. The results suggest that not all tumors that recur after BCG are destined to proceed to muscle invasion or metastases, and that some patients may be managed safely by repeated endoscopic resection and intravesical therapy with cystectomy delayed until objective progression is evident. Such an approach can yield survival equal to that in patients treated with early cystectomy and may result in longer intervals of bladder preservation in a select subset of patients who fail BCG locally.

BCG Vaccine↗
PubMed1988

Comparison of predictions based on observational data with the results of randomized controlled clinical trials of coronary artery bypass surgery.

Clinical decisions are most secure when based on findings from several large randomized clinical trials, but relevant randomized trial data are often unavailable. Analyses using clinical data bases might provide useful information if statistical methods can adequately correct for the lack of randomization. To test this approach, the findings of the three major randomized trials of coronary bypass surgery were compared with predictions of multivariable statistical models derived from observations in the Duke Cardiovascular Disease Databank. Clinical characteristics of patients at Duke University Medical Center who met eligibility requirements for each major randomized trial were used in the models to predict 5 year survival rates expected for medical and surgical therapy in each randomized trial. Model predictions agreed well with randomized trial results and were within the 95% confidence limits of the observed survival rates in 24 (92%) of 26 clinical subgroups. The overall correlation between predicted and observed survival rates was good (Spearman coefficient 0.73, p less than 0.0001). These results suggest that carefully performed analyses of observational data can complement the results of randomized trials.

Angina Pectoris↗
PubMed1995

Protein fluorescence decay: discrete components or distribution of lifetimes? Really no way out of the dilemma?

A new methodology of fluorescence decay analysis by iterative reconvolution is presented. It is based on the recent finding that the statistics of single-photon time-correlated data are best described by a compound Poisson law and requires the recording of a sample of at least 20 decays. Application of multivariate statistical methods to the analysis of the recovered decay parameters results in improved accuracy and better estimation of the uncertainties of mono- and multiexponential decays. If it is, of course, not possible to distinguish unambiguously between discrete components and a continuous distribution of lifetimes, it is, however, possible to determine a higher limit of the width of such a distribution should it be present. With our methodology, the presence of a distribution of lifetimes with a width of approximately 20% of its center value inevitably leads to a failure in the deconvolution procedure, a fact of crucial importance in protein conformational studies, for example.

Biophysical Phenomena↗
PubMed2000

Wavelets as chromatin texture descriptors for the automated identification of neoplastic nuclei.

Chromatin distribution reflects the organization of the DNA of a nucleus and contains important cellular diagnostic and prognostic information. Feulgen staining of breast tissue enables the chromatin distribution of the nucleus to be visualized in the form of texture. Describing texture in an objective and quantitative way by means of a set of texture parameters, combined with the study of the relationship of such parameters to the pathobiological cell properties, is useful both for reduction of the subjectivity inherently coupled to visual observation and for more accurate prognosis or diagnosis. We have presented an automated classification scheme for the diagnosis and grading of invasive breast cancer. The input to this scheme was a digitized microscopical image, from which nuclei were segmented. Chromatin texture was described using a set of textural parameters that include first- and second-order statistics of the image grey levels. The more recently developed wavelet energy parameters were also included in our study. Classification was performed by a Knn-classifier, which is a versatile multivariate statistical classification technique. We investigated the role of the tissue preparation technique and found that parameters derived from cytospins were better texture descriptors than those from sections. A 100% correct classification was achieved in a patient diagnosis experiment and 82% in a nuclear grading experiment.

Breast Neoplasms↗
PubMed2002

Prediction of death in patients with primary intracerebral hemorrhage: a prospective study of a defined population.

OBJECT: Predictors of early (30-day) and long-term (1-year) mortality rates after primary intracerebral hemorrhage (ICH) were studied in a large population in southern Sweden. METHODS: All cases of primary ICH, verified using computerized tomography (CT) scanning or autopsy study, were prospectively registered at the 12 hospitals covering a defined population of 1.14 million during the calendar year 1996. Mortality was analyzed in relation to CT findings (hematoma location and volume and ventricular extension) and clinical parameters (patient age and sex, level of consciousness on admission, and history of preictal risk factors) by using univariate and multivariate statistical methods. Three hundred forty-one cases of primary ICH were detected. The overall mortality rate was 36% at the 30-day and 47% at the 1-year follow up. Multivariate analysis revealed that initial level of consciousness, hematoma volume, and a history of heart disease were independent predictors of death at 30 days postictus. One year after bleeding, independent predictors of mortality were the initial level of consciousness, patient age, and hematoma location. CONCLUSIONS: Primary ICH remains a stroke subtype associated with a high mortality rate and for which the level of consciousness on admission is the strongest predictor of fatal outcome both at 30 days and during the 1st year after bleeding. A preictal history of heart disease increased the 30-day mortality rate.

Adolescent↗
PubMed1981

[Characterization of genetic EEG variables with the amplitude-interval-analysis. II. Variations of the beta-activity and controls (author's transl)].

In 165 adult male probands with different variants of beta-Activity (fronto-percentral beta-wave-groups; diffuse beta-waves) including 76 controls from the same proband population but with inconspicuous EEG patterns, a quantitative description of unipolar leads was carried out using a program for amplitude-interval (time-domain) analysis. Statistically significant differences between some means of the examined parameters were found between the various EEG variants. No single parameter, however, separates these variants reliably. For such a separation, methods of multivariate statistics will have to be used. Significant differences between left and right hemispheres (especially lower average alpha-activity together with higher beta-activity on the left-hand side) were found in all examined EEG types including the controls. Hence, the lack of a significant side difference in the variant with monotonous alpha-waves as described in the first report of this series remains unique.

Adult↗
PubMed1995

Depression in individuals with spinal cord injury: methodological issues.

The methodological problems in research related to depression in individuals with spinal cord injury (SCI) are examined. These include relation to normal emotional reactions following injury, the use of physical and vegetative symptoms in the diagnosis of depression, the utilisation of rating scales primarily designed for use in psychiatric populations, the heterogeneity of patients with SCI, the role of preexisting psychiatric morbidity, the selection of controls for comparison and the necessity for multivariate statistical approaches to analysis. The issues and possible solutions are discussed.

Depressive Disorder↗
PubMed2004

Hyperglycemia at admission to the intensive care unit is associated with elevated serum concentrations of interleukin-6 and reduced ex vivo secretion of tumor necrosis factor-alpha.

OBJECTIVES: The aim of the study was to investigate the association between admission blood glucose concentrations and immune function variables and its correlation to mortality rate in patients of a medical intensive care unit. DESIGN: Prospective, observational study. SETTING: Medical intensive care unit of a university hospital. PATIENTS: Patients were 189 consecutive critically ill patients in the medical intensive care unit. INTERVENTIONS: At admission to the intensive care unit, serum concentrations of interleukin-6, interleukin-8, interleukin-10, and tumor necrosis factor-alpha were measured with immunometric assays. Additionally, ex vivo secretion of tumor necrosis factor-alpha after stimulation with lipopolysaccharide in a whole blood assay and cytometric human leukocyte antigen-DR expression on monocytes were determined in all study subjects. Simplified Acute Physiology Score II and Therapeutic Intervention Scoring System-28 were calculated for the first day in the intensive care unit. MEASUREMENTS AND MAIN RESULTS: The relationships between blood glucose concentrations and immunologic variables were analyzed using univariate and multivariate statistical methods. Overall, 75 patients (39.7%) presented with hyperglycemia. An elevated blood glucose concentration at admission was related to an increased risk of mortality in the intensive care unit (odds ratio, 2.6; p = .009). At univariate and multivariate analysis, hyperglycemia was associated with increased serum concentrations of interleukin-6 (p < .05), a reduced ex vivo production of tumor necrosis factor-alpha (p < .01), and a history of diabetes mellitus (p < .05), whereas other clinical (including Simplified Acute Physiology Score II and Therapeutic Intervention Scoring System-28) and immunologic variables were not statistically related to blood glucose. CONCLUSIONS: Our main findings show that admission hyperglycemia is statistically related to distinct changes of humoral and cellular immune functions. Furthermore, elevated glucose concentrations at admission are associated with increased intensive care unit mortality rate in a medical intensive care unit. Although these data do not explain cause and effect, our results provide a strong rationale for studying the immunologic effects of strict glycemic control in the intensive care unit during the course of critical illness.

APACHE↗
PubMed1999

Quantitative structure-metabolism relationships (QSMR) using computational chemistry: pattern recognition analysis and statistical prediction of phase II conjugation reactions of substituted benzoic acids in the rat.

1. Quantitative relationships between molecular physico-chemical properties of 22 substituted benzoic acids and the extent of excretion of their metabolites in rat urine have been investigated using computational chemistry and multivariate statistics. 2. A data set of 34 theoretically derived physico-chemical descriptors calculated was used to classify the benzoic acids according to their predominant urinary metabolic fate. 3. Quantitative structure-metabolism relationships were obtained by linear regression using combinations of physico-chemical descriptors allowing the prediction of % urinary excretion of glycine (r = 0.73) and glucuronide conjugates (r = 0.82) and % urinary excretion of the parent compound (r = 0.91).

Animals↗
PubMed1987

Symptoms of anxiety and symptoms of depression. Same genes, different environments?

While traditional multivariate statistical methods can describe patterns of psychiatric symptoms, they cannot provide insight into why certain symptoms tend to co-occur in a population. However, this can be achieved using recently developed methods of multivariate genetic analysis. Examining self-report symptoms in a clinically unselected twin sample (3798 pairs), traditional factor analysis indicates that symptoms of depression and anxiety tend to form separate symptom clusters. Multivariate genetic analysis shows that genes act largely in a nonspecific way to influence the overall level of psychiatric symptoms. No evidence could be found for genes that specifically affect symptoms of depression without also strongly influencing symptoms of anxiety. By contrast, the environment seems to have specific effects, ie, certain features of the environment strongly influence symptoms of anxiety while having little impact on symptoms of depression. These results, which are replicated across sexes, suggest that the separable anxiety and depression symptom clusters in the general population are largely the result of environmental factors.

Anxiety↗
PubMedDate not supplied

Analysis of tear protein patterns by a neural network as a diagnostical tool for the detection of dry eyes.

The electrophoretic patterns of tears from patients with dry-eye disease (n = 43) and from healthy subjects (n = 17) were analyzed by means of multivariate statistical methods and an artificial neural network (ANN), following sodium dodecyl sulfate-polyacrylamide gel electrophoresis (SDS-PAGE). From each electrophoretic pattern a data set was created, randomly divided into test (unknown samples) and training patterns (known samples), with ANN training by one of these sets. After training, the performance of the ANN was checked by presenting the test data set to the ANN. Furthermore, the data was classified using multivariate analysis of discriminance. The groups were significantly different from each other (P<0.05). The statistical procedure yielded 97% (known samples) and 71% (unknown samples) correct classifications. The ANN revealed 89% of correct classifications using the test set (unknown samples). The use of pruning algorithms (optimization procedure which automatically eliminates small weighted neurons) or genetic algorithms (optimization procedure which performs genetically induced changes of the neural net) resulted in a slight decrease of correct classifications compared to those of the nonoptimized neural network. The results reveal significant differences between the two groups. Using the ANN we were able to classify the electrophoretic tear protein pattern for diagnostic purposes.

Dry Eye Syndromes↗
PubMed1999

Evaluation of the Washington State Workers' Compensation Managed Care Pilot Project II: medical and disability costs.

OBJECTIVES: This study examined the effect of managed care on medical and disability costs as part of an evaluation of the Washington State Workers' Compensation Managed Care Pilot (MCP). METHODS: One hundred twenty firms (7,041 employees) agreed to have their injured workers treated in managed care plans. Managed care introduced two changes from the fee-for-service (FFS) delivery system currently used by injured workers in Washington State: experience- rated capitation and a primary occupational medicine delivery network. The FFS control group included injured workers employed at 392 firms (12,000 employees). Medical and disability costs were compared for 1,058 injuries in the managed care group and 1,159 injuries in the FFS group occurring between April 1995 and June 1996. Univariate and multivariate statistical methods were used to analyze the effects of managed care on medical and disability costs. RESULTS: The mean unadjusted medical cost per injury ($587) for the managed care group was 21.5% lower (P = 0.06) than for the FFS group ($748). Adjustment for differences in worker and firm-level characteristics through multivariate analysis had little effect on the unadjusted results, except that the difference in costs between managed care and FFS groups became statistically significant (P<0.01). The major cost differences were for outpatient surgery (cost per surgery) and ancillary services (pharmacy, x-ray, physical therapy, and all other costs). In addition, disability costs, particularly percent on time loss and time-loss cost per injury, were significantly lower (P<0.01) in the managed care group. CONCLUSIONS: The results from the MCP suggest that substantial savings in workers' compensation medical and disability costs may be realized using the type of managed care intervention designed for this study. Delivering occupational health services through managed care arrangements whose design is based on an integrated, occupational health-centered delivery model may offer a viable approach for improving delivery systems, reducing costs and encouraging greater attention to disability prevention.

Adult↗
PubMed1998

Multiple correlations and Bonferroni's correction.

Correlation coefficients between biological measurements and clinical scales are often calculated in psychiatric research. Calculating numerous correlations increases the risk of a type I error, i.e., to erroneously conclude the presence of a significant correlation. To avoid this, the level of statistical significance of correlation coefficients should be adjusted. Threshold levels of significance for correlation coefficients were adjusted for multiple comparisons in a set of k correlation coefficients (k = 1, 5, 10, 20, 50, 100) by Bonferroni's correction. Significant correlation coefficients were then calculated according to sample size. The change in the threshold values of significance is larger when the number of correlations goes from 1 to 5 than when it goes from 50 to 100. A correlation coefficient, statistically significant at 5% when calculated alone, can be under the threshold level of significance when calculated even among a few other coefficients. Focusing on the most relevant variables or the use of multivariate statistics is advocated.

Data Interpretation, Statistical↗
PubMed2006

Natural history, diagnosis, treatment and outcome of medullary thyroid cancer: 37 years experience on 157 patients.

AIM: The analysis of a 37-year retrospective study on diagnosis, prognostic variables, treatment and outcome of a large group of medullary thyroid cancer (MTC) patients was conducted, in order to plan a possible evidence-based management process. METHODS: Between Jan 1967 to Dec 2004, 157 consecutive MTC patients underwent surgery in our centre: 60 males and 97 females, mean age 47.3 years (range 6-79). Total thyroidectomy was performed in 143 patients (91.1%); central compartment (CC) node dissection (level VI) in 41 patients; central plus lateral compartment (LC) node dissection (levels II, III, and IV) in 82 patients. Subtotal thyroidectomy was initially performed in 14 cases: 10 of them were re-operated because of persistence of elevated serum calcitonin levels. RESULTS: After a median post-surgical follow-up of 68 months (range 2-440 months), 42.9% of patients were living disease-free, 39.8% were living with disease, 3.1% were deceased due to causes different from MTC, and 3.2% were deceased due to MTC. The overall 10-year survival rate was 72%. At uni-variate statistical analysis (a) patient's age at initial treatment (>45 years; >/=45 years), (b) sporadic vs. hereditary MTC, (c) disease stage, and (d) the extent of surgical approach resulted as significant variables. Instead, at multivariate statistical analysis, only (a) patient's age at initial diagnosis, (b) disease stage, and (c) the extent of surgery resulted as significant and independent prognostic variables influencing survival. CONCLUSION: The presence of lymph node and distant metastases at first diagnosis significantly worsened prognosis and survival rate in our series. Early diagnosis of MTC is very important, allowing complete surgical cure in Stages I and II patients. Due to the relatively bad prognosis of MTC, especially for disease Stages III and IV, it appears reasonable to recommend radical surgery including total thyroidectomy plus CC lymphoadenectomy as the treatment of choice, plus LC lymphoadenectomy in patients with palpable and/or ultrasound enlarged neck lymph nodes.

Adolescent↗