PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “Multivariate response regression”

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 613 records · Page 34Linked to original sources
PubMed2005

An index of local sensitivity to nonignorable drop-out in longitudinal modelling.

In longitudinal studies with potentially nonignorable drop-out, one can assess the likely effect of the nonignorability in a sensitivity analysis. Troxel et al. proposed a general index of sensitivity to nonignorability, or ISNI, to measure sensitivity of key inferences in a neighbourhood of the ignorable, missing at random (MAR) model. They derived detailed formulas for ISNI in the special case of the generalized linear model with a potentially missing univariate outcome. In this paper, we extend the method to longitudinal modelling. We use a multivariate normal model for the outcomes and a regression model for the drop-out process, allowing missingness probabilities to depend on an unobserved response. The computation is straightforward, and merely involves estimating a mixed-effects model and a selection model for the drop-out, together with some simple arithmetic calculations. We illustrate the method with three examples.

Animal Feed↗
PubMed2006

Factors influencing implementation of the Coordinated Approach to Child Health (CATCH) Eat Smart School Nutrition Program in Texas.

The purpose of this research was to evaluate factors influencing the implementation of the Coordinated Approach to Child Health (CATCH) Eat Smart School Nutrition Program in Texas using data from the CATCH dissemination study. A mail survey was sent to school foodservice personnel (N = 213) who attended a CATCH training from August 2000 through January 2002. A response rate of 40% (n = 85) was achieved. The mean score for the percentage of CATCH Eat Smart guidelines implemented was 80.44. Multivariate linear regression analysis revealed that, after adjusting for age and number of years employed in school foodservice, the following factors were significantly associated with the percentage of CATCH Eat Smart guidelines implemented: utility of CATCH and CATCH Eat Smart in meeting requirements for Coordinated School Health Programs (P = 0.006), school foodservice personnel's satisfaction with food made using the CATCH Eat Smart guidelines (P = 0.008), utility of CATCH in facilitating interschool communication about children's health (P = 0.019), and perceived student satisfaction with food made using the CATCH Eat Smart guidelines (P = 0.046). These results suggest that dissemination approaches for Coordinated School Health Programs should focus on ways to enhance program satisfaction, be consistent with legislated mandates, and increase interschool staff communication to increase program implementation by school foodservice personnel.

Adolescent↗
PubMed2006

Microbiologically documented nosocomial infections after coronary artery bypass surgery without cardiopulmonary bypass.

OBJECTIVE: This study was undertaken to evaluate the frequency, characteristics, and risk factors of microbiologically documented nosocomial infections after off-pump coronary artery bypass grafting. METHODS: A prospective cohort study was performed at Henry Dunant Hospital, Athens, Greece. It included all adult patients who underwent coronary artery bypass grafting with no valve surgery and without the use of cardiopulmonary bypass during a period of 3 years. Case patients were those with development of microbiologically documented nosocomial infections. Various variables were examined as possible risk factors for nosocomial infections. RESULTS: Twenty-one of 782 studied patients (2.7%) acquired 26 microbiologically documented nosocomial infections after off-pump coronary artery bypass grafting. Eight of 782 studied patients had pneumonia (1.02%), 7 of 782 (0.90%) had bacteremia, 4 of 782 (0.51%) had superficial wound infection at the sternotomy site, 4 of 782 (0.51%) had urinary tract infection, 2 of 782 (0.26%) had mediastinitis, and 1 of 782 (0.13%) had pressure sore infection. Twenty-one infections were monomicrobial, whereas 5 were polymicrobial. All polymicrobial infections were wound infections. There was a statistically significant difference in mortality between patients with and without nosocomial infection (23.8% vs 1.2%, P < .001). Clinical response of the infection to the treatment administered was observed in 21 of 26 episodes (80.8%) in 21 patients. A backward stepwise multivariable logistic regression model showed that independent risk factors (P < .05) associated with development of microbiologically documented nosocomial infection were arterial hypertension, previous vascular surgery, urgent operation, postoperative atrial fibrillation, number of inotropes used during and after operation, transfusion of fresh-frozen plasma during the intensive care unit stay, and intensive care unit stay until development of infection. CONCLUSION: Nosocomial infection after off-pump coronary artery bypass grafting is an uncommon but potentially life-threatening complication. The identification of independent risk factors, including arterial hypertension, associated with development of postoperative infection may help in the development of clinical strategies for the prevention, early diagnosis, and treatment of these infections.

Adult↗
PubMed2004

Salmonella Dublin infection in dairy cattle: risk factors for becoming a carrier.

Long-term Salmonella Dublin carrier animals harbor the pathogen in lymph nodes and internal organs and can periodically shed bacteria through feces or milk, and contribute to transmission of the pathogen within infected herds. Thus, it is of great interest to reduce the number of new carrier animals in cattle herds. An observational field study was performed to evaluate factors affecting the risk that dairy cattle become carrier animals after infection with Salmonella Dublin. Based on repeated sampling, cattle in 12 Danish dairy herds were categorized according to course of infection, as either carriers (n = 157) or transiently infected (n = 87). The infection date for each animal was estimated from fecal excretion and antibody responses. The relationship between the course of infection (carrier versus transiently infected) and risk factors were analyzed using a random effect multilevel, multivariable logistic regression model. The animals with the highest risk of becoming carriers were heifers infected between the age of 1 year and 1st calving, and cows infected around the time of calving. The risk was higher in the first two quarters of the year (late Winter to Spring), and when the prevalence of potential shedders in the herd was low. The risk also varied between herds. The herds with the highest risk of carrier development were herds with clinical disease outbreaks during the study period. These findings are useful for future control strategies against Salmonella Dublin, because they show the importance of optimized calving management and management of heifers, and because they show that even when the herd prevalence is low, carriers are still being produced. The results raise new questions about the development of the carrier state in cattle after infection with low doses of Salmonella Dublin.

Animals↗
PubMed1996

Long-term outcome, survival analysis, and risk stratification of dynamic cardiomyoplasty.

METHODS: To analyze the long-term outcome of dynamic cardiomyoplasty, we retrospectively studied 127 consecutive patients who underwent this procedure in Paris, France (n = 76), São Paulo, Brazil (n = 37), and Portland, Oregon (n = 14). Preoperative data were collected for patients operated on between January 1985 and June 1994 and examined with respect to effect on long-term survival. Patients had a mean age of 50 +/- 13 years and were predominantly male (82%). In 46% the cause of disease was ischemic. Concomitant operations were performed in 22 patients. RESULTS: Operative mortality was 12% (15/127). Kaplan-Meier survival +/- standard error at 1 through 5 years was 73% +/- 4%, 57% +/- 5%, 49% +/- 6%, 44% +/- 6%, and 40% +/- 7%, respectively. There was a distinct improvement at 6 months in New York Heart Association functional class (3.2 +/- 0.05 vs 1.7 +/- 0.07, p < 0.0001) and a small but significant increase in left ventricular ejection fraction (20% +/- 0.8% vs 23% +/- 1.5%, p = 0.04). Ninety-day mortality was associated with low right ventricular ejection fraction, a blunted hemodynamic response to exercise testing, and requirement for an intraaortic balloon pump at the time of the operation. Using a stepwise Cox regression method of multivariable survival analysis (n = 101), we determined that atrial fibrillation, New York Heart Association class IV, high pulmonary capillary wedge pressure, and balloon pump use were independent variables simultaneously associated with poor overall survival. When metabolic testing variables were added to this model, peak oxygen consumption eliminated both pulmonary capillary wedge pressure and functional class from the model, albeit with fewer (n = 74) patients. CONCLUSION: Dynamic cardiomyoplasty is an evolving therapy for symptomatic congestive heart failure, the results of which may be enhanced by intelligent, risk-sensitive patient selection.

Cardiomyoplasty↗
PubMed2006

(-)-Epicatechin mediates beneficial effects of flavanol-rich cocoa on vascular function in humans.

Epidemiological and medical anthropological investigations suggest that flavanol-rich foods exert cardiovascular health benefits. Endothelial dysfunction, a prognostically relevant key event in atherosclerosis, is characterized by a decreased bioactivity of nitric oxide (NO) and impaired flow-mediated vasodilation (FMD). We show in healthy male adults that the ingestion of flavanol-rich cocoa was associated with acute elevations in levels of circulating NO species, an enhanced FMD response of conduit arteries, and an augmented microcirculation. In addition, the concentrations and the chemical profiles of circulating flavanol metabolites were determined, and multivariate regression analyses identified (-)-epicatechin and its metabolite, epicatechin-7-O-glucuronide, as independent predictors of the vascular effects after flavanol-rich cocoa ingestion. A mixture of flavanols/metabolites, resembling the profile and concentration of circulating flavanol compounds in plasma after cocoa ingestion, induced a relaxation in preconstricted rabbit aortic rings ex vivo, thus mimicking acetylcholine-induced relaxations. Ex vivo flavanol-induced relaxation, as well as the in vivo increases in FMD, were abolished by inhibition of NO synthase. Oral administration of chemically pure (-)-epicatechin to humans closely emulated acute vascular effects of flavanol-rich cocoa. Finally, the concept that a chronic intake of high-flavanol diets is associated with prolonged, augmented NO synthesis is supported by data that indicate a correlation between the chronic consumption of a cocoa flavanol-rich diet and the augmented urinary excretion of NO metabolites. Collectively, our data demonstrate that the human ingestion of the flavanol (-)-epicatechin is, at least in part, causally linked to the reported vascular effects observed after the consumption of flavanol-rich cocoa.

Administration, Oral↗
PubMed2003

Primary metastatic osteosarcoma: presentation and outcome of patients treated on neoadjuvant Cooperative Osteosarcoma Study Group protocols.

PURPOSE: To determine demographic data and define prognostic factors for long-term outcome in patients presenting with high-grade osteosarcoma of bone with clinically detectable metastases at initial presentation. PATIENTS AND METHODS: Of 1,765 patients with newly diagnosed, previously untreated high-grade osteosarcomas of bone registered in the neoadjuvant Cooperative Osteosarcoma Study Group studies before 1999, 202 patients (11.4%) had proven metastases at diagnosis and therefore were enrolled onto an analysis of demographic-, tumor-, and treatment-related variables, response, and survival. The intended therapeutic strategy included pre- and postoperative multiagent chemotherapy as well as aggressive surgery of all resectable lesions. RESULTS: With a median follow-up of 1.9 years (5.5 years for survivors), 60 patients were alive, 37 of whom were in continuously complete surgical remission. Actuarial overall survival rates at 5 and 10 (same value for 15) years were 29% (SE = 3%) and 24% (SE = 4%), respectively. In univariate analysis, survival was significantly correlated with patient age, site of the primary tumor, number and location of metastases, number of involved organ systems, histologic response of the primary tumor to preoperative chemotherapy, and completeness and time point of surgical resection of all tumor sites. However, after multivariate Cox regression analysis, only multiple metastases at diagnosis (relative hazard rate [RHR] = 2.3) and macroscopically incomplete surgical resection (RHR = 2.4) remained significantly associated with inferior outcomes. CONCLUSION: The number of metastases at diagnosis and the completeness of surgical resection of all clinically detected tumor sites are of independent prognostic value in patients with proven primary metastatic osteosarcoma.

Adolescent↗
PubMed1999

Factors associated with the sexual experiences of underprivileged Mexican adolescents.

This study investigated factors associated with the sexual experiences of 523 underprivileged Mexican adolescents. Approximately 41% of the males and 24% of the females were sexually active, with more than half not using contraceptives. Multivariate logistic regression analysis revealed that sexual activity was strongly associated with age, knowledge about sexually transmitted diseases, and attitudes toward sexuality. Positive affective responsiveness in the family was associated with sexual activity and number of sexual partners. Family problem solving and roles were also associated with sexual activity. The use of contraceptives was negatively related to affective involvement between parents, and being a victim of sexual abuse was negatively associated with number of persons in the family. These findings support the notion that affective environment within the family is a factor in adolescent sexuality.

Adolescent↗
PubMed2000

Communication and information needs of a random sample of community psychiatric nurses in the United Kingdom.

This paper reports on a cross-sectional survey investigating communication and information needs of community psychiatric nurses attached to community mental health teams in the United Kingdom. Community psychiatric nurses' access to and communication with other professionals was also assessed. In total, 200 teams were randomly sampled UK-wide, and postal questionnaires were sent to community psychiatric nurses attached to these teams; 110 questionnaires were completed and returned (55% response rate). Spearman's rho, Pearson's correlation and the chi-square test were used in bivariate analyses and multiple logistic regression in multivariate analysis. Participants reported to be mainly in contact with psychiatrists (71%) and other community psychiatric nurses (52%). Eighty-four per cent and 91% reported psychiatrists and community psychiatric nurses, respectively, to be quite/extremely helpful when consulted; the proportions were lower for general practitioners and counsellors/therapists (32% and 31%, respectively). All reported lack of time and 84% reported communication problems with other professionals as barriers to their work. Although 70% reported having the necessary training/skills for managing severe cases, 76% indicated they had information needs. Being a long-serving community psychiatric nurse (OR = 4.51, 95% CI = 1.06-19.20), perceiving the discussion of cases with other professionals as less helpful (OR = 4.82, 95% CI = 1.16-20.01), being mainly in contact with other CPNs (OR= 6.72, 95% CI= 1.21-37.15), reporting not having the necessary training/skills (OR = 7.78, 95% CI = 1.37-44.25), and wanting information on mental health law (OR= 12.27, 95% CI = 1.75-86.36) were significant predictors of having information needs. This survey provided valuable information on problems facing these nurses and highlighted the need for training and for easier access to and increased communication with other professionals.

Adult↗
PubMed2006

Accurate model predicting sustained response at week 4 of therapy with pegylated interferon with ribavirin in patients with chronic hepatitis C.

Current models used to predict response to peginterferon plus ribavirin treatment, based on viral decline during the first 12 weeks of therapy, have focused on creating an early stopping rule to avoid unnecessary prolongation of therapy. We developed a multivariate model that predicted sustained virological response and nonresponse at baseline and during the first 12 weeks of therapy using collected data from 186 unselected patients with chronic hepatitis C treated with peginterferon plus ribavirin. This model employed ordinal regression with similarity least squares technology to assign the probability of a given outcome. Model variables include sex, age, prior treatment status, genotype, baseline serum alanine aminotransferase levels, histologic necroinflammation and fibrosis scores and serum hepatitis C virus RNA concentration at baseline and weeks, 4, 8, and 12. A multivariate model demonstrated high performance values at all time points. At baseline, the model demonstrated a negative predictive value (NPV) and a positive predictive value (PPV) of 91% and 95%, respectively. At week 4, these values improved to 97% and 100%, respectively, with 95% sensitivity, 89% specificity and 93% accuracy. At week 4, the model was equally efficient for naïve or previously treated patients. Internal validation demonstrated 90% PPV, 94% NPV, 95% sensitivity, 88% specificity and 92% accuracy. A week 4 stopping rule for patients with chronic hepatitis C treated with peginterferon with ribavirin might be proposed by using the model developed in our study.

Adult↗
PubMed2005

Calibration of multivariate scatter plots for exploratory analysis of relations within and between sets of variables in genomic research.

The scatter plot is a well known and easily applicable graphical tool to explore relationships between two quantitative variables. For the exploration of relations between multiple variables, generalisations of the scatter plot are useful. We present an overview of multivariate scatter plots focussing on the following situations. Firstly, we look at a scatter plot for portraying relations between quantitative variables within one data matrix. Secondly, we discuss a similar plot for the case of qualitative variables. Thirdly, we describe scatter plots for the relationships between two sets of variables where we focus on correlations. Finally, we treat plots of the relationships between multiple response and predictor variables, focussing on the matrix of regression coefficients. We will present both known and new results, where an important original contribution concerns a procedure for the inclusion of scales for the variables in multivariate scatter plots. We provide software for drawing such scales. We illustrate the construction and interpretation of the plots by means of examples on data collected in a genomic research program on taste in tomato.

Algorithms↗
PubMed2004

Multivariate analysis to separate the signal given by cross-reactants in immunoassay with sample matrix dilution.

This paper describes a new approach to achieve selectivity in an immunoassay by separating the signals given by two cross-reactive compounds present simultaneously in a complex sample matrix. The method is based on the sequential dilution of the sample containing a mixture of the two analytes, spiking each diluted sample with a reference compound, and the detection by enzyme-linked immunosorbent assay (ELISA). The obtained multivariate response was used for the individual calibrations of the assay for each of the two cross-reactants simultaneously by using principal component analysis (PCA) and partial least squares regression (PLSR) data modeling. The calibration models showed that the signal separation due the analytes 2,4-dinitrophenol (2,4-DNP) and 4-nitrophenol (4-NP) was possible with a prediction concentration error of 1.4 microM and 72 microM, respectively.

2,4-Dinitrophenol↗
PubMed2005

[Serum inflammatory related cytokines and circulating endothelial cells in patients with acute coronary syndrome].

OBJECTIVE: To study the number of CECs in patients with acute myocardial infarction (AMI) and unstable angina (UA), and to investigate its relationship with inflammatory related cytokines. METHODS: 37 patients with AMI, 12 patients with UA, and 42 health controls were studied. CECs were isolated from peripheral blood by using of immunomagnetic beads coated with antibodies against CD146. Their endothelial origin was confirmed by the positive labelling of von Willebrand Factor (vWF), CD31 and electron microscope. Annexin V-FITC/PI kit was used to measure the apoptosis of CECs. Inflammatory related cytokines were analyzed turbidimetrically or ELISA using of commercially available testing kit. RESULTS: CECs number was significantly higher in AMI and UA patients [medians (interquartile range) were 52 (28 approximately 81.5) cells/ml and 29 (18 approximately 61) cells/ml respectively] compared with health control [10.5 (6-16.5)cells/ml, P < 0.001]. After excluding diabetes patients, the number of CECs and CRP in AMI and UA group (n = 26) were still significantly higher than controls. The necrotic rate of CECs in AMI and UA was significantly higher than controls (P < 0.01). Correlation analysis revealed a significant positive correlation between CECs and CRP, or IL-6 (r = 0.677, 0.316, P = 0.000, 0.002). The multivariate linear regression analysis showed that CRP and Diabetes increased the number of CECs significantly (OR = 0.620, 0.164, 95% CI 3.985-6.751, 0.301-21.877, P = 0.000, 0.044). CONCLUSION: The mechanism responsible for the increase of CECs in acute coronary disease may be due to the vessel injury caused by inflammation.

Acute Coronary Syndrome↗
PubMed2002

Impact of multiple HPV infection on response to treatment and survival in patients receiving radical radiotherapy for cervical cancer.

To obtain information on the incidence and the clinical significance of infection with various types of the human papillomavirus (HPV) in cancer of the uterine cervix, we retrospectively examined the HPV status of 106 patients who had received radical radiotherapy for cervical cancer stages IB to IIIB. DNA was extracted from formalin-fixed, paraffin-embedded biopsies and PCR was carried out to identify HPV types 16, 18, 31, 35, 33 and 45. To detect additional HPV types, consensus PCR products were cloned and sequenced. A catalyzed signal-amplified colorimetric in situ hybridization was carried out in 84 of 106 specimens as a positive control. Response to therapy, progression-free survival (PFS) and cervical cancer-specific survival (CCSS) were the statistical endpoints. Survival analysis was carried out using univariate and multivariate analysis (Cox regression). Ninety-six patients (90.6%) were HPV-positive and 42/96 (43.7%) were positive for multiple HPV types. Eight patients had persistent disease after radiotherapy. From these 8 patients, 7 were infected with multiple HPV types and only 1 patient had an infection with a single HPV type. After a median follow up period of 50 months, patients with multiple HPV infection had a significantly shorter PFS and CCSS compared to those with single HPV infection (24.8% and 34.9% vs. 64% and 60.8%, Log rank, p < 0.01 and 0.04). In multivariate analysis, the presence of multiple HPV types (RR 1.9), node status (RR 2.3), tumor size (RR 3.2) and histologic type (RR 4.8) were independent prognostic factors of CCSS. Our results demonstrate that the presence of multiple HPV types is associated with poor response and with reduced survival in cervical cancer patients who receive radiotherapy as the primary treatment.

Adenocarcinoma↗
PubMed1990

Alternatives for using multivariate regression to adjust prospective payment rates.

Multivariate regression analysis has been used in structuring three of the adjustments to Medicare's prospective payment rates. Because the indirect-teaching adjustment, the disproportionate-share adjustment, and the adjustment for large cities are responsible for distributing approximately $3 billion in payments each year, the specification of regression models for these adjustments is of critical importance. In this article, the application of regression for adjusting Medicare's prospective rates is discussed, and the implications that differing specifications could have for these adjustments are demonstrated.

Hospitals, Rural↗
PubMed2004

Snoring and atopic disease: a strong association.

The prevalence and factors associated with snoring and habitual snoring in Asian children are largely unknown. Our objectives were to evaluate the prevalence and factors associated with snoring and habitual snoring in preschool and primary school children in Singapore. A self-response questionnaire on snoring was administered to parents of children aged 4-7 years in randomly selected preschools and primary schools in Singapore. The overall response rate was 91.3% (nt = 11,114). Snoring and habitual snoring were reported in 28.1% and in 6.0% of the children, respectively. On multivariate logistic regression analysis, snoring was significantly associated with male gender, race, atopy (asthma, allergic rhinitis, or atopic dermatitis), maternal atopy (allergic rhinitis or atopic dermatitis), maternal smoking, and breastfeeding. Habitual snoring was significantly associated with obesity (odds ratio (OR), 3.75; 95% confidence interval (CI), 1.67-8.42), allergic rhinitis (OR, 2.90; 95% CI, 2.06-4.08), atopic dermatitis (OR, 1.80; 95% CI, 1.28-2.54), maternal smoking (OR, 2.22; 95% CI, 1.09-4.53), and breastfeeding (OR, 1.49; 95% CI, 1.11-1.98). Atopy was the strongest risk factor for habitual snoring, and the effect was cumulative. The odds ratio of a child with all three atopic diseases (asthma, allergic rhinitis, and atopic dermatitis) to have habitual snoring was 7.45 (95% CI, 3.48-15.97). In conclusion, snoring and habitual snoring are common in Asian children. Atopy is strongly associated with snoring and habitual snoring. We suggest that children who are significantly atopic receive additional attention during screening for snoring, habitual snoring, and other features of obstructive sleep apnea syndrome.

Child↗
PubMed1992

The use of cusums and other techniques in modelling continuous covariates in logistic regression.

The assessment of continuous covariates singly as possible predictors in a multivariable logistic regression model is an important first step in the analysis. An approach to plotting which uses a cusum (cumulative sum) of the binary response variable is described. Extreme-deviation statistics associated with the cusum may be used to detect monotonic and non-monotonic trends. Probability plots of the covariate in the two groups defined by the response variable may help to determine the appropriate scale (transformation) of the covariate and to anticipate possible problems with the logistic fit. The ratio of the variances in the response/non-response groups is informative about the need for a quadratic term in the logistic model. Smoothed scatterplots of the response are valuable in displaying the observed and fitted values. The techniques are illustrated with two data sets.

Binomial Distribution↗