Disease relevance of Regression Analysis

• Multiple regression analyses showed that consumption of dairy foods and eggs, but not body weight, was associated with the lipoprotein and cholesterol findings [1].
• Cox regression analysis showed that for each 59.48-micromol/L increase in uric acid level, cardiovascular mortality and ischemic heart disease mortality increased [2].
• Cox regression analysis indicated that only serum bilirubin and histologic stage were associated independently with time to development of esophageal varices [3].
• Multivariate regression analysis in a randomly selected training subset of 217 patients demonstrated that the combination of uric acid, alkaline phosphatase, lactate dehydrogenase, external lymphadenopathy, and age had the strongest predictive relation to survival time [4].
• Stepwise regression analysis revealed that the most important factor related to lymph node metastasis was the expression of CCR7 [5].

Psychiatry related information on Regression Analysis

• Multiple regression analysis revealed both the frequency of physical activity and smoking status to be independent positive and negative factors, respectively, for the HDL cholesterol value [6].
• 1. Best-subset regression analysis and receiver operating characteristic analysis were used to select a subset of items from the structured interview that most efficiently predicted PTSD as diagnosed in the full-length interview [7].
• Furthermore, Cox regression analysis showed that losartan (21% risk reduction) and new-onset AF both independently predicted stroke even when adjusting for traditional risk factors [8].
• The association was consistent across tertiles of fractional excretion of lithium, was independent of age, smoking, alcohol consumption and sodium excretion (taken as an index of sodium intake) and persisted in multiple regression analysis [9].
• Baseline depression scores significantly predicted severity of depressive symptoms during PEG IFN/ribavirin treatment (simple regression analysis: Y = 0.55X + 32.7, p < .0001) [10].

High impact information on Regression Analysis

• Adjustments were made by Cox regression analysis for age, sex, education, smoking status, and the use or nonuse of salicylates, histamine Hz-receptor antagonists, antihypertensive agents, and hypoglycemic agents [11].
• Multiple regression analysis revealed direct correlations between the hematocrit and the serum albumin concentration (P = 0.009) and between the hematocrit and the urea-reduction value (P = 0.012) after adjustment for other factors [12].
• Multivariate regression analysis demonstrated that an increased risk of acute GVHD was associated with an elevated serum creatinine concentration (P = 0.006) and treatment with cyclosporine and prednisone alone (P = 0.02) [13].
• Indeed, regression analysis of data obtained on the control night indicated that the 8 a.m. plasma glucose concentration was directly related to the nocturnal glucose nadir (r = 0.761, P = 0.011) [14].
• Proportional-hazards stepwise regression analyses indicated that only propylthiouracil treatment, prothrombin time, hemoglobin levels, and mean daily urinary alcohol levels significantly affected mortality [15].

Chemical compound and disease context of Regression Analysis

• In multiparametric regression analysis, the occurrence of grade 4 neutropenia was associated with high doses of cyclophosphamide (odds ratio ¿OR, 19.8; P =.008) and high levels of soluble p75-R-TNF (OR, 8.52; P =.001) [16].
• Cox regression analysis revealed baseline serum creatinine (odds ratio 2.00; 95% confidence interval [CI] 1.61 to 2.49; P < 0.001) and ADMA (odds ratio 1.47; 95% CI 1.12 to 1.93 for an increment of 0.1 mumol/L; P < 0.006) as independent predictors of disease progression [17].
• Multivariate regression analysis showed that the serum levels of bone resorption and bone formation markers in MPHD patients were correlated with the hydrocortisone, thyroxine, and testosterone replacement doses [18].
• In a stepwise model of multiple regression analysis using estradiol and free and total testosterone as independent variables, estradiol was the only significant predictor of histomorphometric indices of bone formation and bone resorption in SHAM and ORX rats [19].
• Cox regression analyses showed a relative risk for infection-free catheter survival of 0.10 (95% CI, 0.01 to 0.92) in the gentamicin group when adjusted for gender, race, diabetes mellitus, catheter malfunction, and hemoglobin (P = 0.042) [20].

Biological context of Regression Analysis

• Multivariate Cox regression analysis that included these and six other potential confounding variables revealed a significant association (P less than 0.001) between good HLA-A and B matching and increased graft survival [21].
• In regression analysis, the observed abnormalities in lipolysis regulation correlated in an independent way with the degree of glucose intolerance (r = -0.67) and beta 2-receptor number with insulin resistance (r = 0.67) [22].
• Multiple regression analysis confirmed that in-treatment diastolic pressure was not independently associated with final serum creatinine [23].
• Multiple regression analysis showed that the best three predictors of blood loss in surgery and transfusion requirements were the bleeding time, glass bead platelet retention, and the use of desmopressin [24].
• MAIN OUTCOME MEASURES: Random regression analyses of self-reported frequency of cocaine use and results of urine toxicology screens [25].

Anatomical context of Regression Analysis

• Receiver operating characteristic regression analysis indicated that both white blood cell count and percentage of polymorphonuclear cells were found to contribute independent diagnostic information but lactate dehydrogenase did not [26].
• When all fatty acids were included in a second regression analysis, low concentrations of dihomo-gamma-linolenic (20:3n6) acid in adipose tissue showed a more significant relation with new CHD than did linoleic acid [27].
• Cox regression analyses evaluated risk strata, age, gender, and the numbers of nucleated cells, CD3(+) T cells, CD34(+) hematopoietic cells, and CD4(bright) cells as covariates for EFS, relapse, and nonrelapse mortality [28].
• In multivariate regression analysis for relapse-free survival (RFS) and overall survival (OS), corrected for the contribution of age/menopausal status, tumor size, the number of positive lymph nodes, and steroid-hormone-receptor status, catB and catL were significant predictors of the rates of relapse and death (all, P < .01) [29].
• Cox regression analysis identified variceal size, cherry-red spots, serum bilirubin and congestion index of the portal vein (the ratio of portal vein [cross-sectional area] and portal blood flow velocity) as the only independent predictors of first variceal hemorrhage [30].

Associations of Regression Analysis with chemical compounds

• Multiple regression analyses that included height and weight showed that only small-bowel length and the rate of clearance from plasma were independently related to the required oral dose of cyclosporine [31].
• Regression analysis indicated increased sensitivity of vasopressin osmoreceptors in the older group, although this difference was not statistically significant [32].
• Multiple regression analysis of these changes indicates that increased plasma HDL levels occur when plasma triglyceride level is decreased, cigarette smoking is reduced, and habitual alcohol intake is increased [33].
• The correlation between calcium intake (range, 260-2,035 mg/d) and rate of change in BMD was not significant at the midradius (r = 0.06) or lumbar spine (r = 0.08), even after adjusting for age, menopausal status, and serum estrogen levels by multiple regression analysis [34].
• By regression analysis, after adjustment for ethnicity, there was a significant dose-response relationship between cotinine and the number of cigarettes smoked per day by the mother, both in the children (partial r2 = .23; P = .01) and in the mothers (partial r2 = .22; P = .01) [35].

Gene context of Regression Analysis

• The logrank test and proportional hazards regression analysis were used to calculate the probability that EGFR and TGF-alpha levels were associated with disease-free survival (i.e., no recurrence of cancer) and cause-specific survival (i.e., patients do not die of their disease) [36].
• In multivariate regression analysis, S100A4 expression emerged as a highly significant independent parameter (P < 0.001) with the highest relative-risk factor among other covariates [37].
• In multivariate regression analysis, the only independent predictors of relapse-free survival (RFS) were VEGF, uPA, and lymph node status [38].
• Cox regression analyses demonstrated that COX-2 expression was the strongest predictor of outcome, independent of all other variables [39].
• Univariate Kaplan-Meier analysis and multivariate Cox proportional hazard regression analysis adjusted for standard prognostic indicators were performed to assess the prognostic relevance of CEACAM1 expression [40].

Analytical, diagnostic and therapeutic context of Regression Analysis

• Event-free survival and proportional hazards regression analyses confirmed that overexpression of P-glycoprotein at clinical onset is the most important adverse prognostic factor for high-grade OS patients treated with these chemotherapy protocols [41].
• In multivariate logististic regression analysis, the most powerful independent predictor for excellent outcome was improved brain perfusion: hypoperfusion volume on mean transit time (MTT) map decrease >30% from baseline to 2-hour post tPA scan (p=0.009; odds ratio [95% confidence interval], 20.7 [2.1-203.9]) [42].
• Cox's regression analysis identified three variables that independently correlated with HCC: age, serum levels of platelets, and liver firmness on physical examination [43].
• A stepwise multiple regression analysis showed that the different muscle morphology measurements could account for 3/4 of the variation in the fasting serum insulin concentration, the fasting insulin/glucose ratio, and the blood glucose concentration at 120 min in the OGTT [44].
• OBJECTIVE: Using 6-[(18)F]fluoro-L-dopa (FDOPA) and [(18)F]fluorodeoxyglucoce (FDG) positron emission tomography (PET), multiple regression analyses were performed to determine the specific brain regions that are related to cognitive and motor symptoms in nondemented patients with Parkinson's disease [45].

References