Nonlinear Least Squares and Maximum Likelihood Estimators for Efficient Multivariate Regression Analysis with the Item Count Technique

2000 ◽  
Author(s):  
Magid Maatallah
Keyword(s):  
Regression Analysis ◽  
Maximum Likelihood ◽  
Least Squares ◽  
Multivariate Regression ◽  
Maximum Likelihood Estimators ◽  
Nonlinear Least Squares ◽  
Multivariate Regression Analysis ◽  
Item Count Technique

scholarly journals 1574. Multivariate Regression Analysis to Determine Independent Predictors of Treatment Outcomes in the RESTORE-IMI 2 Trial

2020 ◽  
Vol 7 (Supplement_1) ◽  
pp. S785-S786
Author(s):  
Robert Tipping ◽  
Jiejun Du ◽  
Maria C Losada ◽  
Michelle L Brown ◽  
Katherine Young ◽  
...  
Keyword(s):  
Regression Analysis ◽  
Clinical Response ◽  
Treatment Outcomes ◽  
Multivariate Regression ◽  
Multivariate Regression Analysis ◽  
Apache Ii Score ◽  
Double Blind ◽  
Mitt Population ◽  
Study Results ◽  
All Cause Mortality

Abstract Background In the RESTORE-IMI 2 trial, imipenem/cilastatin/relebactam (IMI/REL) was non-inferior to PIP/TAZ for treating hospital-acquired/ventilator-associated bacterial pneumonia (HABP/VABP) in the primary endpoint of Day 28 all-cause mortality (D28 ACM) and the key secondary endpoint of clinical response (CR) at early follow-up (EFU; 7-14 d after end of therapy). We performed a multivariate regression analysis to determine independent predictors of treatment outcomes in this trial. Methods Randomized, controlled, double-blind, phase 3, non-inferiority trial comparing IMI/REL 500 mg/250 mg vs PIP/TAZ 4 g/500 mg, every 6 h for 7-14 d, in adult patients (pts) with HABP/VABP. Stepwise-selection logistic regression modeling was used to determine independent predictors of D28 ACM and favorable CR at EFU, in the MITT population (randomized pts with ≥1 dose of study drug, except pts with only gram-positive cocci at baseline). Baseline variables (n=19) were pre-selected as candidates for inclusion (Table 1), based on clinical relevance. Variables were added to the model if significant (p < 0.05) and removed if their significance was reduced (p > 0.1) by addition of other variables. Results Baseline variables that met criteria for significant independent predictors of D28 ACM and CR at EFU in the final selected regression model are in Fig 1 and Fig 2, respectively. As expected, APACHE II score, renal impairment, elderly age, and mechanical ventilation were significant predictors for both outcomes. Bacteremia and P. aeruginosa as a causative pathogen were predictors of unfavorable CR, but not of D28 ACM. Geographic region and the hospital service unit a patient was admitted to were found to be significant predictors, likely explained by their collinearity with other variables. Treatment allocation (IMI/REL vs PIP/TAZ) was not a significant predictor for ACM or CR; this was not unexpected, since the trial showed non-inferiority of the two HABP/VABP therapies. No interactions between the significant predictors and treatment arm were observed. Conclusion This analysis validated known predictors for mortality and clinical outcomes in pts with HABP/VABP and supports the main study results by showing no interactions between predictors and treatment arm. Table 1. Candidate baseline variables pre-selected for inclusion Figure 1. Independent predictors of greater Day 28 all-cause mortality (MITT population; N=531) Figure 2. Independent predictors of favorable clinical response at EFU (MITT population; N=531) Disclosures Robert Tipping, MS, Merck & Co., Inc. (Employee, Shareholder) Jiejun Du, PhD, Merck & Co., Inc. (Employee, Shareholder) Maria C. Losada, BA, Merck & Co., Inc. (Employee, Shareholder) Michelle L. Brown, BS, Merck & Co., Inc. (Employee, Shareholder) Katherine Young, MS, Merck & Co., Inc. (Employee, Shareholder)Merck & Co., Inc. (Employee, Shareholder) Joan R. Butterton, MD, Merck & Co., Inc. (Employee, Shareholder) Amanda Paschke, MD MSCE, Merck & Co., Inc. (Employee, Shareholder) Luke F. Chen, MBBS MPH MBA FRACP FSHEA FIDSA, Merck & Co., Inc. (Employee, Shareholder)Merck & Co., Inc. (Employee, Shareholder)

Epicardial fat thickness as arterial hypertension predictor in normotensive patients with abdominal obesity

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
T Kuznetsova ◽  
M Druzhilov
Keyword(s):  
Blood Pressure ◽  
Regression Analysis ◽  
Blood Glucose ◽  
Waist Circumference ◽  
Arterial Hypertension ◽  
Multivariate Regression ◽  
Fasting Blood Glucose ◽  
Multivariate Regression Analysis ◽  
Epicardial Fat Thickness ◽  
Fat Thickness

Abstract Objective Arterial hypertension (HTN) is one of the most common diseases associated with obesity. Visceral obesity (VO) with dysfunctional visceral adipose tissue plays the main role in obesity induced HTN. Direct criteria of VO including echocardiographic epicardial fat thickness (EFT) may become an additional predictor of HTN. Purpose The aim was to assess the role of echocardiographic EFT (EEFT) as a predictor of HTN in normotensive patients with abdominal obesity (AO). Methods 526 normotensive men (according to ambulatory blood pressure monitoring (ABPM) without therapy) with AO (waist circumference (WC) >94 cm) and SCORE <5%, without cardiovascular diseases and diabetes mellitus were examined (age 45.1±5.0 years). The lipid and glucose profiles, creatinine, uric acid and C-reactive protein blood levels, albuminuria evaluation, echocardiography, carotid ultrasound, bifunctional ABPM were performed. The values of EEFT ≥75 percentile for persons 35–45 years and 46–55 years were 4.8 mm and 5.8 mm respectively. These values used as epicardial VO criteria. Patients with subclinical carotid atherosclerosis due to the lipid-lowering therapy administration (n=98) were excluded from the follow-up. Re-examination with ABPM was conducted on average through 46.3±5.1 months. Data were summarized as mean ± standard error, statistical analysis conducted with paired two-tailed t-tests, Pearson χ2 criterion and multivariate regression analysis. Results Data of 406 persons were available for analysis. HTN as average daily blood pressure ≥130/80 mm Hg was detected in 157 (38.7%) patients. These patients were characterized by initially higher values of age (45.9±4.6 years vs 44.3±4.9 years, p<0.001), waist circumference (106.9±7.3 cm vs 104.2±7.3 cm, p<0.001), body mass index (BMI) (32.0±3.3 kg/m2 vs 30.9±3.2 kg/m2, p<0.001), average daily systolic and diastolic blood pressure (120.7/74.5±4.6/3.4 mm Hg vs 118.2/73.2±5.5/3.9 mm Hg, p<0.001), EEFT (5.2±0.7 mm vs 4.4±1.0 mm, p<0.001). The epicardial VO was initially detected in 95 (23.3%) patients. In patients with HTN the initial prevalence of epicardial VO was greater (58.0% vs 23.3%, p<0.001). As predictors for the multivariate regression analysis the clinical and laboratory examinations data and EEFT were evaluated. According to the results a mathematical model for estimating the probability HTN was obtained: 0.696*fasting blood glucose + 0.198*systolic BP + 2.844*EFT – 40.166 (constant). Among these predictors EEFT was characterized by the highest standardized regression coefficient (0.302, p<0.001) (0.295, p<0.01 for fasting blood glucose, 0.035, p<0.001 for systolic BP). The Hosmer-Lemeshow test value was 0.863, the total percentage of correct classifications was 86%, the area under the ROC-curve was 0.913. Conclusions EEFT (4.8 mm for persons 35–45 years and 5.8 mm for persons 46–55 years) may be an additional predictor of HTN in normotensive patients with AO. Funding Acknowledgement Type of funding source: None

Arterial stiffness could reflect increased cardiac load and reduced pulmonary function in the general population

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
S Murai ◽  
T Sugiura ◽  
Y Dohi ◽  
H Takase ◽  
T Mizoguchi ◽  
...  
Keyword(s):  
Regression Analysis ◽  
General Population ◽  
Arterial Stiffness ◽  
Pulmonary Function ◽  
Multivariate Regression ◽  
Troponin I ◽  
Augmentation Index ◽  
Smoking Status ◽  
Multivariate Regression Analysis ◽  
The Other

Abstract Background Pulmonary function is known to decrease with age and reduced pulmonary function has been reported to be associated with all-cause mortality and cardiovascular death. The association between pulmonary impairment and atherosclerosis was reported previously but has not been investigated sufficiently in the general population. Purpose We hypothesized that arterial stiffness could reflect increase of cardiac load and reduced pulmonary function. The present study aimed to investigate whether increased cardiac load and reduced pulmonary function could affect arterial stiffness in the general population. Methods Subjects undergoing their health check-up were enrolled. Plasma B-type natriuretic peptide (BNP) levels and serum high-sensitivity cardiac troponin I (hs-cTnI) levels were measured to evaluate cardiac load and myocardial damage. Radial augmentation index (rAI) was measured to investigate arterial stiffness using HEM-9000AI device. Subjects with an ST-T segment abnormality on the electrocardiogram, renal insufficiency, cancer, active inflammatory disease, or a history of cardiovascular events and pulmonary disease were excluded. Pulmonary function was assessed using spirometry by calculating forced vital capacity (FVC) as a percentage of predicted value (FVC%-predicted), forced expiratory volume in 1 second (FEV1) as a percentage of predicted value (FEV1%-predicted), and the ratio of FEV1 to FVC (FEV1/FVC). Results A total of 1100 subjects aged 57 years were enrolled and their median values of BNP and hs-cTnI were 15.5 and 2.3 pg/ml. The levels of rAI were significantly associated with the levels of BNP after adjustment for possible confounders in multivariate regression analysis, but were not with the levels of hs-TnI. While the parameters of pulmonary function were inversely associated with the levels of rAI and hs-cTnI after adjustment for possible confounders in the multivariate regression analysis, but not with the levels of BNP. The other multivariate regression analyses where BNP, hs-cTnI, parameters of pulmonary function, and the other possible factors were simultaneously included as independent variables revealed that the BNP levels and the FVC%-predicted or FEV1%-predicted, besides age, gender, smoking status, body mass index, blood pressure, heart rate, creatinine, fasting plasma glucose, and triglyceride, were significantly associated with the levels of rAI. Conclusions The significant associations of rAI with BNP and pulmonary function were revealed in the general population. These findings support that arterial stiffness could reflect increased cardiac load and reduced pulmonary function, in apparently healthy individuals. Funding Acknowledgement Type of funding source: None

Relation of Fatigue with Alexithymia and Depression in Psychiatric Outpatients

2007 ◽  
Vol 105 (2) ◽  
pp. 539-545
Author(s):  
Thomas N. Wise ◽  
Michael J. Sheridan
Keyword(s):  
Primary Care ◽  
Regression Analysis ◽  
Psychosocial Stress ◽  
Multivariate Regression ◽  
Multivariate Regression Analysis ◽  
Psychiatric Outpatients ◽  
The Mean

The complaint of fatigue is common in community, primary care, and psychiatric settings. Fatigue is often associated with depression and psychosocial stress. This report investigated the role of alexithymia and depression in fatigue as reported in a sample of 151 psychiatric outpatients (75 men and 76 women) who completed all scales. The mean age of the sample was 45.5 yr. ( SD = 12.5), and mean education was 16.2 yr. ( SD = 2.4). Fatigue was inversely correlated with education (–.16) and positively correlated with depression (.44), anxiety (.30), and alexithymia (.35). However, in a multivariate regression analysis, only depression and alexithymia remained significant ( p ≤ .01).

In Hyperacute Recanalization Therapy, Early Hospital Arrival Improves Outcome in Patients with Large Artery Occlusion

2018 ◽  
Vol 79 (5-6) ◽  
pp. 335-341
Author(s):  
Junya Aoki ◽  
Kentaro Suzuki ◽  
Satoshi Suda ◽  
Seiji Okubo ◽  
Masahiro Mishina ◽  
...  
Keyword(s):  
Regression Analysis ◽  
Clinical Outcome ◽  
Multivariate Regression ◽  
Intravenous Thrombolysis ◽  
Multivariate Regression Analysis ◽  
Artery Occlusion ◽  
Favorable Outcome ◽  
Large Artery ◽  
Independent Factor ◽  
Hospital Arrival

Background: It is unknown whether the effect of onset-­­to-door (OTD) time on clinical outcomes differs between ­patients with and without large artery occlusion (LAO) who undergo hyperacute recanalization therapy. Methods: Hyperacute recanalization therapy includes intravenous thrombolysis tissue-plasminogen activator (tPA), and endovascular therapy (EVT). Favorable clinical outcome was defined as modified Rankin Scale of ≤2 at discharge. Results: Among 164 patients, 117 (71%) patients received tPA, 86 (52%) received EVT, and 39 (24%) received tPA and EVT. One hundred and fifteen patients (70%) were classified into the LAO group and 49 (30%) into the non-LAO group. In the total cohort, multivariate regression analysis showed OTD time (OR 0.809 [95% CI 0.693–0.944], p = 0.007) was an independent factor related to the favorable outcome. Similarly, among patients with LAO, OTD was an independent negative factor for the favorable outcome (0.779 [0.646–0.940], p = 0.009). On the contrary, OTD was not associated with the favorable outcome (1.5 [0.7–2.5] vs. 1.7 [1.1–3.2], p = 0.155) in patients without LAO. This was confirmed with multivariate regression analysis, which did not show OTD to be an independent factor for the favorable outcome (0.900 [0.656–1.236], p = 0.516). Conclusion: The effect of early hospital arrival on clinical outcome differed between patients with and without LAO.

Sign in / Sign up

Export Citation Format

Share Document