Efficient simultaneous partial envelope model in multivariate linear regression

Abstract Background Triglyceride–glucose (TyG) index, a simple surrogate marker of insulin resistance, has been reported to be associated with arterial stiffness. However, previous studies were limited by the cross-sectional design. The purpose of this study was to explore the longitudinal association between TyG index and progression of arterial stiffness. Methods A total of 6028 participants were derived from the Kailuan study. TyG index was calculated as ln [fasting triglyceride (mg/dL) × fasting glucose (mg/dL)/2]. Arterial stiffness was measured using brachial-ankle pulse wave velocity (baPWV). Arterial stiffness progression was assessed by the annual growth rate of repeatedly measured baPWV. Multivariate linear regression models were used to estimate the cross-sectional association of TyG index with baPWV, and Cox proportional hazard models were used to investigate the longitudinal association between TyG index and the risk of arterial stiffness. Results Multivariate linear regression analyses showed that each one unit increase in the TyG index was associated with a 39 cm/s increment (95%CI, 29–48 cm/s, P < 0.001) in baseline baPWV and a 0.29 percent/year increment (95%CI, 0.17–0.42 percent/year, P < 0.001) in the annual growth rate of baPWV. During 26,839 person-years of follow-up, there were 883 incident cases with arterial stiffness. Participants in the highest quartile of TyG index had a 58% higher risk of arterial stiffness (HR, 1.58; 95%CI, 1.25–2.01, P < 0.001), as compared with those in the lowest quartile of TyG index. Additionally, restricted cubic spline analysis showed a significant dose–response relationship between TyG index and the risk of arterial stiffness (P non-linearity = 0.005). Conclusion Participants with a higher TyG index were more likely to have a higher risk of arterial stiffness. Subjects with a higher TyG index should be aware of the following risk of arterial stiffness progression, so as to establish lifestyle changes at an early stage.

Download Full-text

Forecasting hyponatremia in hospitalized patients using multilayer perceptron and multivariate linear regression techniques

Concurrency and Computation Practice and Experience ◽

10.1002/cpe.6248 ◽

2021 ◽

Author(s):

Prasannavenkatesan Theerthagiri

Keyword(s):

Linear Regression ◽

Multilayer Perceptron ◽

Hospitalized Patients ◽

Multivariate Linear Regression ◽

Regression Techniques

Download Full-text

The Moderating Effect of Prosocial Behavior on the Relationship between Emotional Labor and Emotional Exhaustion of Hotel Employees: based on the Multivariate Linear Regression

2020 16th Dahe Fortune China Forum and Chinese High-educational Management Annual Academic Conference (DFHMC) ◽

10.1109/dfhmc52214.2020.00031 ◽

2020 ◽

Author(s):

Yixing Jin ◽

Cheng Lin ◽

Peiying Wu ◽

Yingda Wang

Keyword(s):

Linear Regression ◽

Prosocial Behavior ◽

Emotional Exhaustion ◽

Emotional Labor ◽

Moderating Effect ◽

Multivariate Linear Regression ◽

Hotel Employees ◽

The Relationship

Download Full-text

2011. Reaction of Clinicians to Positive Respiratory Viral Panels in Non-critically Ill Patients Without Bacterial Infection

Open Forum Infectious Diseases ◽

10.1093/ofid/ofz360.1691 ◽

2019 ◽

Vol 6 (Supplement_2) ◽

pp. S675-S675

Author(s):

Jason C Gallagher ◽

Sara Lee ◽

Leah Rodriguez ◽

Jacqueline Emily Von Bulow ◽

Kaede Ota Sullivan

Keyword(s):

Linear Regression ◽

Bacterial Infection ◽

Linear Regression Analysis ◽

Solid Organ Transplantation ◽

Retrospective Chart Review ◽

Multivariate Linear Regression ◽

Antibiotic Prescribing ◽

Antibiotic Administration ◽

Multivariate Linear Regression Analysis ◽

Solid Organ

Abstract Background Respiratory viral panels (RVPs) can detect multiple viral pathogens and give clinicians diagnostic confidence to discontinue antibiotics. However, relatively little is known about how these tests influence antibiotic prescribing in hospital settings. Methods This was a 26-month retrospective chart review of patients with positive RVPs. Hospitalized adults receiving antibiotics at the time of the RVP were included. Exclusion criteria were: ICU care, solid-organ transplantation (SOT), positive RVP for influenza, positive bacterial cultures, and antibiotic administration for bacterial infection (e.g., cellulitis). A multivariate linear regression model was created to investigate associations with longer antibiotic use after a positive RVP. Results 1,346 patients were screened and 242 met inclusion criteria. Primary reasons for exclusion were SOT, ICU, and influenza diagnosis. Patients were a median age of 60.5 years [IQR 51,70] and 35.5% were men. The median length of stay (LOS) was 4 days [IQR 3.6]. 233 patients (6.3%) had chest radiology performed, of which 71 (30.4%) had possible pneumonia noted. 50 (20.7%) were immunocompromised (IC). 199 (82.2%) had a history of pulmonary disease, most commonly COPD. Rhinovirus was isolated in 156 patients (64.5%), followed by metapneumovirus (35, 14.9%) and RSV (32, 13.3%). Antibiotics were given for a median total of 3 days [IQR 3.6]; they were discontinued within 24 hours of the RVP result in 107 patients (44.2%). Conclusion In this population of patients with viral infection and no discernable bacterial infection, 44.2% of patients had antibiotics discontinued within 24 hours of RVP results. On multivariate linear regression analysis, younger age, longer LOS, and IC status were associated with longer antibiotic duration after a positive RVP. A comparison with patients with negative RVP results could reveal if the test prompted discontinuation. Disclosures All authors: No reported disclosures.

Download Full-text

Correlation between FA and ADC, number and length of the periprostatic neurovascular fibers

Urologia Journal ◽

10.1177/03915603211063769 ◽

2021 ◽

pp. 039156032110637

Author(s):

Valerio Di Paola ◽

Angelo Totaro ◽

Giacomo Avesani ◽

Benedetta Gui ◽

Andrea Boni ◽

...

Keyword(s):

Regression Analysis ◽

Linear Regression ◽

Negative Correlation ◽

Multivariate Regression ◽

Linear Regression Analysis ◽

Multivariate Linear Regression ◽

Multivariate Linear Regression Analysis ◽

Independent Variables ◽

Fiber Tracts ◽

Good Agreement

Purpose: Our aim was to explore the relation between FA and ADC, number and length of the periprostatic neurovascular fibers (PNF) by means of 1.5 T Diffusion Tensor Imaging (DTI) imaging through a multivariate linear regression analysis model. Methods: For this retrospective study, 56 patients (mean age 63.5 years), who underwent 1.5-T prostate MRI, including DTI, were enrolled between October 2014 and December 2018. Multivariate regression analysis was performed to evaluate the statistically significant correlation between FA values (dependent variable) and ADC, the number and the length of PNF (independent variables), if p-value <0.05. A value of 0.5 indicated poor agreement; 0.5–0.75, moderate agreement; 0.75–0.9, good agreement; 0.61–0.80, good agreement; and 0.9–1.00, excellent agreement. Results: The overall fit of the multivariate regression model was excellent, with R2 value of 0.9445 ( R2 adjusted 0.9412; p < 0.0001). Multivariate linear regression analysis showed a statistically significant correlation ( p < 0.05) for all the three independent variables. The r partial value was −0.9612 for ADC values ( p < 0.0001), suggesting a strong negative correlation, 0.4317 for the number of fiber tracts ( p < 0.001), suggesting a moderate positive correlation, and −0.306 for the length of the fiber tracts ( p < 0.05), suggesting a weak negative correlation. Conclusions: Our multivariate linear regression model has demonstrated a statistically significant correlation between FA values of PNF with other DTI parameters, in particular with ADC.

Download Full-text