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

2021 ◽  
Author(s):  
Prasannavenkatesan Theerthagiri
Keyword(s):  
Linear Regression ◽  
Multilayer Perceptron ◽  
Hospitalized Patients ◽  
Multivariate Linear Regression ◽  
Regression Techniques

scholarly journals 729. Comparing Length of Stay and Clinical Outcomes for Hospitalized Patients at Bridgeport Hospital who Received Baloxavir Marboxil (BM) or Oseltamivir Phosphate (OP) During the 2018–2019 Influenza Season

2019 ◽  
Vol 6 (Supplement_2) ◽  
pp. S326-S326
Author(s):  
Arun C Nachiappan ◽  
Wei-Teng Yang
Keyword(s):  
Linear Regression ◽  
Length Of Stay ◽  
Airway Disease ◽  
Hospitalized Patients ◽  
T Test ◽  
Multivariate Linear Regression ◽  
Ethnic Composition ◽  
Categorical Variables ◽  
Continuous Variables ◽  
Viral Mutant

Abstract Background BM has been approved for the management of acute uncomplicated influenza in otherwise healthy individuals between age 12 and 64, and found to have a greater reduction in viremia. The original trial excluded hospitalized patients and those with co-morbidities. Methods This is a single-center, retrospective analysis of hospitalized patients diagnosed with influenza between October 1, 2018 and March 31, 2019. This study excluded those diagnosed before the addition of BM to the hospital formulary; those who were not treated with antivirals, treated before admission, or treated with both antivirals; those younger than 12 years old; and those who remain hospitalized. The relationship between length of stay and antiviral used was ascertained using t-test and multivariate linear regression. Due to heterogeneity in reasons for hospitalization, analysis was stratified by the main reasons for hospitalization. T-test and Wilcoxon’s rank-sum test were used for continuous variables, and Pearson’s chi-squared test was used for categorical variables. The significance level was 0.05. Results The study population (n = 145) has a mean age of 66.5 years; of whom, 43% are male. In terms of patient characteristics, those treated with BM (n = 105) vs. OP (n = 40) were older, less frequently admitted to ICU and of differing ethnic composition. The length of stay was similar in those treated with BM vs. OP in both univariate and multivariate linear regression (5.5 (5.3) vs. 8.2 (11.4) days, P = 0.33). In addition, the length of stay was similar in those treated with BM vs. OP when stratified by reasons for hospitalization: pneumonia/bronchitis (6.6 (7.1) vs. 8.2 (9.2) days, P = 0.43), obstructive airway disease exacerbation (5.5 (4.8) vs. 4.8 (8.0) days, P = 0.56), elderly with multiple co-morbidities (5.0 (4.0) vs. 3.4 (6.8) days, P = 0.63), reactive airway disease (4.1 (4.8) vs. 7.4 (1.5) days, P = 0.27) or congestive heart failure exacerbation (9.8 (9.0) vs. 5.6 (5.0) days, P = 0.43). Conclusion In hospitalized patients with co-morbidities diagnosed with influenza, there was no difference in length of stay in those who received BM vs. OP. This highlights the need to clarify the role of BM in this population, particularly given its comparable symptom reduction, greater cost, and the emergence of PA138T viral mutant. Disclosures All authors: No reported disclosures.

scholarly journals Association between triglyceride-glucose index and risk of arterial stiffness: a cohort study

2021 ◽  
Vol 20 (1) ◽  
Author(s):  
Shouling Wu ◽  
Luli Xu ◽  
Mingyang Wu ◽  
Shuohua Chen ◽  
Youjie Wang ◽  
...  
Keyword(s):  
Growth Rate ◽  
Linear Regression ◽  
Arterial Stiffness ◽  
Multivariate Linear Regression ◽  
Annual Growth ◽  
Annual Growth Rate ◽  
Cross Sectional ◽  
Tyg Index ◽  
Longitudinal Association ◽  
The Cross

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.

Correlation Between Gestures’ Qualitative Properties and Usa- bility metrics

2020 ◽  
Vol 64 (1) ◽  
pp. 726-730
Author(s):  
Daniela Chanci ◽  
Naveen Madapana ◽  
Glebys Gonzalez ◽  
Juan Wachs
Keyword(s):  
Linear Regression ◽  
User Satisfaction ◽  
Completion Time ◽  
User Study ◽  
Task Completion ◽  
Time Error ◽  
Qualitative Properties ◽  
Regression Techniques ◽  
Overall Efficiency ◽  
Usability Metrics

The choice of best gestures and commands for touchless interfaces is a critical step that determines the user- satisfaction and overall efficiency of surgeon computer interaction. In this regard, usability metrics such as task completion time, error rate, and memorability have a long-standing as potential entities in determining the best gesture vocabulary. In addition, some previous works concerned with this problem have utilized qualitative measures to identify the best gesture. In this work, we hypothesize that there is a correlation between the qualitative properties of gestures (v) and their usability metrics (u). Therefore, we conducted an experiment with linguists to quantify the properties of the gestures. Next, a user study was conducted with surgeons, and the usability metrics were measured. Lastly, linear and non-linear regression techniques were used to find the correlations between u and v. Results show that usability metrics are correlated with the gestures’ qualitative properties ( R2 = 0.4).

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

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.

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

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.

scholarly journals Weight and height prediction of immobilized patients

2006 ◽  
Vol 19 (6) ◽  
pp. 655-661 ◽  
Author(s):  
Estela Iraci Rabito ◽  
Gabriela Bergamini Vannucchi ◽  
Vivian Marques Miguel Suen ◽  
Laércio Lopes Castilho Neto ◽  
Júlio Sérgio Marchini
Keyword(s):  
Linear Regression ◽  
Multiple Linear Regression ◽  
Hospitalized Patients ◽  
Anthropometric Measurements ◽  
Abdominal Circumference ◽  
Calf Circumference ◽  
Mean Error ◽  
Arm Circumference ◽  
Height Prediction ◽  
The One

OBJECTIVE: To confirm the adequacy of the formula suggested in the literature and/or to develop appropriate equations for the Brazilian population of immobilized patients based on simple anthropometric measurements. METHODS: Hospitalized patients were submitted to anthropometry and methods to estimate weight and height of bedridden patients were developed by multiple linear regression. RESULTS: Three hundred sixty eight persons were evaluated at two hospital centers and five weight-predicting and two height-predicting equations were developed from the measurements obtained. Among the new equations developed, the simplest one for weight estimate was: Weight (kg) = 0.5759 x (arm circumference, cm) + 0.5263 x (abdominal circumference, cm) + 1.2452 x (calf circumference, cm) -4.8689 x (Sex, male = 1 and female = 2) -32.9241 (r = 0.94); and the one for height estimate was: Height (cm) = 58.6940 - 2.9740 x (Sex) -0.0736 x (age, years) + 0.4958 x (arm length, cm) + 1.1320 x (half- span, cm) (r = 0.88). The estimates thus calculated did not differ significantly from actual measurements, with p = 0.94 and 0.89 and a mean error of 6.0 and 2.1% for weight and height, respectively. CONCLUSION: We suggest that these equations can be used to estimate the weight and height of bedridden patients when necessary or when these parameters cannot be measured with a scale and a stadiometer.

Sign in / Sign up

Export Citation Format

Share Document