Search results for " Regression"
showing 10 items of 1835 documents
Alternating model trees
2015
Model tree induction is a popular method for tackling regression problems requiring interpretable models. Model trees are decision trees with multiple linear regression models at the leaf nodes. In this paper, we propose a method for growing alternating model trees, a form of option tree for regression problems. The motivation is that alternating decision trees achieve high accuracy in classification problems because they represent an ensemble classifier as a single tree structure. As in alternating decision trees for classification, our alternating model trees for regression contain splitter and prediction nodes, but we use simple linear regression functions as opposed to constant predicto…
Helicobacter pyloriinfection among children with gastrointestinal symptoms: a high prevalence of infection among patients with reflux oesophagitis
2007
Aim: To investigate the link between H.pylori infection and dyspepsia in children, and association with reflux oesophagitis. Patients and Methods: H.pylori status was detected by rapid urease test and/or culture in 130 consecutive symptomatic children coming for upper gastrointestinal endoscopy: 40 – aged 8–12 years (55% boys); 90 – aged 13–18 years (21% boys). Endoscopic findings were analyzed. H.pylori prevalence in the age group 8–12 years was compared to the prevalence among 55 asymptomatic children, aged 7–12 years (13C–urea breath test). Statistical analysis: χ2 test, Fisher's test, and logistic regression analysis. Results: The prevalence of H.pylori infection among patients with gas…
Predictors for early readmission after COPD exacerbation
2019
Aim: Identify predictors for early readmission in patients with COPD and severe exacerbation. Material and methods: Prospective study (July 2017-June 2018) that included all patients hospitalized for an acute exacerbations of COPD. Demographic date, clinical and spirometric parameters, arterial blood gases, length of stay, and evolutive parameters were collected. We used univariate and multivariate statistical techniques to identify risks for readmission. Results: 278 consecutive patients were enrolled. During the follow-up 31 (11%) patients were admitted within 30 days of discharge (early readmission). Univariate analysis showed that FEV1 (p=0.02), FEV1 (%) (p=0.01), total dose of steroids…
A Statistical Study to Analyze the Impact of External Weather Change on Chronic Pulmonary Infection in South Norway with Machine Learning Algorithms
2021
In this paper, we analyzed the holistic impact of external weather on chronic pulmonary infection in the Agder region with traditional machine learning algorithms. Millions of people are diagnosed with Chronic Obstructive Pulmonary Disease (COPD). Our study is dedicated in the Agder region, the Southern part of Norway. Norway has four seasons – winter (December-February), late winter/spring (March-May), Summer (June-August), and Autumn (September-November) in a year with average annual temperature approx. 7.5 °C | 45.5 °F and an annual rainfall of 1260 mm or 49.6 in. in Kristiansand. As predicted by the World Health Organization (WHO), in 2016, Norway suffered from 8% mortality due to c(1)h…
Inhaled steroids and prevalence of osteoporosis in chronic obstructive pulmonary disease: Data from the DACCORD cohort
2020
Introduction: Osteoporosis is a frequent COPD comorbidity with age, female gender, smoking, immobility and the use of oral steroids (OCS) as common risk factors. The role of inhaled steroids (ICS) is still under debate. Methods: Baseline data from the real life cohort DACCORD were analyzed. The diagnosis of osteoporosis was based on patients’ reports of physician-based diagnoses. Associations of ICS exposure at time of inclusion and osteoporosis were examined by group comparisons and multivariable logistic regression analyses with age, gender, smoking, exacerbation history (EH) and FEV1% as covariates. To avoid interactions with other steroid containing medications, exposure to any corticos…
Respiratory disease phenotypes in a general population sample: latent transition analysis
2018
Background: Few data are available on the temporal pattern of respiratory disease phenotypes in general population. Aim: To detect longitudinal patterns of disease phenotypes related to risk factors and physician visits. Methods: Pisan general population sample from 2 cross-sectional studies (PI1: 1991-93; PI2: 2009-11; n=1107), questionnaire-based data. Latent transition analysis (LTA) was performed to assess respiratory disease phenotypes at PI1 and PI2, labelled according to disease/symptom occurrence. Possible patterns were persistence, worsening and improvement of the phenotype. Multiple logistic regression models were estimated to assess the association among phenotype patterns, risk …
Multivariate quality control studies applied to Ca(II) and Mg(II) determination by a portable method
1998
Made available in DSpace on 2022-04-28T19:53:14Z (GMT). No. of bitstreams: 0 Previous issue date: 1998-01-01 A portable or field test method for simultaneous spectrophotometric determination of calcium and magnesium in water using multivariate partial least squares (PLS) calibration methods is proposed. The method is based on the reaction between the analytes and methylthymol blue at pH 11. The spectral information was used as the X-block and the Ca(II) and Mg(II) concentrations obtained by a reference technique (ICP-AES) were used as the Y-block. Two series of analyses were performed, with a month's difference between them. The first series was used as the calibration set and the second on…
Calibration transfer in chemiluminescence analysis
2001
Abstract Direct standardization (DS) and piecewise direct standardization (PDS) methods are applied to multivariate standardization of chemiluminescence signals using PLS model as the calibration model. The linear concentration interval of the chemiluminescence determination was determined. This interval was located using univariate robust calibration by least median of squares (LMS) method. The linear calibration model was corroborated by conventional least-squares method. The standardization subset and window size were optimized by means of the prediction residual error sum of squares. Several instrumental sources of variability have been studied: the detection cell, instrument, batch ver…
Fetal growth and childhood acute lymphoblastic leukemia: Findings from the childhood leukemia international consortium
2013
Positive associations have been reported between measures of accelerated fetal growth and risk of childhood acute lymphoblastic leukemia (ALL). We investigated this association by pooling individual-level data from 12 case-control studies participating in the Childhood Leukemia International Consortium. Two measures of fetal growth – weight-for-gestational-age and proportion of optimal birth weight (POBW) – were analysed. Study-specific odds ratios (ORs) and 95% confidence intervals (CIs) were estimated using multivariable logistic regression, and combined in fixed effects meta-analyses. Pooled analyses of all data were also undertaken using multivariable logistic regression. Subgroup analy…
Impact of socio-economic position on cancer stage at presentation: Findings from a large hospital-based study in Germany
2016
We explored the relationship between socio-economic characteristics and cancer stage at presentation. Patients admitted to a university hospital for diagnosis and treatment of cancer provided data on their education, vocational training, income, employment, job, health insurance and postcode. Tumor stage was classified according to the Union International Contre le Cancer (UICC). To analyze disparities in the likelihood of late-stage (UICC III/IV vs. I/II) diagnoses, logistic regression models adjusting for age and gender were used. Out of 1,012 patients, 572 (59%) had late-stage cancer. Separately tested, increased odds of advanced disease were associated with post-compulsory education com…