Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Linear Regression”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,279 records · Page 71Linked to original sources
PubMed2000

The relationship between mortality caused by cardiovascular diseases and two climatic factors in densely populated areas in Norway and Ireland.

BACKGROUND: Seasonal variations in mortality due to cardiovascular disease have been demonstrated in many countries, with the highest levels occurring during the coldest months of the year. It has been suggested that this can be explained by cold climate. In this study, we examined the relationship between mortality and two different climatic factors in two densely populated areas (Dublin, Ireland and Oslo/Akershus, Norway). METHODS: Meteorological data (mean daily air temperatures and wind speed) and registered daily mortality data for three groups of cardiovascular disease for the period 1985-1994 were obtained for the two respective areas. The daily mortality ratio for both men and women of 60 years and older was calculated from the mortality data. The wind chill temperature equivalent was calculated from the Siple and Passels formula. RESULTS: The seasonal variations in mortality were greater in Dublin than in Oslo/Akershus, with mortality being highest in winter. This pattern was similar to that previously shown for the two respective countries as a whole. There was a negative correlation between mortality and both air temperature and wind chill temperature equivalent for all three groups of diseases. The slopes of the linear regression lines describing the relationship between mortality and air temperature were a lot steeper for the Irish data than for the Norwegian data. However, the difference between the steepness of the linear regression lines for the relationship between mortality and wind chill temperature equivalent was considerably less between the two areas. This can be explained by the fact that Dublin is a much windier area than Oslo/Akershus. CONCLUSION: The results of this study demonstrate that the inclusion of two climatic factors rather than just one changes the impression of the relationship between climate and cardiovascular disease mortality.

Adult↗
PubMedDate not supplied

[Computer-aided prediction of the mutagenic activity substituted polycyclic compounds].

The relationship between mutagenic activity and chemical structure was studied for 54 polycyclic compounds using two approaches: multiple linear regression analysis and artificial neural networks. Structural fragments, quantum chemical indices, and hydrophobicity (octanol-water partition coefficient) were used as descriptors (properties of the molecules introduced in the model). Both linear regression equations and nonlinear relationships obtained with the help of a neural network were shown to accurately predict mutagenic activity for the compounds structurally similar to those in the training sample. The introduction of experimentally selected descriptors is substantiated to verify the proposed mechanism of related compounds mutagenic activity.

Heterocyclic Compounds, 3-Ring↗
PubMed2005

Magnetic resonance imaging of pelvic musculoskeletal and genitourinary anatomy in patients before and after complete primary repair of bladder exstrophy.

PURPOSE: We characterize pelvic soft tissue and bony anatomy of patients before and after complete primary repair of exstrophy (CPRE). MATERIALS AND METHODS: We evaluated 15 measurements on pelvic magnetic resonance imaging (MRI) in patients who underwent CPRE without osteotomy at our institution from 1996 to 2004. MRI protocols included axial, sagittal and coronal fast spin echo proton density sequences. Measurements were compared before and after CPRE using a paired t test, and between patients after CPRE, and age and gender matched controls using linear regression adjusting for the matched case-control groups. Patients older than 3 years with continent intervals longer than 3 hours after CPRE were compared to age and gender matched controls using linear regression. RESULTS: A total of 29 MRIs in 18 patients with exstrophy were available for analysis. Median patient age at postoperative MRI was 25 months (range 4 to 36). The configuration of the post-CPRE pelvis was significantly different from that of controls in all parameters measured including wider symphyseal diastasis (34.5 mm vs less than 1 mm) and more obtuse iliac wing (121 degrees vs 98 degrees), puborectalis (94 degrees vs 49 degrees) and ileococcygeus angles (111 degrees vs 98 degrees ). The anatomy of continent patients after CPRE was not significantly different from that of controls in most parameters measured. CONCLUSIONS: Comparison of the pelvic anatomy in patients before and after CPRE suggests that after CPRE patients have parameters that more closely approximate, but are still significantly different, from those of control patients. Patients with greater than 3-hour continent intervals after CPRE have anatomic parameters most similar to those of age matched controls.

Bladder Exstrophy↗
PubMed2004

Birthweight by gestational age and sex at a rural referral center.

OBJECTIVE: Determine the distribution of birthweights in singleton births by gestational age and gender at Marquette General Hospital, a rural referral center in Michigan's upper peninsula. STUDY DESIGN: Birth log data were examined for prenatal factors and obstetrical outcomes. The birthweight distribution was compared to published values, and a linear regression model of prenatal factors was developed. RESULTS: Our median birthweights were significantly greater than published values. Males were 128 g heavier than female infants after adjusting for gestational age. In a multivariable linear regression model, birthweight was significantly associated with gestational age, sex of the infant, maternal age, primigravida status of mother, and maternal diabetes (all p<0.01). Using published standards resulted in an overdiagnosis of large for gestational age and an underdiagnosis of small for gestational age. CONCLUSION: Local birthweight distributions can differ significantly from historical or national distributions. The development of birthweight distributions accommodating for prenatal factors is needed.

Adult↗
PubMed2004

.VO2 is attenuated above the lactate threshold in endurance-trained runners.

PURPOSE: To determine whether a deviation from linearity occurs in the .VO2-speed relationship, above the lactate threshold (LT) in running; and whether the length of the submaximal exercise bouts alters the magnitude of any deviation. METHODS: Ten endurance-trained runners (N = 3 state level, N = 4 club level, and N = 3 recreational) (mean +/- SE; age 24.4 +/- 2.8 yr, mass 76.1 +/- 2.2 kg, .VO2 59.3 +/- 10.6 mL.kg-1.min-1) completed a .VO2, LT test and 10 x 4-min submaximal constant load exercise bouts. Data were evenly spread above and below LT, which was fitted by a dual linear regression model. RESULTS: There was a significant decrease (51.4%) in slope of the .VO2-speed relationship above LT. The use of 3-min, in comparison with 4-min, submaximal data did not alter the slope of the .VO2-speed regression above LT. There was no significant difference in the .VO2max estimated from the .VO2-speed regression above LT (58.1 +/- 3.3 mL.kg-1.min-1) but a significant difference below LT (63.6 +/- 3.9 mL.kg-1.min-1) to that obtained during the .VO2max test. CONCLUSION: Data from the current study suggest that the use of the linear regression of .VO2-speed data below the LT may potentially overestimate the prediction of .VO2 values above LT.

Adaptation, Physiological↗
PubMed1995

[Accuracy and clinical applicability of the echocardiographic automated endocardial boundary detection system: correlation and bias analysis].

INTRODUCTION AND OBJECTIVES: Automated edge detection of endocardial borders is a new echo system that permits on-line delineation and tracking of blood-tissue interface and offers promise for measuring cyclic changes in cavity area and the assessment of left ventricular function on-line. Its accuracy has only been analyzed by linear regression and its applicability in unselected patients is not clearly established. METHODS: We analyzed the accuracy and clinical applicability of the system in 150 patients. Its accuracy was assessed not only by linear regression but also by bias analysis by comparing the results of the system with those obtained by manual tracing from parasternal short-axis and apical 4 chamber views. RESULTS: We obtained satisfactory studies with this system in at least one of the two echo views in 66% of patients: 47% from 4-chambers view, 43% from parasternal short-axis view and 24.6% from both echo views. A visual semiquantitative assessment of left ventricular function could be performed in 88.6% of patients (p < 0.001). On-line and hand-traced left ventricular areas there well correlated, but fractional area change values from both methods correlated less closely. 95% limits of agreement between both methods were: 2.8 +/- 5.5 cm2 (end-diastolic area), 1 +/- 4.4 cm2 (end-systolic area) and 1.2 +/- 23% (fractional area change) in short-axis parasternal view; in apical 4-chambers view these limits were: 1.16 +/- 6.4 cm2,--1.1 +/- 6 cm2 and 7.3 +/- 16%, respectively. CONCLUSIONS: Although the correlations between left ventricular areas from both methods were close the limits of agreement exceeded our acceptable range of reproducibility. Fractional area change showed only moderate correlations and a lack of agreement with off-line method. Poor image quality of the conventional echo still limits the clinical applicability of the current automated edge detection system.

Adult↗
PubMedDate not supplied

Costs of asthma in a cohort of Swiss adults: associations with exacerbation status and severity.

OBJECTIVE: This article will address the effect of exacerbation status, disease severity (defined by medication required), and other variables on resource use and costs for asthma in Switzerland in 1996 to 1997. METHODS: A retrospective chart-based study was performed. A sample of 422 adults was analyzed. Target variables were stratified by disease severity and exacerbation status. Bivariate associations were assessed. Multiple linear regression was performed on the logarithm of direct medical costs. RESULTS: The probability of exacerbations was positively associated with disease severity. Resource use and costs were associated with both of these variables. Multiple linear regression identified age, presence of asthma-related comorbidities, degree of severity, exacerbation status, quick reliever versus controller therapy, and diagnosis or treatment by a pulmonologist as independent influences on direct costs. An interaction between severity and exacerbation status was also noted. Regression identified direct costs in the highest severity group to be 2.5 times higher than those in the lowest group, if there were no exacerbations. If exacerbations were present, costs were 5.7 times higher. CONCLUSIONS: Because of its high prevalence, asthma has a high impact on public health. This impact depends on disease severity and, according to these findings, may also depend on the extent to which exacerbations are avoided or at least controlled.

Acute Disease↗
PubMed2003

A multilevel analysis of the relation of socioeconomic status to adolescent depressive symptoms: does school context matter?

OBJECTIVE: To determine whether the socioeconomic context of the school environment is associated with adolescent depressive symptoms independent of individual household income. Study design Data were drawn from a 1995 nationally representative study of 7th to 12th grade students. Multivariable linear regression at the school and individual levels assessed the relation between income and depressive symptoms. Multilevel modeling techniques were then used to understand how these factors are jointly associated with adolescent depressive symptoms. PARTICIPANTS: Adolescents (n=13,235) in grades 7 through 12 from 132 schools whose parent provided income information. RESULTS: Linear regression analyses indicated that lower household income, average school income, and increasing school-level income inequality were significantly (P<.001) associated with depressive symptoms. Further examination of these relations through multilevel modeling indicated that both household income (P<.01) and average school income (P<.05) were significantly related to depressive symptoms after adjusting for covariates, with evidence for an interaction between the two. The impact of lower household income on depressive symptoms was approximately 2-fold greater for students attending a poor versus a rich school. CONCLUSIONS: School context is associated with adolescents' depressive symptoms, even after adjusting for individual-level factors. The school environment may partially buffer the adverse influence of lower household income on adolescent depressive symptoms.

Adolescent↗
PubMed1995

[Kinetic model of micro-organism growth: the case of Xanthomonas campestris].

Microbial growth is studied and kinetic models to describe the process rate useful in the scale-up are proposed. The growth of Xanthomonas campestris NRRL B-1459, a bacterium producing xanthan, a major industrial gum, is studied. Experimental data are arranged by means of different methods, and linear and non-linear regression techniques are applied in several ways (i.e. fixing or not fixing the values of certain parameters) and they are compared. To obtain parameter values with statistical meaning, two parameters must be calculated (namely, the maximum specific growth rate and the maximum biomass concentration available) by means of a non-linear regression technique employing the logistic equation. The maximum specific growth rate is related to temperature by means of different equations, but that of Ratkowsky et al. is the most suitable for X. campestris growth. Studied variables present no tendency to error and the reproduction of experimental data is very good.

Bacteriological Techniques↗
PubMedDate not supplied

Oral health and treatment needs in institutionalized psychiatric patients in India.

The caries prevalence, oral hygiene status, periodontal health and treatment needs were evaluated in a group of institutionalized psychiatric patients in Goa, India. Of the total 153 inmates, males constituted 59 percent, the mean age was 25 years, 96 percent were self sufficient and the response rate was 84 percent. 63 percent were diagnosed with schizophrenia. They did not receive any assistance in daily self-care activities including oral hygiene maintenance. None of the 5 edentulous patients had dentures, 5% had been referred for emergency dental care during the period of institutionalization. 15 subjects (12%) were caries-free, the stepwise linear regression analysis showed that the mean DMFT index significantly increased with age (t = 2-819, PL 0.05). Two third of the study population (88%) were in need of conservative dental treatment. The stepwise linear regression analysis showed that the mean OHI-S index significantly increased with age (t = 2.412, P < 0.01). Only 5.4% reported a healthy periodontium whereas 16.27% required complex periodontal therapy. Soft tissue lesions included dorsal lingual depapillation/heavily coated areas and angular cheilitis in addition to incidental observations such as mucosal hyperpigmentation, gingival hyperplasia, and leucoedema. Bruxism and factitious injuries were also noted. The onus of meeting the oral health needs of this marginalized patient population therefore depends on the effectiveness of community dentistry programs vis a vis the efforts of the staff of the institution to provide such services on a regular basis.

Adult↗
PubMed2000

Simulation of longitudinal threshold visual field data.

PURPOSE: To describe and evaluate a computer model that simulates longitudinal visual field data. METHODS: A computer model was designed using factors that influence thresholds of normal and glaucomatous visual fields. The simulation model was used to quantify the effects of fluctuation on the outcomes of pointwise linear regression by comparison with simulated gold standard data with no variability. RESULTS: Serial sets of 10 stable and 10 progressive visual fields with different fluctuation levels were generated by simulation and were analyzed using pointwise linear regression. Regression outcome measures used were slopes of -1 dB/year or worse and slopes of -1 dB/year or worse that were also statistically significant. In stable visual fields, the number of locations with regression slopes worse than -1 dB/year increased with fluctuation and defect size and was inversely related to the number of fields. The number of locations with statistically significant slopes remained low and appeared unaffected by these variables. In progressive visual fields, analysis of a small number of visual field test results (<8) overestimated the number of locations with regression slopes worse than -1 dB/year and underestimated the number of locations with statistically significant slopes. CONCLUSIONS: Computer simulation may be used to provide a gold standard outcome that permits evaluation of statistical tools for monitoring progressive glaucomatous visual field loss.

Computer Simulation↗
PubMed2006

On the equivalence of case-crossover and time series methods in environmental epidemiology.

The case-crossover design was introduced in epidemiology 15 years ago as a method for studying the effects of a risk factor on a health event using only cases. The idea is to compare a case's exposure immediately prior to or during the case-defining event with that same person's exposure at otherwise similar "reference" times. An alternative approach to the analysis of daily exposure and case-only data is time series analysis. Here, log-linear regression models express the expected total number of events on each day as a function of the exposure level and potential confounding variables. In time series analyses of air pollution, smooth functions of time and weather are the main confounders. Time series and case-crossover methods are often viewed as competing methods. In this paper, we show that case-crossover using conditional logistic regression is a special case of time series analysis when there is a common exposure such as in air pollution studies. This equivalence provides computational convenience for case-crossover analyses and a better understanding of time series models. Time series log-linear regression accounts for overdispersion of the Poisson variance, while case-crossover analyses typically do not. This equivalence also permits model checking for case-crossover data using standard log-linear model diagnostics.

Air Pollution↗
PubMed1981

Statistical package for analysis of competition ELISA results.

A computation and analysis program has been assembled to facilitate the use of competition ELISA and similar assays for studies of antigen regulation and turnover. The program fits sigmoidal standard curves using a 4-parameter logistic function, determines amounts of antigen from the equation which defines the standard curve, and calculates specific activities by linear regression of the levels of antigen in varying amounts of total protein. An optional weighting function is provided to adjust for systematic non-uniform variance. Outlying points are identified during the linear regression, and the user may delete them or redefine the acceptable working range of the standard curve. The program provides a complete print-out of the data and optional plots of the fitted standard curve and the regression analysis of the samples, as well as statistics which are useful for quality control. It also provides the option of storing the data points from the standard curve on magnetic diskettes. The package is written in BASIC for a Wang Model 2200 computer equipped with a magnetic diskette drive, line printer, and flat-bed X-Y plotter, but it is readily adaptable to other systems and input/output devices.

Antigens↗
PubMed2006

Associations among body composition, androgen levels, and human immunodeficiency virus status in adolescents.

PURPOSE: To investigate whether factors influencing body composition may be unique for male and female adolescents with horizontal transmission of human immunodeficiency virus (HIV). METHODS: HIV infected and uninfected youth (aged 13-18 years) participating in the multi-center project REACH (Reaching for Excellence on Adolescent Health Care) had at baseline anthropomorphic measurements including height, weight, bicep, tricep, subscapular and suprailiac skinfold measurements and midarm circumference. Body mass index, muscle mass, fat free body mass, and fat mass were calculated and predictors of these measures were assessed using multiple variable linear regression. Predictors included contraception, HIV status and related variables (CD4 counts, treatment status, and viral load), substance use, androgen levels as well as appetite changes, and bone age. RESULTS: In multiple variable linear regression analysis, female adolescents' body composition was associated with HIV status, CD4 + T cell counts, and free testosterone levels. HIV status was found associated with higher fat and lean body mass, however lower CD4+T cell counts were associated with lower fat and lean body mass. Higher testosterone levels were associated with higher lean and fat mass. For adolescent males, higher total testosterone levels but not free testosterone levels were associated with lower lean and fat mass. CONCLUSIONS: HIV status was not associated with a lower muscle or fat mass. Different factors influenced body composition for females than males. Higher testosterone levels may be protective against loss in lean and fat mass in females.

Adolescent↗
PubMed1997

New indices of ischemic heart disease and aging: studies on the serum levels of soluble intercellular adhesion molecule-1 (ICAM-1) and soluble vascular cell adhesion molecule-1 (VCAM-1) in patients with hypercholesterolemia and ischemic heart disease.

It is known that the expression of intercellular adhesion molecule-1 (ICAM-1) and vascular cell adhesion molecule-1 (VCAM-1) on the surface of vascular endothelial cells is closely related to the formation of early atherosclerotic lesions. In this study, serum soluble ICAM-1(sICAM-1) and soluble VCAM-1(sVCAM-1) were determined by sandwich ELISA both in normal healthy individuals (n = 114) and in patients with hypercholesterolemia (HC, n = 112) or ischemic heart disease (IHD, n = 38) to clarify the significance of the soluble forms of the adhesion molecules in the development of atherosclerotic diseases. IHD patients, not HC patients, showed significant elevation of sICAM-1, but not of sVCAM-1, compared with controls in age and sex-matched subjects. In addition, multiple linear regression analysis showed that sICAM-1 was correlated only to the presence of IHD but not to age and lipids. Multiple logistic regression analysis revealed that sICAM-1 was the most powerful independent predictor of the presence of IHD. On the other hand, sVCAM-1, not sICAM-1, was positively correlated to age. Multiple linear regression analysis showed that age was the most powerful independent predictor of the level of sVCAM-1. These data suggest that sICAM-1 and sVCAM-1 are useful as indices of clinical manifestations of atherosclerosis and aging, respectively.

Adult↗
PubMed1980

Rapid method for determination of riboflavin in urine by high-performance liquid chromatography.

A simple, specific, and sensitive high-performance liquid chromatographic (HPLC) method for the determination of riboflavin directly in urine samples using a fixed-wave-length spectrofluorometer is described. Centrifuged raw urine samples (50 microliter) are injected onto a reversed-phase microparticulate C18 column. The eluent is 0.01 M KH2PO4 (pH 5.0)-methanol (65:35). This method is capable of differentiating riboflavin from riboflavin-5-phosphate, non-riboflavin fluorescing components in urine, and photo-degraded riboflavin. The method shows good reproducibility and is linear to at least 12 micrograms/ml. The sensitivity of this procedure, at the 95% confidence limit, determined by linear regression analysis, is estimated to be 0.05 micrograms/ml using peak height and 0.07 micrograms/ml using peak area. This HPLC method is compared to an automated fluorometric method for riboflavin. The coefficient of linear regression of this comparison is Y = 0.858 + 0.893X, where X is the HPLC method and Y is the fluorometric method.

Chromatography, High Pressure Liquid↗
PubMed2006

Insular cortical ischaemia does not independently predict acute hypertension or hyperglycaemia within 3 h of onset.

OBJECTIVES: To test the hypothesis that insular cortical ischaemia is associated with acute hypertension and hyperglycaemia. METHODS: From the Canadian Activase for Stroke Effectiveness Study, which included only patients treated with thrombolysis hyperacutely (ie, within 3 h of onset of stroke), 966 patients were identified with ischaemia affecting (n = 685), or sparing (n = 281), the insular cortex. Demographic and clinical data, pretreatment indices of blood pressure, blood glucose, atrial fibrillation, and clinical imaging and outcome measures were compared between the two groups. Multivariable linear regression was used to assess predictors of systolic blood pressure and glucose levels before thrombolysis. RESULTS: Pretreatment hypertension (p = 0.009), but not hyperglycaemia (p = 0.32), was predicted by insular ischaemia in univariable linear regression analyses. After adjusting for other factors, however, insular cortical ischaemia was not found to be an independent predictor for acute hypertension or hyperglycaemia. CONCLUSIONS: Raised blood pressure or serum glucose levels in hyperacute (<3 h) cerebral ischaemia is not independently predicted by insular involvement. Several hours are required for sympathetic manifestations of insular ischaemia to evolve.

Acute Disease↗
PubMed1991

Simple models for description of small-solute transport in peritoneal dialysis.

The convective component in the general description of transport of solutes across the peritoneal membrane can be expressed as SQuc, where S is the sieving coefficient, Qu is the ultrafiltration flow rate, and c is the average concentration in the membrane (c = (1-F)cB + FcD, where cB and cD are blood plasma and dialysate solute concentration, respectively). F is a weighing function dependent on Qu, S, and the diffusive mass transport coefficient KBD. In this study a class of simple models of solute transport was considered in which S = 1 (justified for small solutes) was chosen, and F was selected as follows: F = 0 (as in the S = 1 (justified for small solutes) was chosen, and F was selected as follows: F = 0 (as in the widely used model of Garred and coworkers), F = 0.5 (theoretically justified model), F = 0.33 (theoretically justified for a high ultrafiltration period), and F = 1 (for convective transport from dialysate to blood). For all these models the estimation of KBD from clinical data can be performed with the aid of linear regression. The simple models were compared with the Pyle-Popovich model which takes into account the general expression for convective solute transport, for both the accuracy of the KBD determination (using linear regression) and the accuracy of theoretically calculated dialysate to plasma concentration ratios (D/P) to experimental D/P. Clinical evaluation of the new models was carried out in 28 6-hour dwell studies in 21 nondiabetic patients using 2 liters of hypertonic (glucose 3.86%) dialysis fluid. The differences between the simple models were small from the clinical point of view for urea, creatinine, glucose, and potassium, whereas for sodium the predictions were not satisfactory for any of the models. For urea and creatinine the model with F = 0.5 yielded the best fit of theoretical predictions to experimental data. For glucose and potassium small but systematic deviations of theoretical D/P from experimental D/P were observed for all simple models. The protein transport could be satisfactorily described by a model in which F = 1, as shown for total protein.

Creatinine↗