SEARCH · PubMed Health

Results for “Logistic Models”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

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

At least 217 records · Page 12Linked to original sources

PubMed2006

Bioinformatics research on the SARS coronavirus (SARS_CoV) in China.

Severe acute respiratory syndrome (SARS) first appeared in 2002 in China, which fastly affected about 8000 patients over 29 countries and caused 774 fatalities. As its pathogen was identified as a new kind of coronavirus (SARS_CoV), its genome was quickly sequenced on several isolates. Studies on its functional genomics were performed by combinatorial application of all the available bioinformatics tools and the development of new programs. In this way, it was found that the four proteins were absolutely responsible for nosogenesis of SARS, i.e. spike (S) protein; small envelop (E) protein; membrane (M) protein; and nucleocaspid (N) protein. Molecular evolution studies have revealed that SARS must be originated from wild animals, and it was demonstrated that the major genetic variations in some critical genes, particularly the Spike gene, was essential for the transition from animal-to-human transmission to human-to-human transmission. Theoretical models, either Logistic model or SIR model, were developed to describe the transmission of SARS. The recorded difference of SARS spreading in Beijing and Hong Kong was also reasonably analyzed according to these models. The whole process of fruitful bioinformatics studies, along with other related scientific investigations have set up an unprecedented paradigm for human of how to battle against sudden-breaking and catastrophic epidemics.

China↗

PubMed1995

Logistic transmission modeling of simulated data.

A nonparametric method for linkage analysis has been developed and applied to the Problem 1 data set of the Genetic Analysis Workshop 9. Basically, the univariate matched pair strategy of the transmission disequilibrium test has been adapted to multivariate modeling using the conditional logistic function. After setting the critical value for significance at p < or = 0.0001, models at only D5G23 and D1G31 appear to be significant (p < 10(-7)). Logistic transmission modeling is a powerful method for establishing linkage by disequilibrium.

Alleles↗

PubMed1989

Estimating intervention effects in longitudinal studies.

Longitudinal studies aimed at assessing the impact of interventions on disease risk factors often confront several statistical problems. These problems include 1) dependent variables measured by ordered categories, 2) numerous potentially relevant patterns of transition between outcome levels, 3) mixed units of analysis (e.g., assignment by social unit while theorizing in terms of individuals), 4) incomplete randomization, and 5) correlated estimates for successive occasions of longitudinal measurement. Longitudinal data on use of cigarettes, alcohol, and marijuana among adolescents (n = 1,244, complete data) from the Midwestern Prevention Project are used to demonstrate solutions to each of these problems: 1) a proportional odds regression model, 2) conditional logistic models of transitions with interactions between baseline level and intervention effect, 3) a logistic model estimated with linear regression methods on measures aggregated by social unit, 4) conditional and unconditional models of effect magnitude, and 5) a repeated measures logistic regression technique. Panel data fit to the various models yielded the following conclusions concerning intervention effects in the Midwestern Prevention Project: reduction in the prevalence of cigarette users in treatment schools compared with control schools (8% vs. 18% smoked in the last week at one year follow-up), mixed evidence of an effect on marijuana use, and no evidence of an effect on alcohol use.

Adolescent↗

PubMed2001

Conduct problems and early cannabis initiation: a longitudinal study of gender differences.

AIM: To investigate the relationship between early conduct problems and early onset of cannabis use, with special emphasis on possible gender differences. DESIGN: A prospective longitudinal study of a national sample of 2436 adolescents. The sample was followed up over a year and a half, when the adolescents were in their early teens. SETTING: Norway. MEASUREMENTS: On the basis of an earlier study, conduct problems (CP) closely related to the criteria for conduct disorder (CD) in DSM-III-R were decomposed into three dimensions, labelled serious, aggressive and covert. Further, information was collected about alcohol intoxication, daily smoking and use of cannabis. A number of questions were posed about sexual interactions and perceived puberty development. Parental socio-economic status was measured according to the ISCO-88. Separate information was collected as to whether the parents were on social welfare or unemployed. A parental bonding measure (PBI) was used to measure the emotional relationship between respondents and parents. Further, a measure of parental monitoring was used, and information was also collected on other aspects of the family milieu, and on the adolescents' peers. Statistical models. Logistic regression analysis was employed. As the sample consisted of pupils clustered within classes within schools, a three-level error structure for the logistic regression model was estimated. FINDINGS: There was a strong association between early conduct problems and subsequent cannabis initiation. Also conduct problems at a potential subclinical level seemed to have great impact. The effect was significantly stronger in girls than in boys. Serious CP was found to have a moderate effect upon cannabis initiation in boys, whereas aggressive and covert CP had strong effects in girls. Early onset of puberty and early sexual involvement had no impact, whereas early use of cigarettes proved an important precursor to cannabis use. CONCLUSIONS: Conduct problems are important precursors of early onset cannabis use, but probably represent gender-specific aetiologies. There might be an important potential for prevention of early onset drug use in the prevention of early conduct problems, in particular for girls.

Adolescent↗

PubMedDate not supplied

The relation of smoking to waist-to-hip ratio and diabetes mellitus among elderly women.

BACKGROUND: Smoking is associated with lower body weight, but an increased risk of diabetes in some studies. Because smoking may increase waist-to-hip ratio (WHR), a risk factor for diabetes, we postulated that the relation between smoking and diabetes may be mediated in part by smoking-associated differences in body fat distribution. METHODS: We conducted a cross-sectional analysis of baseline data from 9,435 elderly nonblack women enrolled in the Study of Osteoporotic Fractures. Data were collected by Self-report and physical examination. Linear and logistic models were used to determine the relation of smoking to WHR and prevalence of self-reported diabetes. RESULTS: Current and past smokers had greater WHRs compared with never smokers. In multivariate models that adjusted for body mass index, the prevalence of diabetes was lower among smokers of < or = 10 cigarettes/day [odds ratio (OR) = 0.57, 95% confidence interval (CI) 0.31-1.03] and higher among smokers of > 10 cigarettes/day (OR = 1.38, 95% CI 0.99-1.92) compared with never smokers. The relation of smoking > 10 cigarettes/day to prevalence of diabetes was slightly attenuated after further adjustment for WHR. CONCLUSIONS: Smoking-associated differences in WHR may mediate, at least in part, the prevalence of diabetes among smokers of > 10 cigarettes/day. The decreased prevalence of diabetes that we observed among smokers of < or = 10 cigarettes/day was not explained by differences in obesity and requires confirmation.

Aged↗

PubMed2006

Effect of plasma homocysteine level and urinary monomethylarsonic acid on the risk of arsenic-associated carotid atherosclerosis.

Arsenic-contaminated well water has been shown to increase the risk of atherosclerosis. Because of involving S-adenosylmethionine, homocysteine may modify the risk by interfering with the biomethylation of ingested arsenic. In this study, we assessed the effect of plasma homocysteine level and urinary monomethylarsonic acid (MMA(V)) on the risk of atherosclerosis associated with arsenic. In total, 163 patients with carotid atherosclerosis and 163 controls were studied. Lifetime cumulative arsenic exposure from well water for study subjects was measured as index of arsenic exposure. Homocysteine level was determined by high-performance liquid chromatography (HPLC). Proportion of MMA(V) (MMA%) was calculated by dividing with total arsenic species in urine, including arsenite, arsenate, MMA(V), and dimethylarsinic acid (DMA(V)). Results of multiple linear regression analysis show a positive correlation of plasma homocysteine levels to the cumulative arsenic exposure after controlling for atherosclerosis status and nutritional factors (P < 0.05). This correlation, however, did not change substantially the effect of arsenic exposure on the risk of atherosclerosis as analyzed in a subsequent logistic regression model. Logistic regression analyses also show that elevated plasma homocysteine levels did not confer an independent risk for developing atherosclerosis in the study population. However, the risk of having atherosclerosis was increased to 5.4-fold (95% CI, 2.0-15.0) for the study subjects with high MMA% (> or =16.5%) and high homocysteine levels (> or =12.7 micromol/l) as compared to those with low MMA% (<9.9%) and low homocysteine levels (<12.7 micromol/l). Elevated homocysteinemia may exacerbate the formation of atherosclerosis related to arsenic exposure in individuals with high levels of MMA% in urine.

Age Factors↗

PubMed2004

Role of osmolality of contrast media in the development of post-ERCP pancreatitis: a metanalysis.

The role of osmolality of contrast media (CM) in the development of post-ERCP pancreatitis (PEP) is debated. We therefore performed a metanalysis to determine whether osmolality affects the incidence of PEP. A literature search of English-language studies was performed using computerized databases and manual searching of abstracts and article bibliographies. Randomized controlled trials comparing the incidence of PEP associated with high- and low-osmolality contrast media (HOCM, LOCM) were considered. The outcome assessed was clinical pancreatitis as evidenced by both elevation of pancreatic enzymes and pain. Data were analyzed using logistic regression with terms for study and osmolality. Fisher's exact test was done to compare PEP rates. Homogeneity between studies was indicated by the nonsignificance of the study effect in the logistic regression model. Logistic regression also indicated no difference in PEP rates between LOCM and HOCM (P = 0.399). Comparison of PEP rates in both groups using Fisher's exact test did not indicate a difference in any individual study (all P values > 0.05). Due to the large variation of study sample sizes, we repeated the analysis by creating three study groups. The effect of osmolality was invariant to how the data were combined. The results of this metanalysis indicate that there is no significant difference between HOCM and LOCM with respect to clinical PEP.

Cholangiopancreatography, Endoscopic Retrograde↗

PubMed2003

Identifying febrile young infants with bacteremia: is the peripheral white blood cell count an accurate screen?

STUDY OBJECTIVE: We estimated the accuracy of the total peripheral WBC count as a screen for bacteremia in febrile young infants. METHODS: We evaluated, retrospectively, the performance characteristics of linear and nonlinear (U-shaped) logistic models for predicting bacteremia that are based on the total peripheral WBC count. Research subjects were consecutive 0- to 89-day-old infants who had a temperature in triage of greater than or equal to 38 degrees C (> or =100.4 degrees F) and were evaluated for infection at a pediatric emergency department (1993 to 1999). Infants with leukemia were excluded. Areas under the receiver operator characteristic curves (AUC), as well as sensitivity, specificity, interval likelihood ratios, and the corresponding odds of bacteremia predicted at various thresholds of the test, were calculated. RESULTS: The rate of bacteremia was 1% (38/3,810). The U-shaped model was more accurate (AUC 0.69 versus 0.56); however, no threshold of the total peripheral WBC count had both good sensitivity and specificity. Sensitivity and specificity values were 79% and 5%, respectively, at a peripheral WBC count cutoff of 5,000 cells/mm(3), and 45% and 78%, respectively, at a cutoff of 15,000 cells/mm(3). The odds of bacteremia were not decreased substantially at any cutoff and were increased only modestly at values outside published norms of the test. CONCLUSION: The total peripheral WBC count is an inaccurate screen for bacteremia in febrile young infants; thus, decisions to obtain blood cultures should not rely on this test.

Age Factors↗

PubMed2005

Generalizations of the Moran effect explaining spatial synchrony in population fluctuations.

The Moran effect for populations separated in space states that the autocorrelations in the population fluctuations equal the autocorrelation in environmental noise, assuming the same linear density regulation in all populations. Here we generalize the Moran effect to include also nonlinear density regulation with spatial heterogeneity in local population dynamics as well as in the effects of environmental covariates by deriving a simple expression for the correlation between the sizes of two populations, using diffusion approximation to the theta-logistic model. In general, spatial variation in parameters describing the dynamics reduces population synchrony. We also show that the contribution of a covariate to spatial synchrony depends strongly on spatial heterogeneity in the covariate or in its effect on local dynamics. These analyses show exactly how spatial environmental covariation can synchronize fluctuations of spatially segregated populations with no interchange of individuals even if the dynamics are nonlinear.

Demography↗

PubMed1994

Thyroid diseases among atomic bomb survivors in Nagasaki.

OBJECTIVE: To elucidate the current thyroid disease status for the Nagasaki Adult Health Study cohort of the Radiation Effects Research Foundation. DESIGN: Survey study. SETTING: Nagasaki, Japan. PARTICIPANTS: Cohort members of the Nagasaki Adult Health Study who received biennial health examinations from October 1984 to April 1987 (n = 2856). A total of 2587 subjects remained after exclusion of persons exposed in Hiroshima or in utero and those who were not in Nagasaki at the time of the bombing. Thyroid radiation dose by the dosimetry system established in 1986 was available for 1978 of the 2587 subjects. MAIN OUTCOME MEASURES: Thyroid diseases were diagnosed using uniform procedures including ultrasonic scanning. The relationship of the prevalence of each thyroid disease with thyroid radiation dose, sex, and age was analyzed using logistic models. RESULTS: A significant dose-response relationship was observed for solid nodules, which include cancer, adenoma, adenomatous goiter, and nodules without histological diagnosis, and for antibody-positive spontaneous hypothyroidism (autoimmune hypothyroidism) but not for other diseases. The prevalence of solid nodules showed a monotonic dose-response relationship, yet that of autoimmune hypothyroidism displayed a concave dose-response relationship reaching a maximum (+/- SE) level of 0.7 +/- 0.2 Sv. CONCLUSIONS: The present study confirmed the results of previous studies by showing a significant increase in solid nodules with dose to the thyroid and demonstrated for the first time a significant increase in autoimmune disease among atomic bomb survivors. A concave dose-response relationship indicates the necessity for further studies on the effects of relatively low doses of radiation on thyroid disease.

Cohort Studies↗

PubMed1991

Age-dependent logistic regression model and its application.

In the present paper we introduce the theory and algorithm of the unconditional and conditional age-dependent logistic regression model, which combines logistic regression analysis of case-control study with survival analysis of cases in the data, thus facilitating simultaneous comparison analysis between cases and controls and among cases with different ages of disease onset under study. In age-dependent logistic regression analysis, estimated compound relative risk (CRR) and compound attributable risk (CAR) comprise the variance contributions of risk factors to disease occurrence and the time of disease onset, thereby the role played by various risk factors in etiology and etiopathology can be objectively evaluated. The current logistic regression model is only a particular case of age-dependent logistic regression theory neglecting the variations in onset age of diseases.

Age Factors↗

PubMed1998

Diagnosing breast cancer from FNAs: variable relevance in neural network and logistic regression models.

We compared the selection of variables for building a classification model for the diagnosis of breast cancer using neural networks and logistic regression. A set of 460 cases was used to build neural network and logistic regression models that classify cell samples obtained by fine-needle aspiration (FNA) as malignant or benign, depending on nine pathology features. Variables selected by a step down logistic regression model were compared to those selected by a measure of relevance derived from neural network weights. Since both types of models resulted in similar predictive accuracy, we expected approximately the same variables to be selected. The variables with the highest relevance values for the neural network models corresponded to those of high significance in univariate logistic regression models, but were not the ones selected in the step down procedure of multivariate models. Variable relevance based on weights for neural network models does not seem to be a consistent index of the importance of that variable for multivariate models such as logistic regression.

Analysis of Variance↗

PubMed2006

Epidemiology of fat replacement of the right ventricular myocardium determined by multislice computed tomography using a logistic regression model.

PURPOSE: We frequently observe fat replacement (FR) of the anterior wall of the right ventricular myocardium (RVM), but its epidemiological significance is not clear. METHODS AND MATERIALS: 49 consecutive subjects (28 males, 36-83 years old, median 67) underwent enhanced ECG-gated multislice CT (Light speed ultra 16, General Electrics, WI) and we retrospectively analyzed the presence of FR of RVM. A logistic model for predicting FR of RVM was constructed using age, sex, hypertension [HT], diabetes mellitus [DM], hyperlipidemia [HL] smoking, obesity (body mass index >25.0) and calcified and non-calcified plaques of coronary arteries (CA). RESULTS: FR of RVM was detected in 21 subjects (12 males, 51-78 years old, median 67), 76% of whom had HT, 38% DM, 43% HL, 48% smoking history, 52% were obese, and 76% had calcified and 24% had non-calcified plaques of CA. Only obesity was significantly higher in FR (p<0.05). A logistic regression model showed, although there was a close association between obesity and an increased incidence of FR, it did not reach statistical significance (p=0.0515, relative risk 5.11). CONCLUSIONS: Obesity is significantly more common in cases of FR, and despite a negative multivariable analysis, may influence FR in the RVM. FR in obesity may occur independently of clinically-significant arrhythmia, which is different from ARVC. Thus, even with FR, obesity must be considered as a diagnosis before ARVC.

Adult↗

PubMed2000

Interpreting parameters in the logistic regression model with random effects.

Logistic regression with random effects is used to study the relationship between explanatory variables and a binary outcome in cases with nonindependent outcomes. In this paper, we examine in detail the interpretation of both fixed effects and random effects parameters. As heterogeneity measures, the random effects parameters included in the model are not easily interpreted. We discuss different alternative measures of heterogeneity and suggest using a median odds ratio measure that is a function of the original random effects parameters. The measure allows a simple interpretation, in terms of well-known odds ratios, that greatly facilitates communication between the data analyst and the subject-matter researcher. Three examples from different subject areas, mainly taken from our own experience, serve to motivate and illustrate different aspects of parameter interpretation in these models.

Animals↗

PubMed2001

A logistic regression model for measuring gene-longevity associations.

The logistic regression model is a popular model for data analysis in epidemiological research. In this paper, we use this model to analyze genetic data collected from gene-longevity association studies. This new approach models the probability of observing one genotype as a function of the age of investigated individuals. Applying the model to genotype data on the TH and 3'ApoB-VNTR loci collected from an Italian centenarian study, we show how it can be used to model the different ways that genes affect survival, including sex- and age-specific influences. We highlight the advantages of this application over other available models. The application of the model to empirical data indicates that it is an efficient and easily applicable approach for determining the influences of genes on human longevity.

Adolescent↗

PubMed2000

One model, several results: the paradox of the Hosmer-Lemeshow goodness-of-fit test for the logistic regression model.

BACKGROUND: The Hosmer-Lemeshow test, used extensively to assess the fit of the logistic regression model, is performed by several statistical packages. Recent studies have shown some problems in the use of this test when ties are present. These problems were attributed merely to the test implementation. METHODS: We analysed the order of the observations as an alternative explanation of the problem of ties. Using a data-set of 1393 intensive care unit (ICU) patients we performed the Hosmer-Lemeshow test with all possible subjects dispositions. RESULTS: We obtained about one million different P values, ranging from 0.01 to 0.95. DISCUSSION: It is already known that when the Hosmer-Lemeshow goodness-of-fit test is performed with a number of covariate patterns lower than the number of subjects, its result may be inaccurate. We showed that the extent of this problem could be relevant under particular conditions. We also suggest a strategy for estimating the extent of the problem and subsequent interpretation.

Hospital Mortality↗

PubMed2002

Estimation of the Doppler ultrasound umbilical maximal waveform envelope: II. Prediction of fetal distress.

Blood flow variables obtained via Doppler ultrasound (US) waveform estimation have been investigated for prediction of fetal distress. The umbilical flow was assessed using a number of waveform summary statistics in addition to the currently used resistance indices. We examined the relationship between umbilical artery waveform patterns and intrauterine growth restriction, preterm delivery and hypertensive disorders. To enhance prediction, we defined waveform skewness profiles based on pivotal points of the umbilical waveform that appeared to be related to the incidence of preterm delivery and that facilitated construction of IUGR prediction models. The data comprised 204 unselected pregnancies with the umbilical artery images recorded at 18 pregnancy weeks. The sample was divided into 114 pregnancies used to estimate model parameters and 90 pregnancies to validate the model. Logistic prediction models for detection of abnormal velocity waveforms associated with intrauterine growth restriction were derived, based on the waveform information. The estimated model sensitivity and specificity on the training data were 74% and 84%, respectively. Validation of the model on independent data yielded a sensitivity of 57% and specificity of 84%. The logistic IUGR prediction model appears to have significant predictive ability and potential for clinical use, even at this early gestational age. Our data suggest that prediction of IUGR at 18 pregnancy weeks can be much improved when the waveform shape is captured with a number of summary statistics in addition to resistance indices.

Algorithms↗

PubMed2006

Predictors of non-calcified plaques in the coronary arteries of 242 subjects using multislice computed tomography and logistic regression models.

OBJECTIVES: We detected non-calcified plaques (NCPs) in the coronary arteries using multislice computed tomography (MSCT) in order to determine the predictors of NCPs using logistic regression models. METHODS: Two hundred and forty-two consecutive subjects (141 males; overall age range, 17-91 years old) underwent enhanced electrocardiogram-gated MSCT to detect NCPs. Logistic models for predicting NCPs were developed which incorporated age, sex, coronary calcified-plaque (CP), and the following coronary risk factors (RFs): hypertension (HT), diabetes mellitus (DM), hyperlipidemia (HL), a smoking habit, and obesity. RESULTS: NCPs were detected in 76 subjects (59 males, 35-82 years old [median=67]) whose average number of coronary RFs was 2.6, 75% of whom presented with HT, 30% with DM, 51% with HL, 64% were present or past cigarette smokers, and 32% were obese. In the 76 subjects with NCPs, the incidence of male sex, presence of HT, a smoking habit, CP and the number of coronary RFs were significantly higher than in the 166 subjects without NCP. Of the 101 female subjects, 17 showed NCPs and in every case the subject was more than 50 years old. In a logistic regression model, male sex, HT and smoking habit (relative risks 2.7, 2.0, and 2.7 [95% confidence interval=1.3-5.6, 1.0-4.0, and 1.5-4.9, respectively]) were associated with increased incidence of NCPs. CONCLUSIONS: The incidence of NCPs was significantly increased in the presence of HT and a smoking habit, suggesting that lesions may be caused by HT or smoking-induced vessel injury even in the young male.

Abstracting and Indexing↗