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 613 records · Page 34Linked to original sources

PubMed2001

Surgical antibiotic prophylaxis: effect in postoperative infections.

OBJECTIVE: to assess the risk of surgical wound infection and hospital acquired infections among patients with and without adequate antibiotic prophylaxis. Also, to provide models to predict the contributing factors of hospital infection and surgical wound infection. DESIGN: survey study. Prospective cohort study over 14 months, with data collected by a nurse and a epidemiologist through visits to the surgical areas, a review of the medical record and consultation with the medical doctor and nurses attending the patients. SETTING: Two hundred and fifty bed, general hospital serving Puertollano (Ciudad Real), population--50,000. RESULTS: between February 1998 and April 1999, 754 patients underwent surgery, 263 (34.88%) received appropriate perioperative prophylaxis while 491 (65.12%) received inadequate prophylaxis. For those who received adequate antibiotic prophylaxis, the percentage of nosocomial infection was 10.65% compared with the group who received inadequate prophylaxis in which the percentage of nosocomial infection was 33.40%. The relative risk of nosocomial infection was, therefore, 4.21 times higher in the latter group (confidence intervals 95%: 2.71-6.51). A patient in the inadequate prophylaxis group had a 14.87% chance of wound infection while a patient in the adequate prophylaxis group had a 4.56% chance of wound infection. The relative risk of wound infection was 3.65 times higher in the group that received inadequate prophylaxis (confidence intervals 95%: 1.95-6.86). The final regression logistic model to assess nosocomial infection incorporated seven prognostic factors: age, length of venous periferic route, vesicle catheter, duration of operation, obesity, metabolic or neoplasm diseases and adequate or inadequate prophylaxis. When we incorporated these variables in the multi-factorial analysis we found that the relative risk of developing nosocomial infection was 2.33 times higher in the group which received inadequate prophylaxis. When we applied the second logistic multiple regression model (wound infection), we discovered that the probability of developing surgical wound infection was 2.32 times higher in the group which received inadequate prophylaxis as opposed to the group, which received adequate prophylaxis. The goodness of fit (Hosmer-Lemeshow test) showed a correct significance in all models. CONCLUSIONS: a multi-factorial analysis was applied to identify the high-risk patients and the risk factors for postoperative infections. Through the application of these multiple regression logistic models, we conclude that the correct antibiotic prophylaxis is effective and will subsequently reduce postoperative infection rates, especially in high-risk patients. Therefore, the choice of antimicrobial agent should be made on the basis of the criteria of hospital committee.

Antibiotic Prophylaxis↗

PubMed1990

[Time-related incidence of AIDS--epidemiological developments in various groups with increased risk of HIV infection].

It is no longer possible to depict the number of AIDS cases over time as an exponential curve. In the group of homosexual/bisexual men, who still account for nearly 70% of all cases, the increase in the logistic model has reached a maximum (turning point of the logistic function). Nevertheless, in this group increasing numbers of cases are still to be expected. In the case of injecting drug users no such turning point can yet be detected with sufficient statistical accuracy.

AIDS-Related Complex↗

PubMed2005

Weaknesses of goodness-of-fit tests for evaluating propensity score models: the case of the omitted confounder.

PURPOSE: Propensity scores are used in observational studies to adjust for confounding, although they do not provide control for confounders omitted from the propensity score model. We sought to determine if tests used to evaluate logistic model fit and discrimination would be helpful in detecting the omission of an important confounder in the propensity score. METHODS: Using simulated data, we estimated propensity scores under two scenarios: (1) including all confounders and (2) omitting the binary confounder. We compared the propensity score model fit and discrimination under each scenario, using the Hosmer-Lemeshow goodness-of-fit (GOF) test and the c-statistic. We measured residual confounding in treatment effect estimates adjusted by the propensity score omitting the confounder. RESULTS: The GOF statistic and discrimination of propensity score models were the same for models excluding an important predictor of treatment compared to the full propensity score model. The GOF test failed to detect poor model fit for the propensity score model omitting the confounder. C-statistics under both scenarios were similar. Residual confounding was observed from using the propensity score excluding the confounder (range: 1-30%). CONCLUSIONS: Omission of important confounders from the propensity score leads to residual confounding in estimates of treatment effect. However, tests of GOF and discrimination do not provide information to detect missing confounders in propensity score models. Our findings suggest that it may not be necessary to compute GOF statistics or model discrimination when developing propensity score models.

Confounding Factors, Epidemiologic↗

PubMed2006

Use of linear, Weibull, and log-logistic functions to model pressure inactivation of seven foodborne pathogens in milk.

Survival curves of six foodborne pathogens suspended in ultra high-temperature (UHT) whole milk and exposed to high hydrostatic pressure at 21.5 degrees C were obtained. Vibrio parahaemolyticus was treated at 300 MPa and other pathogens, Listeria monocytogenes, Escherichia coli O157:H7, Salmonella enterica serovar Enteritidis, Salmonella enterica serovar Typhimurium, and Staphylococcus aureus were treated at 600 MPa. All the survival curves showed a rapid initial drop in bacterial counts followed by tailing caused by a diminishing inactivation rate. A linear model and two nonlinear models were fitted to these data and the performances of these models were compared using mean square error (MSE) values. The log-logistic and Weibull models consistently produced better fits to the inactivation data than the linear model. The mean MSE value of the linear model was 6.1, while the mean MSE values were 0.7 for the Weibull model and 0.3 for the log-logistic model. There was no correlation between pressure resistance and the taxonomic group the bacteria belong to. The order, most to least pressure-sensitive, of the single strains tested was: V. parahaemolyticus (gram negative)<L. monocytogenes (gram positive)<Salmonella Typhimurium (gram negative) approximately = Salmonella Enteritidis (gram negative)<E. coli O157:H7 approximately = Staphylocollus aureus (gram positive)<Shigella flexneri (gram negative). The most pressure-resistant gram-negative bacterium, Shigella flexneri, and most pressure resistant gram-positive bacterium, Staphylocollus aureus, were pressurized at 50 degrees C. Staphylocollus aureus was treated at 500 MPa and Shigella flexneri at 600 MPa. Elevated temperature considerably enhanced pressure inactivation of these two pathogens, but did not affect the overall shape of the survival curves. Pressure level (250 MPa) and substrate (1% peptone water plus 3% NaCl) in which V. parahaemolyticus was suspended affected the shape of survival curves of V. parahaemolyticus.

Animals↗

PubMed1998

Occurrence and clinical significance of thrombocytopenia in a population undergoing high-risk percutaneous coronary revascularization. Evaluation of c7E3 for the Prevention of Ischemic Complications (EPIC) Study Group.

OBJECTIVES: This study sought to determine the frequency of thrombocytopenia and its relation with clinical outcomes in high risk patients undergoing percutaneous coronary revascularization who received either the platelet glycoprotein (GP) IIb/IIIa receptor antagonist abciximab (ReoPro, c7E3 Fab) or conventional therapy. BACKGROUND: The development of thrombocytopenia on exposure to GPIIb/IIIa antagonists threatens the utility and economic viability of this drug class for patients with vascular disease. METHODS: We analyzed data from the Evaluation of c7E3 for the Prevention of Ischemic Complications trial (EPIC), a 2,099-patient, randomized trial of placebo, abciximab bolus or abciximab bolus plus a 12-h infusion during high-risk coronary revascularization. RESULTS: Thrombocytopenia (nadir platelet count <100 x 10(9)/ liter) developed in 81 patients (3.9%) during their hospital stay, with 19 (0.9%) developing severe (<50 x 10(9)/liter) thrombocytopenia. Both thrombocytopenia and severe thrombocytopenia were more frequent in the bolus-plus-infusion arm (5.2% and 1.6%, respectively) than in the bolus-only and placebo arms combined (p = 0.020 and p = 0.025, respectively). Acute profound thrombocytopenia developed in two patients in the bolus-plus-infusion arm. Patients with thrombocytopenia experienced more unfavorable clinical outcomes than those who did not develop thrombocytopenia, regardless of treatment assignment, but those with thrombocytopenia who received abciximab had fewer worse outcomes at 30 days. Multivariable logistic modeling revealed a lower baseline platelet count, older age and lighter weight to be important predictors of thrombocytopenia. In a logistic regression model, bolus-plus-infusion treatment was a significant predictor of thrombocytopenia (p = 0.016) and remained so after adjustment for procedures and baseline risk factors (p = 0.0077). CONCLUSIONS: Thrombocytopenia was associated with adverse clinical outcomes and excessive bleeding, but patients receiving abciximab fared better than those receiving placebo.

Abciximab↗

PubMed2006

Establishing the change in antibiotic resistance of Enterococcus faecium strains isolated from Dutch broilers by logistic regression and survival analysis.

In this study, we investigated the change in the resistance of Enterococcus faecium strains isolated from Dutch broilers against erythromycin and virginiamycin in 1998, 1999 and 2001 by logistic regression analysis and survival analysis. The E. faecium strains were isolated from caecal samples that had been randomly collected from six slaughterhouses. Moreover, between the sample collection in 1998 and the sample collection in 1999, virginiamycin and the macrolide antibiotics (of which erythromycin is a member) have been banned in The Netherlands from use in broiler feeds as growth promoter. In the logistic regression analysis we used the internationally accepted cut-off values to determine whether bacteria were resistant or not. In the survival analysis, inhibition of bacterial growth was the event and time to event was replaced by concentration of antibiotic to event. As a consequence, changes in the growth of bacteria can be tested over an entire range of concentrations and no cut-off value for resistance has to be determined. We performed the survival analysis by use of a Cox logistic model with an odds ratio (OR) for the increase of the odds of the basic hazard rate as outcome. Both the logistic regression and the survival analyses showed that resistance to erythromycin and virginiamycin decreased during the study period. In the logistic regression model the ORs associated with the fraction of bacteria inhibited by the antibiotics in 2001 as compared to 1998 were 3.76 (2.57-5.49) for erythromycin and 11.65 (7.68-17.66) for virginiamycin. The corresponding ORs from the survival analysis were lower; 2.88 (2.21-3.76) and 2.11 (1.80-2.49), respectively. The reason for the differences between the ORs of the survival analysis and the logistic regression analysis is probably because most changes in resistance included the cut-off value and logistic regression specifically examines those changes.

Abattoirs↗

PubMed1998

Comparison of multiple prediction models for ambulation following spinal cord injury.

Few studies have properly compared predictive performance of different models using the same medical data set. We developed and compared 3 models (logistic regression, neural networks, and rough sets) in the in prediction of ambulation at hospital discharge following spinal cord injury. We used the multi-center Spinal Cord Injury Model System database. All models performed well and had areas under the receiver operating characteristic curve in the 0.88-0.91 range. All models had sensitivity, specificity, and accuracy greater than 80% at ideal thresholds. The performance of neural network and logistic regression methods was not statistically different (p = 0.48). The rough sets classifier performed statistically worse than either the neural network or logistic regression models (p-values 0.002 and 0.015 respectively).

Acute Disease↗

PubMed2003

How many IRT parameters does it take to model psychopathology items?

The authors compared the fit of the 2- and 3-parameter logistic models (2PLM; 3PLM) on 15 unidimensional factor scales derived from the Minnesota Multiphasic Personality Inventory--Adolescent item pool. Log-likelihood chi-square deviance tests indicated that a 3PLM provided an improved fit. However, residual statistics indicated that the difference in fit between the 2 models was negligible. An unexpected finding was that from 10% to 30% of the items had substantial lower asymptote parameters (c > or = .10) when the scales were scored in the pathology or nonpathology directions. The authors argue that the large lower asymptote parameters are attributable to item-content ambiguity possibly caused by item-level multidimensionality. These findings suggest that the direction of scoring can critically affect an item response theory analysis.

Adolescent↗

PubMed2003

Logistic or additive EuroSCORE for high-risk patients?

OBJECTIVES: To assess whether the use of the full logistic European System for Cardiac Operative Risk Evaluation (EuroSCORE) is superior to the standard additive EuroSCORE in predicting mortality in high-risk cardiac surgical patients. METHODS: Both the simple additive EuroSCORE and the full logistic EuroSCORE were applied to 14,799 cardiac surgical patients from across Europe, of whom there were 4293 high-risk patients (additive EuroSCORE of 6 or more). The systems were compared for absolute prediction and discrimination (area under the receiver operating characteristic (ROC) curve). RESULTS: Actual mortality was 4.72%. The logistic model was closer to this than the additive model (4.84% (4.72-4.94) versus 4.21 (4.21-4.26)). Most of this difference was due to high-risk patients where actual mortality was 11.18% and predicted was 7.83% (additive) and 11.23% (logistic). Discrimination was similar in both systems as measured by the area under the ROC curve (additive 0.783, logistic 0.785). CONCLUSIONS: The additive EuroSCORE model remains a simple "gold standard" for risk assessment in European cardiac surgery, usable at the bedside without complex calculations or information technology. The logistic model is a better risk predictor especially in high-risk patients and may be of interest to institutions engaged in the study and development of risk stratification.

Aged↗

PubMed2001

Dietary patterns, nutrient intake and gastric cancer in a high-risk area of Italy.

OBJECTIVES: To better understand the role of overall dietary patterns and major energy-providing components in gastric cancer etiology. METHODS: In a population-based case-control study conducted in a high-risk area in central Italy, 382 gastric cancer cases and 561 controls were available for analysis. Multivariate models based on energy-adjusted residuals and completely partitioned logistic models were used; dietary patterns were evaluated by factor analysis and multiple correspondence analysis. RESULTS: Gastric cancer risk was inversely related to high energy-adjusted intakes of vegetable fat, sugar, beta-carotene, vitamin C, alpha-tocopherol, and nitrates. In contrast, significant positive associations emerged with high intake of protein, nitrite, and sodium. According to energy decomposition models, gastric cancer risk increased with increasing intake of protein and decreased with increasing intake of sugar and total fat. The pattern analysis identified four dietary profiles, overall explaining 75% of total dietary variability. Two patterns, named "traditional" and "vitamin-rich", were strongly associated with gastric cancer risk and overall accounted for 44% of estimated gastric cancer attributable risk. The other two patterns, "refined" and "fat-rich", were not consistently associated with gastric cancer. CONCLUSION: Innovative methodological approaches may contribute to better evaluation of the complex relationship between diet and cancer risk and to planning dietary interventions.

Adult↗

PubMed2000

Methods of ordinal classification applied to medical scoring systems.

Scoring systems are used in nearly all fields of medicine for evaluation of the state of a disease. The prediction performance of scoring systems with respect to an ordinal outcome scale is investigated, based on grouped continuous logistic models as well as on an extension of the stereotype logistic regression model. The latter is a canonical approach, which allows assessment of properties of outcome categories such as partial and total ordering, distinguishability and allocatability. The approach is applied to a data set of patients with injuries of the head.

Cerebral Arteries↗

PubMed1999

Redundancy of single diagnostic test evaluation.

Diagnostic research and diagnostic practice frequently do not cohere. Studies commonly evaluate whether a single test discriminates between disease presence and absence, whereas in practice a test is always judged in the context of other information. This study illustrates drawbacks of single-test evaluation and discusses principles of diagnostic research. We used data on 140 patients suspected of pulmonary embolism who had an inconclusive ventilation-perfusion lung scan. We evaluated three tests: partial pressure of oxygen in arterial blood (PaO2), x-ray film of the thorax, and leg ultrasound. On the basis of single-test evaluations, ultrasound was most informative. Given a prior probability of 0.27, it had a much better combination of positive and negative predictive value (0.71 and 0.21, respectively) relative to thorax x-ray (0.33 and 0.11) and PaO2 (0.35 and 0.27). The combination of positive and negative likelihood ratio was also more promising for ultrasound (7.3 and 0.7) than for thorax x-ray (1.3 and 0.3) and PaO2 (1.3 and 0.9). As the tests are always performed after the history and physical, we judged their added value using multivariable logistic modeling with receiver operating characteristic (ROC) analyses. The ROC areas of the model, including history and physical, with additional PaO2, thorax x-ray, or ultrasound, were 0.75, 0.77, 0.81, and 0.81, respectively, which indicated similar added value of thorax x-ray and ultrasound. Application of the models to patient subgroups also yielded added predictive value for thorax x-ray film. Thus, the results of single-test evaluations may be very misleading. As no diagnosis is based on one test, single-test evaluations have limited value in diagnostic research and only have relevance in the context of screening and the initial phase of test development. Diagnostic research should always apply an approach of constructing, extending, and validating diagnostic models in agreement with routine clinical work-up using logistic regression analyses.

Analysis of Variance↗

PubMed2002

Assessing risk factors for mortality in elderly White and African American people: implications of alternative analyses.

PURPOSE: The aim of this study was to ascertain whether the determinants of death differ as a function of type of analysis in a representative sample of older African American and White people with comparable mortality rates. DESIGN AND METHODS: Participants included all African American (n = 2,261) and White (n = 1,875) people at the Duke site of the Established Populations for Epidemiological Studies of the Elderly. Baseline information used to predict mortality 12 years later included demographic, health, and functional characteristics. Mortality (55% for African American people and 54% for White people) was determined through the National Death Index. Cox proportional hazards models, logistic regression, and tree-based classification analysis were used (separately for African American and White people) to identify risk factors for mortality. RESULTS: Risk factors for mortality were comparable, but the constellation of characteristics indicating higher risk for death differed between African American and White people. IMPLICATIONS: Proportional hazards and logistic regression identified risk factors in general; tree-based classification models identified the characteristics of groups at risk. The analysis used may influence the type and manner of intervention.

Aged↗

PubMed1993

Birth interval and family effects on postneonatal mortality in Brazil.

In this paper random-effects logistic models are used to analyze the effects of the preceding birth interval on postneonatal mortality in Brazil, controlling for the correlation of survival outcomes between siblings. The results are compared to those obtained by using ordinary logistic regression. Family effects are found to be highly significant in the random-effects model, but the substantive conclusions of the ordinary logistic model are preserved. In particular, birth interval effects remain highly significant.

Birth Intervals↗

PubMed2001

Uterine electrical activity as predictor of preterm birth in women with preterm contractions.

OBJECTIVE: To estimate the risk of preterm birth in women admitted to the tertiary maternity hospital for preterm contractions by measuring electrical uterine activity. STUDY DESIGN: The study included 47 patients with contractions between the 25th and 35th week of gestation and additional risk factors for preterm delivery. Uterine electrical activity was recorded using bipolar electrodes placed on the abdominal surface. A logistic model with the electromyographic and obstetric data was built, preterm delivery before 37th week of gestation being the outcome measure. RESULTS: Seventeen patients (36%) delivered before term. Logistic regression model suggested only the intensity of electrical uterine activity and woman's body weight to be significant predictors of preterm delivery, with high values related to preterm birth. They predict preterm delivery with the sensitivity of 47% and specificity of 90%. CONCLUSION: We propose uterine EMG as a simple, non-invasive means to estimate the risk of preterm birth in a high-risk population with multiple risk factors present.

Electromyography↗

PubMed2005

A Bayesian analysis of mouse infectivity data to evaluate the effectiveness of using ultraviolet light as a drinking water disinfectant.

Modelling disinfectant performance using Bayesian hierarchical methods can overcome problems with traditional methods and lead to improved estimates. Animal and cell-culture assays are used to estimate the degree of inactivation of a microorganism produced by a given disinfectant dose. Assay data traditionally are analyzed with logistic model or most probable number (MPN) method. These methods are limited particularly when assays show all (or no) animals or cells to be infected-estimates are reported as greater than (or less than) a measurement limit (i.e., censored data). The proposed Bayesian approach (1) properly models the propagation of uncertainty through the data analysis/modelling process, resulting in reduced model uncertainty, and (2) uses appropriate probability distribution models for the response variables, avoiding the censored data problem and more accurately describing statistical error when estimating dose-response behavior. This paper applies the Bayesian hierarchical models to logistic and MPN data from published papers for the ultraviolet (UV) inactivation of Cryptosporidium. Results are compared to those from three alternative models. The Bayesian model estimates a significantly lower UV dose for a given level of Cryptosporidium inactivation than the alternative models, due mainly to the reduced model uncertainty.

Animals↗

PubMed1993

An autologistic model for the genetic analysis of familial binary data.

Regressive logistic models specify the probability distribution of familial binary traits by conditioning each individual's phenotype on those of preceding relatives; therefore, the expression of the joint probability of the familial data necessitates ordering the observations. In the present paper, we propose an autologistic model of this familial dependence structure, which does not require specification of a particular ordering of the phenotypic observations. Genetic effects are introduced into the model in order to perform segregation analysis that is aimed at detecting the role of a major locus in the expression of familial phenotypes. In this model, the conditional probabilities have a logistic form, and large patterns of dependence between relatives can be considered with a simple interpretation of the parameters measuring the relationship between two phenotypes. The model is compared with the regressive logistic approach in terms of odds ratios and by using a simulation study.

Computer Simulation↗

PubMed2003

Developing and testing a model to predict outcomes of organizational change.

OBJECTIVE: To test the effectiveness of a Bayesian model employing subjective probability estimates for predicting success and failure of health care improvement projects. DATA SOURCES: Experts' subjective assessment data for model development and independent retrospective data on 221 healthcare improvement projects in the United States, Canada, and The Netherlands collected between 1996 and 2000 for validation. METHODS: A panel of theoretical and practical experts and literature in organizational change were used to identify factors predicting the outcome of improvement efforts. A Bayesian model was developed to estimate probability of successful change using subjective estimates of likelihood ratios and prior odds elicited from the panel of experts. A subsequent retrospective empirical analysis of change efforts in 198 health care organizations was performed to validate the model. Logistic regression and ROC analysis were used to evaluate the model's performance using three alternative definitions of success. DATA COLLECTION: For the model development, experts' subjective assessments were elicited using an integrative group process. For the validation study, a staff person intimately involved in each improvement project responded to a written survey asking questions about model factors and project outcomes. RESULTS: Logistic regression chi-square statistics and areas under the ROC curve demonstrated a high level of model performance in predicting success. Chi-square statistics were significant at the 0.001 level and areas under the ROC curve were greater than 0.84. CONCLUSIONS: A subjective Bayesian model was effective in predicting the outcome of actual improvement projects. Additional prospective evaluations as well as testing the impact of this model as an intervention are warranted.

Bayes Theorem↗