Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “model selection”

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 1,225 records · Page 68Linked to original sources
PubMed2002

Monoclonal anti-epidermal growth factor receptor (ior EGF/r3) antibody pharmacokinetic studies on nude mice I: a radio-receptor analysis applied to drug serum quantification.

Due to its antagonistic properties upon ligand-epidermal growth factor receptor (EGFr) interaction, the monoclonal antibody anti-EGFr ior EGF/r3 is considered a potential therapeutic agent against several epithelium-derived tumours. This paper affords further analysis of the relevant corporal interaction of this monoclonal antibody in terms of its pharmacodynamic properties, using nude mice, following a single bolus intravenous dose administration. The radio-receptor assay allows quantification of the serum ior EGF/r3 level. The dose selection procedure, according to the Kolmogorov-Smirnov test, suggested using doses of 12.5-16 mg kg(-1) for pharmacokinetic assessments. The experimental data were best fitted to a bi-exponential function (r2 = 0.985), through the classical two-compartment open modelling approach. The model selection was corroborated by the AKAIKE information criteria, and also the SCHWARTZ and ESTRIP test were used. The estimated pharmacokinetic parameters (e.g. t 1/2 beta = 34.65 h, Vc = 2.84 mL, Vss = 4.21 mL and CL = 0.09 mL h(-1)) bear out the strategies for the evaluation of the therapeutic application of this drug. Finally, the radio-receptor analysis has provided a rationale for the proposed serum monoclonal antibody ior EGF/r3 quantification to characterize its concentration-time course.

Animals↗
PubMedDate not supplied

Developing psychodynamic group treatment methods for aggressive male inpatients.

Group psychotherapy is one intervention that can be used for aggressive male inpatients. This paper reports relevant literature and clinical applications for conducting a psychodynamic psychotherapy group designed to help patients (a) identify, understand, and deal with underlying problems resulting in aggressive behavior; (b) improve interpersonal relationships; and (c) find more appropriate ways of expressing feelings, particularly those associated with aggressive behavior. The review of literature focuses on therapeutic approaches for dealing with aggressive feelings in group therapy; men's issues in group psychotherapy, including stages of group development for men and the expression of aggression; and the outcome of aggressive behavior in response to group therapy. Clinical applications discussed are preparation for the group; the group contract, including the "group as a whole" approach; patient selection; modeling authority; and countertransference and projective identification.

Adaptation, Psychological↗
PubMed2000

Shorter hospital stays for angioplasty patients who receive abciximab.

The purpose of this retrospective study is to examine the effect of abciximab treatment on hospital length of stay for patients undergoing angioplasty in a naturalistic setting. Multivariate analysis was used to control for a wide range of factors (patient demographics, insurance provider, health conditions, admission and discharge information, and hospital characteristics) that may influence length of stay. Estimation was conducted on a sample of 13,384 angioplasty patients via a two-stage sample selection model. In addition, the model was re-estimated for a subgroup of 4,800 patients who underwent angioplasty and were also diagnosed with acute myocardial infarction. The study finds that patients in poorer health were more likely to receive abciximab. After adjusting for high-risk indications and selection bias, results also indicate that angioplasty patients (n = 13,384) who are given abciximab have a significantly shorter length of stay (0.89+/-0.12 fewer days) than those patients who did not receive abciximab. In a subgroup analysis of patients who had an acute myocardial infarction (n = 4,800), patients receiving abciximab were also found to have significantly shorter hospital stays (0.54+/-0.26 fewer days) than patients who did not receive abciximab. These results indicate that there are potential economic benefits for hospitals administering abciximab.

Abciximab↗
PubMed2004

Ageing and health-care expenditure: the red herring argument revisited.

Zweifel and colleagues have previously proposed that proximity to death is a more important influence on health-care costs than age, suggesting that demographic change per se will not have a large impact on future aggregate health expenditure. However, issues of econometric methodology have led to challenges of the robustness of these findings. This paper revisits the analysis. Using a longitudinal hospital data set from Oxfordshire, England, the two-step Heckman model from the Zweifel study is first replicated, to find that neither age nor proximity to death have a significant effect on hospital costs. Econometric problems with the model are demonstrated, and instead a two-part model shows both age and proximity to death to have significant effects on quarterly hospital costs. Cost predictions, calculated with bootstrapped 95% confidence intervals, further demonstrate that while age may significantly affect quarterly costs, these cost changes are small compared to the tripling of quarterly costs that occurs with approaching death in the last year of life. The analyses show the importance of model selection to properly assess the determinants of health-care expenditures.

Aged↗
PubMed2006

Bivariate survival modeling: a Bayesian approach based on Copulas.

Copula models have become increasingly popular for modeling multivariate survival data. In this paper we review some of the recent work that has been appeared for copula model for bivariate survival data and propose a Bayesian modeling. Our approach is very flexible with respect to the choice of marginal distributions and, depending on the copula model employed, it is possible to have a class of variation for the dependence parameter. We compare some of the copula models using a descriptive diagnostic method and three popular Bayesian model selection criteria. Our methodology is illustrated with the Diabetic Retinopathy Study (1976).

Bayes Theorem↗
PubMed1994

Application of the case management model to a trauma patient.

Alternative models and patterns of health care delivery have emerged in order to decrease institutional costs and maintain quality of care. The case management model, an alternative health care delivery model, serves as a framework for the delivery of care to trauma patients with multiple injuries. In this article, we review delivery of care, the role of the case manager, and components of the case management model: selection of patient, health assessment, planning and coordination of care, monitoring, and evaluation of outcomes.

Humans↗
PubMed1997

Hepatic foci in rats after diethylnitrosamine initiation and 2,3,7,8-tetrachlorodibenzo-p-dioxin promotion: evaluation of a quantitative two-cell model and of CYP 1A1/1A2 as a dosimeter.

2,3,7,8-Tetrachlorodibenzo-p-dioxin (TCDD) is a potent hepatic tumor promoter in female rats. We used a quantitative, stochastic initiation-promotion model based on R. B. Conolly and J. S. Kimbell (Toxicol. Appl. Pharmacol. 124, 284-295, 1994) to analyze initiation-promotion results from a previously published study (H. C. Pitot et al., Carcinogenesis 8, 1491-1499, 1987) within the context of a negative selection model of tumor promotion. In this model, two types of initiated cells (called A and B cells) are produced by DEN initiation. Visually excellent correspondence between model predictions and data (i.e., foci/cm3 liver and percentage of liver occupied by foci) are obtained when TCDD is described as having dose-responsive effects on division and death (apoptotic) rates of these two cell types. For A cells, both the division and the death rates increase while the difference between division and apoptotic rates decreases. For B cells, the difference between division and apoptotic rates increases, primarily due to a decrease in the apoptotic rate. We also linked these alterations in cell kinetics to a pharmacokinetic model for TCDD incorporating a five subcompartment model of the liver acinus with induction of CYP1A1 and 1A2 genes in the subcompartments. Alterations in A cell kinetics correlate with effects of TCDD in the region most sensitive to induction (subcompartment 5-centrilobular region); B cell dynamics correlate with induction in subcompartments 3-5 (centrilobular and mid-zonal regions). In summary, these modeling exercises show that (1) the two-cell model, without presuming effects of TCDD on the mutation rate of normal hepatocytes, reproduces the data of Pitot et al. (1987) and (2) induction of CYP1A1/1A2 in different regions of the hepatic acinus can be used as a general correlate of these presumed changes in cell growth kinetics.

Animals↗
PubMed2004

Model-based detection of lung nodules in computed tomography exams. Thoracic computer-aided diagnosis.

RATIONALE AND OBJECTIVES: In this study, we developed a prototype model-based computer aided detection (CAD) system designed to automatically detect both solid and subsolid pulmonary nodules in computed tomography (CT) images. By using this CAD algorithm, along with the radiologist's initial interpretation, we aim to improve the sensitivity of radiologic readings of CT lung exams. MATERIALS AND METHODS: We have developed a model-based CAD algorithm through the use of precise mathematic models that capture scanner physics and anatomic information. Our model-based CAD algorithm uses multiple segmentation algorithms to extract noteworthy structures in the lungs and a Bayesian statistical model selection framework to determine the probability of various anatomical events throughout the lung. We tested this algorithm on 50 low-dose CT lung cancer screening cases in which ground truth was produced through readings by three expert chest radiologists. RESULTS: Using this model-based CAD algorithm on 50 low-dose CT cases, we measured potential sensitivity improvements of 7% and 5% in two radiologists with respect to all noncalcified nodules, solid and subsolid, greater than 5 mm in diameter. The third radiologist did not miss any nodules in the ground truth set. The CAD algorithm produced 8.3 false positives per case. CONCLUSION: Our prototype CAD system demonstrates promising results as a tool to improve the quality of radiologic readings by increasing radiologist sensitivity. A significant advantage of this model-based approach is that it can be easily extended to support additional anatomic models as clinical understanding and scanning practices improve.

Algorithms↗
PubMed1990

Analysis of multi-type recurrent events in longitudinal studies; application to a skin cancer prevention trial.

We consider the statistical modeling and analysis of replicated multi-type point process data with covariates. Such data arise when heterogeneous subjects experience repeated events or failures which may be of several distinct types. The underlying processes are modeled as nonhomogeneous mixed Poisson processes with random (subject) and fixed (covariate) effects. The method of maximum likelihood is used to obtain estimates and standard errors of the failure rate parameters and regression coefficients. Score tests and likelihood ratio statistics are used for covariate selection. A graphical test of goodness of fit of the selected model is based on generalized residuals. Measures for determining the influence of an individual observation on the estimated regression coefficients and on the score test statistic are developed. An application is described to a large ongoing randomized controlled clinical trial for the efficacy of nutritional supplements of selenium for the prevention of two types of skin cancer.

Analysis of Variance↗
PubMed2002

5D-QSAR: the key for simulating induced fit?

In this journal we recently reported the development and the validation of a four-dimensional (4D)-QSAR (quantitative structure-activity relationships) concept, allowing for multiple conformation, orientation, and protonation state representation of ligand molecules. While this approach significantly reduces the bias with selecting a bioactive conformer, orientation, or protonation state, it still requires a "sophisticated guess" about manifestation and magnitude of the associated local induced fit-the adaptation of the receptor binding pocket to the individual ligand topology. We have therefore extended our concept (software Quasar) by an additional degree of freedom--the fifth dimension--allowing for a multiple representation of the topology of the quasi-atomistic receptor surrogate. While this entity may be generated using up to six different induced-fit protocols, we demonstrate that the simulated evolution converges to a single model and that 5D-QSAR--due to the fact that model selection may vary throughout the entire simulation--yields less biased results than 4D-QSAR where only a single induced- fit model can be evaluated at a time. Using two bioregulators (the neurokinin-1 receptor and the aryl hydrocarbon receptor), we compare the results obtained with 4D- and 5D-QSAR. The NK-1 receptor system (represented by a total of 65 antagonist molecules) converges at a cross-validated r2 of 0.870 and a predictive r2 of 0.837; the corresponding values for the Ah receptor system (represented by a total of 131 dibenzodioxins, dibenzofurans, biphenyls, and polyaromatic hydrocarbons) are 0.838 and 0.832, respectively. The results indicate that the formal investment of additional computer time is well-returned both in quantitative and in qualitative values: less-biased boundary conditions, healthier (i.e., less inbred) model populations, and more accurate predictions of new compounds.

Ligands↗
PubMed2025

Optimal Control of Directional False Discovery Rates in Large-Scale Testing.

The high-throughput biomedical technology enables measurement of thousands of gene expression levels contemporaneously. A major task in analyzing these gene expression data is to identify both over-expressed and under-expressed genes. The popular two-group models select the non-null genes without further classifying them as overexpression or underexpression. Consequently, two-group decision rules are unable to constrain the numbers of falsely discovered over-expressed or under-expressed genes respectively. We propose a general three-group model that allows dependence between the test statistics and develop a decision rule that separately controls the two types of false discoveries. We show that the optimal decision rule in our three-group model has a special monotonic structure. By making use of this monotonic structure, we can linearize the two-directional false discovery rate constraints. We prove that our decision rule optimizes the expected number of true discoveries while controlling the proportions of falsely discovered over-expressed and under-expressed genes at desired levels simultaneously. The data-driven versions of the proposed procedures are suggested, and their consistency is established. Comparisons with state-of-the-art approaches and applications to genomic studies show that our procedures work well.

Humans↗
PubMed2003

The analysis of profile data--revisited.

We revisit a former problem that led to much commentary regarding a proposed use of testing whether profiles for several groups in a repeated measurement scenario were parallel. Here we review previous approaches and propose Bayesian model selection to indicate whether the profiles can be considered parallel and if so support an estimation procedure for the profile differences.

Analysis of Variance↗
PubMed1990

The use of logit models to investigate social and biological factors in infant mortality. V: A multilogit analysis of stillbirths, neonatal and post-neonatal mortality.

Infant mortality data for England and Wales, cross classified by mother's age, parity and social class were published for 1949/50 and 1975. Previous analyses of these data have been based on graphical, tabular and logit models of stillbirths, neonatal and post-neonatal deaths separately. This paper summarizes the overall changes in infant mortality using a multilogit model. The model selected is illustrated by appropriate graphical presentations.

Adolescent↗
PubMed1994

Analysis of longitudinal data: random coefficient regression modelling.

We review random coefficient regression (RCR) models and methods for fitting these models from an applications perspective. Methods for data with exponential family distributions are presented with the Gaussian distribution as a special case. Attention is given to interpretation of fixed effects and the correlation structures implied by RCR models. Estimation methods are presented wtih computational approaches. Problems associated with testing fixed effects include accurate variance estimation and robustness to misspecification of the covariance structure. Methods for model selection and assessment are presented. An example is used to demonstrate recommended approaches.

Adult↗
PubMed2005

Accelerated degradation models for failure based on geometric Brownian motion and gamma processes.

Based on a generalized cumulative damage approach with a stochastic process describing degradation, new accelerated life test models are presented in which both observed failures and degradation measures can be considered for parametric inference of system lifetime. Incorporating an accelerated test variable, we provide several new accelerated degradation models for failure based on the geometric Brownian motion or gamma process. It is shown that in most cases, our models for failure can be approximated closely by accelerated test versions of Birnbaum-Saunders and inverse Gaussian distributions. Estimation of model parameters and a model selection procedure are discussed, and two illustrative examples using real data for carbon-film resistors and fatigue crack size are presented.

Equipment Failure Analysis↗
PubMed2004

Advances on BYY harmony learning: information theoretic perspective, generalized projection geometry, and independent factor autodetermination.

The nature of Bayesian Ying-Yang harmony learning is reexamined from an information theoretic perspective. Not only its ability for model selection and regularization is explained with new insights, but also discussions are made on its relations and differences from the studies of minimum description length (MDL), Bayesian approach, the bit-back based MDL, Akaike information criterion (AIC), maximum likelihood, information geometry, Helmholtz machines, and variational approximation. Moreover, a generalized projection geometry is introduced for further understanding such a new mechanism. Furthermore, new algorithms are also developed for implementing Gaussian factor analysis (FA) and non-Gaussian factor analysis (NFA) such that selecting appropriate factors is automatically made during parameter learning.

Algorithms↗
PubMedDate not supplied

[Myocardial infarct in diabetes mellitus: short- and long-term prognostic factors].

To determine the evolution of acute myocardial infarction in patients with diabetes we study 207 consecutive patients with myocardial infarction. Using WHO's criteria 23% of our cases were diagnosed of diabetes mellitus. Diabetic patients were older than non diabetic (67.9 +/- 10 years vs. 62.4 +/- 11 years, p less than 0.05) and had a higher ratio of females (52% vs. 21%, p less than 0.001). Cigarette smoking was infrequent in diabetic population. Incidence of other risk factors was comparable. Despite an increased proportion on no q-wave myocardial infarction in the diabetic patients (12.5% vs. 6.9%, p NS), the site of infarction was similar into the two groups. Acute phase mortality was higher in the diabetic group (37.5% vs. 16.3%, p less than 0.001). This increased mortality is, partially, related to an increased incidence of pump failure, but a multivariate analysis using stepwise logistic regression, selected diabetes as an independent predictor of prognosis. Survivors were followed for 41 +/- 20 months; diabetic patients showed a poor prognosis with a higher incidence of congestive heart failure (42.8% vs. 13.7%, p less than 0.01), reinfarction (16.6% vs. 8.5%) and death. Cox proportional hazard model selected diabetes as an independent predictor of survival. We conclude that patients with diabetes mellitus constitute a subgroup into the myocardial infarction population; this subgroup had greater mortality than non diabetic patients in relation to increased incidence of pump failure, but multivariate analysis indicates that other factors not considered in the present study may play a role in their poor prognosis.

Aged↗
PubMed2005

Prediction of coronary artery disease severity in patients referred for coronary angiography.

BACKGROUND: Diagnostic coronary angiography is often followed by coronary stenting. Therapy with aspirin and clopidogrel is currently the standard treatment for patients undergoing coronary stenting. Clopidogrel loading is usually given prior to the procedure. Some pretreated patients, however, are found to have triple-vessel disease (3VD) or left main disease (LMD) that requires referral for coronary artery bypass graft (CABG) surgery. Surgery in patients pretreated with clopidogrel may be complicated by excessive bleeding or delayed to avoid that risk. HYPOTHESIS: A risk factor-based formula may predict the likelihood that patients referred for coronary angiography will have 3VD or LMD. METHODS: Consecutive patients (n = 2,180) referred for coronary angiography constitute the training subset (n = 1,296) used to build the model, and the validation subset (n = 884) used to test the model. Logistic regression models selected five variables showing strong associations with the presence of 3VD or LMD: age, gender, diabetes, hypercholesterolemia, and prior myocardial infarction (MI). A formula based on these variables and on the training subset was constructed to calculate the probability of 3VD or LMD. RESULTS: Applying this model to the validation subset predicted 3VD or LMD with 79% sensitivity, 53% specificity, 45% positive predictive value, and 83% negative predictive value. CONCLUSIONS: This simple formula based on five clinical variables is helpful in predicting the likelihood that patients, referred for coronary angiography, will have 3VD or LMD. Use of this formula can help decide in which patients clopidogrel loading prior to angiography should be avoided.

Adult↗