SEARCH · PubMed Health

Results for “bootstrap”

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 1,081 records · Page 60Linked to original sources

PubMedDate not supplied

Comparing the bivariate effects of toxicity and efficacy of treatments.

Medical studies often involve comparing the toxicity and efficacy of drugs. Separately evaluating toxicity and efficacy, the usual practice, does not correspond to how doctors manage patients and does not use the information provided in their bivariate relationship. This paper presents methods for analysing the bivariate data. One method is based on assessing the benefit for patient values to lie in different regions of the toxicity-efficacy plane. A second method includes patient thresholds for tolerating drugs. We propose dividing the toxicity-efficacy plane into regions where patients are likely to tolerate the drug. Several statistics are defined on these regions for measuring the toxic-therapeutic relationship, and the bootstrap is proposed for estimating their variances. We illustrate with treatment information available on rheumatoid arthritis patients.

Arthritis, Rheumatoid↗

PubMed1995

A multiple imputation strategy for clinical trials with truncation of patient data.

Clinical trials of drug treatments for psychiatric disorders commonly employ the parallel groups, placebo-controlled, repeated measure randomized comparison. When patients stop adhering to their originally assigned treatment, investigators often abandon data collection. Thus, non-adherence produces a monotone pattern of unit-level missing data, disabling the analysis by intent-to-treat. We propose an approach based on multiple imputation of the missing responses, using the approximate Bayesian bootstrap to draw ignorable repeated imputations from the posterior predictive distribution of the missing data, stratifying by a balancing score for the observed responses prior to withdrawal. We apply the method and some variations to data from a large randomized trial of treatments for panic disorder, and compare the results to those obtained by the original analysis that used the standard (endpoint) method.

Adult↗

PubMed1995

Confidence interval estimates of an index of quality performance based on logistic regression models.

This paper considers an index of hospital quality performance defined as the ratio of the observed number deaths to the number predicted by a fitted logistic regression model. We study tests and confidence intervals under two different scenarios depending on the availability of an estimate of the covariance matrix of the coefficients from the fitted logistic regression model. We propose parametric as well as bootstrap-based confidence intervals. We apply the methods to an analysis of the performance of 27 intensive care units.

Aged↗

PubMedDate not supplied

A GEE approach to estimating sensitivity and specificity and coverage properties of the confidence intervals.

A generalized estimating equation (GEE) approach is used to estimate the sensitivity and specificity of five non-culture screening tests for detecting Chlamydia trachomatis in endocervical specimens from women attending family planning clinics. Since the estimates of these parameters can be very close to the upper limit of one, confidence interval construction based on the traditional approaches, such as the delta method or a back-transformation approach, may not have the stated coverage. We compare different approaches to calculating confidence intervals for the sensitivity and specificity from the results of the GEE approach. These methods include the delta method, a back-transformation approach, and a bootstrap approach. In addition, we use simulations to investigate the estimated coverage rates of the delta method and the back-transformation approach. Published in 2001 by John Wiley & Sons, Ltd.

Chlamydia Infections↗

PubMed2001

A standardization method to adjust for the effect of patient selection in phase II clinical trials.

New combination regimens evaluated in phase II cancer clinical trials often show promising results compared to the standard therapy for a disease system. Selection of patients with a better prognosis can be a prominent factor for this optimism. For most disease systems, prognostic variables that are related to the outcome are available and are called risk factors. Patients are classified into risk categories depending on the number of risk factors they possess. The patient distribution is defined as the proportion of patients falling into each of these risk categories. Typically, the patient distribution observed for a phase II study differs from the standard therapy reports so that the outcomes are not comparable. A randomized trial is the ultimate step for establishing the efficacy of a new treatment. In order to determine whether a regimen should progress to a phase III trial, we suggest adjusting the standard therapy outcome for the effect of the observed phase II patient distribution. If the endpoint of interest is tumour response proportion, a weighted average utilizing the standard therapy response proportions and the phase II patient distribution would provide an estimate of the adjusted standard therapy response proportion. Confirmatory phase II trials often attempt to estimate median survival in addition to response proportion, since this is the primary endpoint for most phase III cancer studies. Because data are censored, we propose an adjustment method based on the bootstrap resampling technique. We illustrate the problem of disparate patient selection with data from melanoma studies and demonstrate the usefulness of the proposed adjustment method with data from bladder cancer studies. A simulation study indicates that the magnitude of the adjustment is heavily dependent on the degree of separation of the risk categories. SAS code is available on a website (http://lib.stat.cmu.edu) for easy implementation.

Antineoplastic Combined Chemotherapy Protocols↗

PubMed2001

Variance estimation of a survival function for interval-censored survival data.

Interval-censored survival data often occur in medical studies, especially in clinical trials. In this case, many authors have considered estimation of a survival function. There is, however, relatively little discussion on estimating the variance of estimated survival functions. For right-censored data, a special case of interval-censored data, the most commonly used method for variance estimation is to use the Greenwood formula. In this paper we propose a generalization of the Greenwood formula for variance estimation of a survival function based on interval-censored data. Also a simple bootstrap approach is presented. The two methods are evaluated and compared using simulation studies and a real data set. The simulation results suggest that the methods work well.

Analysis of Variance↗

PubMed2001

Analysis of change in the presence of informative censoring: application to a longitudinal clinical trial of progressive renal disease.

The rate of change in a continuous variable, measured serially over time, is often used as an outcome in longitudinal studies or clinical trials. When patients terminate the study before the scheduled end of the study, there is a potential for bias in estimation of rate of change using standard methods which ignore the missing data mechanism. These methods include the use of unweighted generalized estimating equations methods and likelihood-based methods assuming an ignorable missing data mechanism. We present a model for analysis of informatively censored data, based on an extension of the two-stage linear random effects model, where each subject's random intercept and slope are allowed to be associated with an underlying time to event. The joint distribution of the continuous responses and the time-to-event variable are then estimated via maximum likelihood using the EM algorithm, and using the bootstrap to calculate standard errors. We illustrate this methodology and compare it to simpler approaches and usual maximum likelihood using data from a multi-centre study of the effects of diet and blood pressure control on progression of renal disease, the Modification of Diet in Renal Disease (MDRD) Study. Sensitivity analyses and simulations are used to evaluate the performance of this methodology in the context of the MDRD data, under various scenarios where the drop-out mechanism is ignorable as well as non-ignorable.

Algorithms↗

PubMed2001

Order-restricted dose-related trend tests.

Methods of isotonic regression are proposed to increase the power of common trend tests in situations where a monotonicity constraint is imposed upon the dose-response function. Isotonic versions of Cochran-Armitage type trend tests for binary response data are developed, and the bootstrap method is used in finding the empirical distributions of the test statistics and their critical values. The isotonic likelihood ratio test with a survival adjustment is also proposed. This survival adjustment can be applied to the likelihood ratio test for either the order-restricted or unrestricted parameter cases. To achieve the isotonic modifications, an amalgamation algorithm is applied when the observed dose-response is non-monotonic. A Monte Carlo simulation study comparing these trend tests shows the advantages of the isotonic modifications and survival adjustment. By applying the proposed methods to data from a toxicology and carcinogenesis study conducted as part of the National Toxicology Program, the effect of CI Pigment Red 23 is investigated.

Adenocarcinoma, Clear Cell↗

PubMed2001

Phase specific analysis of herpes zoster associated pain data: a new statistical approach.

Herpes zoster or shingles is a frequent occurrence in both elderly individuals and immunocompromised hosts. The pain associated with herpes zoster is the most debilitating complication of the disease. It can be described as acute pain and post-herpetic neuralgia or zoster associated pain (ZAP). The latter definition encompasses pain from the onset of disease through its resolution and provides a convenient analytic tool for evaluation of antiviral therapy. A heuristic examination of ZAP historical data suggests the existence of three phases of pain resolution: the acute, subacute and chronic phases. The subacute and chronic phases comprise the post-herpetic neuralgia (PHN) stage. Common analytic methods, such as a Kaplan-Meier survival function or a Cox's model, have been used to assess the pain. However, such approaches do not adequately allow for phase comparison. Notably, in the clinical trial setting the comparison of specific treatment effects on the latter stages of pain are of the greatest medical relevance since this is the most debilitating phase of the illness. In order to incorporate the phase-specific information in the modelling of time to cessation of ZAP, we assumed the hazard function was a stepwise constant. Utilizing the full likelihood function, we obtained the maximum likelihood estimate for the transition times (that is, change-points), and other parameters of medical importance. The standard error of the change-point estimates were obtained through a bootstrapping method. The asymptotic properties of the parameter estimates are also discussed. Hence, the rates of pain resolution across all phases can be examined in order to precisely define the existence of multiple phases. In addition, the covariates effect can be examined across phases and populations, thereby allowing us to translate potential efficacy of a standard therapy to different populations. These results can be utilized in the design of clinical trials or in targeting the outcome for a specific phase while controlling for the effect of other variables.

Acute Disease↗

PubMed2001

Graphical model checking with correlated response data.

Correlated response data arise often in biomedical studies. The generalized estimation equation (GEE) approach is widely used in regression analysis for such data. However, there are few methods available to check the adequacy of regression models in GEE. In this paper, a graphical method is proposed based on Cook and Weisberg's marginal model plot. A bootstrap method is applied to obtain the reference band to assess statistical uncertainties in comparing two marginal mean functions. We also propose using the generalized additive model (GAM) in a similar fashion. The proposed two methods are easy to implement by taking advantage of existing smoothing and GAM softwares for independent data. The usefulness of the methodology is demonstrated through application to a correlated binary data set drawn from a clinical trial, the Lung Health Study.

Adult↗

PubMed2001

Residual mass histology in testicular cancer: development and validation of a clinical prediction rule.

After chemotherapy for metastatic non-seminomatous testicular cancer, surgical resection is a generally accepted treatment to remove remnants of the initial metastases, since residual tumour may still be present (mature teratoma or viable cancer cells). In this paper, we review the development and external validation of a logistic regression model to predict the absence of residual tumour. Three sources of information were used. A quantitative review identified six relevant predictors from 19 published studies (996 resections). Second, a development data set included individual data of 544 patients from six centres. This data set was used to assess the predictive relationships of five continuous predictors, which resulted in dichotomization for two, and a log, square root, and linear transformation for three other predictors. The multiple logistic regression coefficients were reduced with a shrinkage factor (0.95) to improve calibration, based on a bootstrapping procedure. Third, a validation data set included 172 more recently treated patients. The model showed adequate calibration and good discrimination in the development and in the validation sample (areas under the ROC curve 0.83 and 0.82). This study illustrates that a careful modelling strategy may result in an adequate predictive model. Further study of model validity may stimulate application in clinical practice.

Biomarkers, Tumor↗

PubMed2002

Evaluating inter-hospital variability in mortality rates over time, allowing for time-varying effects.

In outcome studies, quality of care in various institutions is typically assessed by comparing observed to expected outcome rates, after adjusting for patients' case-mix factors in logistic regression models. However, differences in patterns of outcome rates over time, especially when there is a distinction between the determinants affecting early and later events, are rarely studied. We use six-month mortality after coronary artery bypass graft operation (CABG) as an example. We present a statistically valid approach to estimate expected survival curves for different subgroups, based on a Cox survival model with time-varying effects. Bootstrap confidence intervals around the expected survival curves are constructed. This approach is applied for examining the pattern of deviation of high-mortality hospitals after CABG. Implications for quality assessment in comparative outcome studies are discussed.

Aged↗

PubMed1991

Statistical methods for analyzing developmental toxicity data.

A description and review of methods for performing per-litter analyses involving extrabinomial proportion response is provided. It is stressed that the litter should be regarded as the appropriate experimental unit for quantitative analysis in studies for teratogenic or heritable mutagenic effects. Attention is directed at statistical identification of possible treatment effects, such as a positive dose response to a chemical stimulus. The methods range from distribution-free, nonparametric analyses to models involving parametric distributions such as the beta-binomial density. It is seen that most current methods require computer implementation. When concern is raised over misspecification of assumptions critical to the statistical analysis, it is argued that relatively parameter-free methods are appropriate for use. These include statistical bootstrapping and rank-based analyses.

Models, Statistical↗

PubMed2001

An investigation of bisphosphonate inhibition of a vacuolar proton-pumping pyrophosphatase.

We report the results of a three-dimensional quantitative structure-activity relationship (3D-QSAR)/comparative molecular field analysis (CoMFA) of the activity of 18 bisphosphonates and imidodiphosphate in the inhibition of a mung bean (Vigna radiata L.) vacuolar proton pumping pyrophosphatase (V/H(+)-PPase; EC 3.6.1.1). We find an experimental versus QSAR predicted pK(app)(i) R(2) value of 0.89, a cross-validated R(2) = 0.77, and a bootstrapped R(2) = 0.89 for 18 bisphosphonates plus imidodiphosphate over the 1.3 microM to 425 microM range of K(app)(i) values. We also demonstrate that this approach has predictive utility (a 0.26 pK(app)(i) rms error for three test sets of 3 activity predictions each), corresponding to about a factor of two error in K(app)(i) prediction. The 3D-QSAR/CoMFA approach provides a quantitative method for predicting the activity of V/H(+)-PPase inhibitors and is likely to be of use in the design of novel pharmacological agents since all of the major human disease-causing parasitic protozoa contain large levels of pyrophosphate, together with V-type proton-pumping pyrophosphatases located in plant-like vacuoles (acidocalcisomes), which are absent in their mammalian hosts.

Diphosphonates↗

PubMed1998

Cognitive and Metacognitive Abilities Involved in the Solution of Mathematical Word Problems: Validation of a Comprehensive Model.

With this investigation we tried to validate an economic model of the cognitive and metacognitive abilities involved in Mathematical Word Problems. From the literature we chose seven abilities: text comprehension, problem representation, problem categorization, solution estimate, planning the solution, procedure self-evaluation, calculus self-evaluation. In order to measure these abilities, we devised a series of mathematical word problems (partitioned problem) where, for each ability, subjects have to answer a multiple choice question. A hierarchical regression model with only five variables (excluding solution estimate and calculus self-evaluation) explained more than 50% of the variance of the solution scores of the Partitioned Problems, and 40% of the variance of the solution of a series of problems presented with only the text. The model was validated with five different samples of subjects of different school grade and with a bootstrap procedure. Furthermore the relationship of the variables was tested using a path analysis. The discrimination validity of three different levels of problem solving efficiency give further support to the validity of the model. The model obtained may be utilized in order to devise practical instruments for the analysis of mathematical word problem difficulties. Copyright 1998 Academic Press.

Journal Article↗

PubMed1995

Applicability of CoMFA in ecotoxicology: a critical study on chlorophenols.

Comparative molecular field analysis (CoMFA) is used to relate ecotoxicological data with steric and electrostatic fields of chemicals forming an intentionally selected homogeneous set, the chlorophenols, for which reliable data are abundant in literature. Among these data, those concerning 16 different biological systems were selected, leading to predictive CoMFA QSAR in 14 of the cases. This is attested by cross-validation and bootstrapping, which also authorize the prediction of the chlorophenols toxicity values, when they are missing. The quality of obtained CoMFA models and the applicability of the method are discussed. The results are very promising, and they encourage further investigation into CoMFA in ecotoxicology.

Animals↗

PubMed1998

Molecular phylogenetic, morphological, and mycotoxin data support reidentification of the Quorn mycoprotein fungus as Fusarium venenatum.

Molecular phylogenetic, morphological, and mycotoxin data were obtained in order to investigate the relationships and identity of the Quorn mycoprotein fungus within Fusarium and to examine Quorn strains and commercial Quorn food products for trichothecene mycotoxins. Phylogenetic analyses of aligned DNA sequences obtained via the polymerase chain reaction from the nuclear 28S ribosomal DNA, nuclear ribosomal internal transcribed spacer region, and beta-tubulin gene exons and introns indicate that the Quorn fungus is Fusarium venenatum, rather than F. graminearum as previously reported. All of the Quorn strains examined were morphologically degenerate aconidial colonial mutants except for NRRL 25139, which produced chlamydospores in recurved terminal chains together with mostly 5-septate sporodochial conidia on doliform monophialides diagnostic of F. venenatum. Bootstrap and decay analyses provide strong support for a monophyletic lineage containing F. venenatum and several other type A trichothecene-producing species, while reference strains of F. graminearum were nested in a separate clade of species that produce type B trichothecenes and/or zearalenone. Analysis of mycotoxins from rice cultures inoculated with Quorn strain NRRL 25416 revealed that four type A trichothecenes are produced, but at low levels relative to strain NRRL 22198 of F. venenatum. No trichothecene mycotoxins, however, were detected from the analysis of three commercial Quorn products marketed for human consumption in England.

DNA, Fungal↗

PubMed1998

Phylogeny of the genus trichoderma based on sequence analysis of the internal transcribed spacer region 1 of the rDNA cluster

Sequences of the internal transcribed spacer region 1 (ITS1) of the ribosomal DNA were used to determine the phylogenetic relationships of species of Trichoderma sect. Pachybasium. To this end, 85 strains-including all the available ex-type strains-were analyzed. Parsimony analysis demonstrated that the section is nonmonophyletic, distributing the 85 strains among three main groups that were supported by bootstrap values. Group A comprises two clades (A1 and A2), with A1 including T. polysporum, T. piluliferum, and T. minutisporum, while A2 included T. hamatum, T. pubescens, and T. strigosum in addition to species previously included in sect. Trichoderma (i.e., T. viride, T. atroviride, and T. koningii). The ex-type strain of T. fasciculatum formed a separate branch basal to clade A. Clade B contained the sect. Pachybasium members T. harzianum, T. fertile, T. croceum, T. longipile, T. strictipile, T. tomentosum, T. oblongisporum, T. flavofuscum, T. spirale, and the anamorphs of Hypocrea semiorbis and H. cf. gelatinosa. Sequence differences among clades A1, A2, and B were in the same order of magnitude as between each of them and T. longibrachiatum, which was used as an outgroup in these analyses. Sequence differences within clades A1, A2, and B were considerably smaller: in some cases (i.e., T. virens and T. flavofuscum; T. strictipile and H. cf. gelatinosa), the ITS1-sequences were identical, suggesting conspecifity. In other cases (e.g., T. crassum and T. longipile; T. harzianum, T. inhamatum, T. croceum, T. fertile, and H. semiorbis; T. hamatum and T. pubescens; and T. viride, T. atroviride, and T. koningii) differences were in the range of 1-3 nt only, suggesting a very close phylogenetic relationship. The sequence of a previously described aggressive mushroom competitor group of T. harzianum strains (Th2) was strikingly different from that of the ex-type strain of T. harzianum and closely related species and is likely to be a separate species. Copyright 1998 Academic Press.

Journal Article↗