Biomedical subjects

Craig B Borkowf

Publications and source records attributed to Craig B Borkowf.

7 recordsLinked to original sources

PubMed2006

Constructing binomial confidence intervals with near nominal coverage by adding a single imaginary failure or success.

In this paper we present a simple method for constructing (1- alpha)100 per cent confidence intervals for binomial proportions with near nominal coverage for all underlying proportion parameters on the unit interval. This new method uses, with a slight modification, the standard normal approximation technique taught in introductory statistics classes. Specifically, we first augment the observed binomial data with an imaginary failure to compute the lower bound and an imaginary success to compute the upper bound. By contrast, the Agresti-Coull method adds the same number of imaginary successes and failures to the observed data, yet it can still give somewhat subnominal coverage. As motivation, we discuss the relationship between this new method and the Clopper-Pearson exact method. We also present numerical calculations to illustrate the satisfactory performance of this new method compared with several common alternatives. Finally, we argue that for certain statistical applications, such as the design and analysis of clinical trials with adverse events, this new method represents a valuable complementary approach.

Biometry↗

PubMed2005

A simple hybrid variance estimator for the Kaplan-Meier survival function.

In this paper, we propose a hybrid variance estimator for the Kaplan-Meier survival function. This new estimator approximates the true variance by a Binomial variance formula, where the proportion parameter is a piecewise non-increasing function of the Kaplan-Meier survival function and its upper bound, as described below. Also, the effective sample size equals the number of subjects not censored prior to that time. In addition, we consider an adjusted hybrid variance estimator that modifies the regular estimator for small sample sizes. We present a simulation study to compare the performance of the regular and adjusted hybrid variance estimators to the Greenwood and Peto variance estimators for small sample sizes. We show that on average these hybrid variance estimators give closer variance estimates to the true values than the traditional variance estimators, and hence confidence intervals constructed with these hybrid variance estimators have more nominal coverage rates. Indeed, the Greenwood and Peto variance estimators can substantially underestimate the true variance in the left and right tails of the survival distribution, even with moderately censored data. Finally, we illustrate the use of these hybrid and traditional variance estimators on a data set from a leukaemia clinical trial.

Analysis of Variance↗

PubMed2005

Efficient estimation of the risk of a disease by quantile-categories of a key predictor variable using generalized additive models.

Suppose that one wishes to make inference to the risk of a disease by the population quartile-categories of a key continuous predictor variable. When one collects data on a prospective cohort, the standard method is simply to categorize the key predictor variable by the empirical quartiles. One may then include indicator variables for these empirical quartile-categories as predictors, along with other covariates, in a generalized linear model (GLM), with the observed health status of each subject as the response. The standard GLM method, however, is relatively inefficient, because it treats all observations that fall in the same quartile-category of the predictor variable identically, regardless of whether they lie in the centre or near the boundaries of that category. Alternatively, one may include the key predictor variable, along with other covariates, in a generalized additive model (GAM), again with the observed health status of each subject as the response. The alternative GAM method non-parametrically estimates the functional relationship between the key predictor variable and the response. One may then compute statistics of interest, such as proportions and odds ratios, from the fitted GAM equation using the empirical quartile-categories. Simulations show that both the GLM and GAM methods are nearly unbiased, but the latter method produces smaller variances and narrower bootstrap confidence intervals. An example from nutritional epidemiology illustrates the use of these methods.

Adult↗

PubMed2004

Carotenoids, vitamin A and risk of adenomatous polyp recurrence in the polyp prevention trial.

One trial reported beta-carotene supplementation was protective of adenomatous polyp recurrence in nonsmokers. We now examine the relation of serum and dietary carotenoids and vitamin A to adenomatous polyp recurrence in a subcohort of 834 participants in a low fat, high fiber, high fruit and vegetable dietary intervention, the Polyp Prevention Trial. Multivariate odds ratio (OR) and 95% confidence intervals (CI) of polyp recurrence were obtained using baseline or the average (first 3 years of the trial) carotenoid and vitamin A values after adjustment for covariates. Compared to the lowest quartile of baseline alpha-carotene concentrations, the OR of multiple polyp recurrence for the highest quartile was 0.55 (95% CI = 0.30-0.99) and the OR of right-sided recurrence was 0.60 (95% CI = 0.37-0.95). Baseline dietary intakes of alpha-carotene and vitamin A from food with/without supplements were inversely associated with any recurrence (p for linear trend = 0.03-alpha-carotene; p = 0.004 and p = 0.007 -intakes of vitamin A). Compared to the lowest quartile of averaged beta-carotene concentrations, the OR of multiple adenomas for the highest quartile was 0.40 (95% CI = 0.22-0.75) with an inverse trend (p = 0.02). The risk was inversely related to averaged: alpha-carotene concentrations and right-sided polyps; alpha-carotene intake and recurrence of any, multiple and right-sided polyps; beta-carotene intake and multiple adenoma recurrence; vitamin A from food (with supplements) and each adverse endpoint. Thus, alpha-carotene and vitamin A may protect against recurrence in nonsmokers and nondrinkers or be indicative of compliance or another healthy lifestyle factor that reduces risk.

Adenomatous Polyps↗

PubMed2003

Phase II trial of thalidomide and carmustine for patients with recurrent high-grade gliomas.

PURPOSE: The use of thalidomide as an antiangiogenic agent has met with only limited success in the treatment of malignant gliomas. On the basis of preclinical data demonstrating synergistic antitumor activity when antiangiogenic agents are combined with cytotoxic agents, we explored the clinical activity of the combination of thalidomide and carmustine (BCNU) in patients with recurrent high-grade gliomas. PATIENTS AND METHODS: Patients with a histologic diagnosis of high-grade glioma and radiographic evidence of tumor progression after standard surgery, radiation, and chemotherapy were eligible for the study. Patients received BCNU 200 mg/m2 on day 1 of every 6-week cycle, and 800 mg/d of thalidomide that was escalated to a maximal dose of 1,200 mg/d as tolerated. RESULTS: A total of 40 patients (38 with glioblastomas, two with anaplastic gliomas) were accrued to the study. The combination of thalidomide and BCNU was well tolerated; mild myelosuppression and mild to moderate sedation were the most common side effects. The median progression-free survival (100 days) and the objective radiographic response rate (24%) for patients with glioblastoma compared favorably with data from historical controls. CONCLUSION: This is one of the first clinical trials to evaluate the strategy of combining a putative antiangiogenic agent with a cytotoxic agent in patients with primary brain tumors. Our data demonstrate that thalidomide in combination with BCNU is well tolerated and has antitumor activity in patients with recurrent high-grade gliomas. Although the combination seems to be more active than either agent alone, such conclusions await confirmatory trials.

Adult↗

PubMed2003

Using lowess to remove systematic trends over time in predictor variables prior to logistic regression with quantile categories.

In case-control studies one may employ logistic regression to model the relationship between binary responses and continuous predictor variables that have been categorized by the empirical quartiles of the controls. Sometimes, however, systematic trends over time (or drifts) contaminate the laboratory measurements of predictor variables. In this paper we consider the use of locally weighted robust regression (lowess) to estimate and remove these systematic trends when the trends for the cases and controls have a common shape. One can then use the lowess adjusted data in the desired logistic regression model. We illustrate these methods with a case-control study that was designed to assess the risk of oesophageal cancer as a function of the quartile categories of sphinganine levels in the blood serum. Upon examination of the data, it was discovered that the sphinganine laboratory measurements were contaminated by a systematic trend, the magnitude of which depended only on the day of analysis. This trend needed to be removed before performing further analyses of the data. In addition, we present simulations to examine the use of lowess methods to estimate and remove various shapes of trends from contaminated predictor data before constructing logistic regression models with quartile categories. We found that using the trend-contaminated data tends to give attenuated parameter estimates and hence lower significance and power levels than using the uncontaminated data. Conversely, using appropriate lowess methods to adjust the data tends to give nearly unbiased parameter estimates, near nominal significance levels, and improved power.

Adult↗

PubMed2002

Autoantibodies associated with volatile anesthetic hepatitis found in the sera of a large cohort of pediatric anesthesiologists.

UNLABELLED: Anesthetic-induced hepatitis is thought to have an immune-mediated basis, in part because many patients who develop hepatitis have serum autoantibodies that react with specific hepatic proteins. The present study shows that pediatric anesthesiologists also have these serum autoantibodies. Moreover, levels of these autoantibodies are higher than those of general anesthesiologists. We collected sera from 105 pediatric and 53 general anesthesiologists (including 3 nurse anesthetists), 20 halothane hepatitis patients, and 20 control individuals who were never exposed to inhaled anesthetics. Serum cytochrome P450 2E1 (P450 2E1) and 58-kd hepatic endoplasmic reticulum protein (ERp58) autoantibodies were measured by enzyme-linked immunosorbent assays. Positive values were 2 SD above median control values. Two multiple regression models were constructed. Pediatric anesthesiologists, like halothane hepatitis patients, had higher serum autoantibody levels of ERp58 and P450 2E1 than general anesthesiologists and controls, which was possibly because of their increased occupational exposures to anesthetics. Female anesthesiologists had higher levels of ERp58 autoantibodies than male anesthesiologists, whereas female pediatric anesthesiologists had higher levels of P450 2E1 autoantibodies than all other anesthesiologists. One female pediatric anesthesiologist had symptoms of hepatic injury. Because most anesthesiologists do not develop volatile anesthetic-induced hepatic injury, the findings suggest that pathogenic ERp58 and P450 2E1 autoantibodies may not directly cause volatile anesthetic hepatitis. Female anesthesiologists have high levels of these autoantibodies; however, the majority of these individuals do not develop hepatitis, suggesting that autoantibodies may not have a pathological role in volatile anesthetic-induced hepatitis. IMPLICATIONS: Environmental exposure of anesthesiology personnel to certain inhaled anesthetics can induce the formation of autoantibodies that have been associated with anesthetic hepatitis. Female anesthesiologists have high levels of these autoantibodies; however, the majority of these individuals do not develop hepatitis, suggesting that autoantibodies may not have a pathological role in volatile anesthetic-induced hepatitis.

Adult↗