Predictive probability in clinical trials

In a recent paper, Choi and Pepple (1989, Biometrics 45, 317-323) consider the use of predictive probabilities in the monitoring of clinical trials. In particular, they characterise the predictive probability as a "useful conservative measure" for monitoring purposes. In this note the nature and source of this "conservatism" are investigated.     

Predictive probability early termination plans for phase II clinical trials

A phase II clinical trial is designed to gather data to help decide whether an experimental treatment has sufficient effectiveness to justify further study. In a one-arm trial with dichotomous outcome, we wish to test a simple null hypothesis on the Bernoulli parameter against a one-sided alternative in a sample of N patients. It is advisable to have a rule to terminate the trial early when evidence accumulates that the treatment is ineffective. Predictive probabilities based on the binomial distribution and beta and uniform prior distributions for the binomial parameter are found to be useful as the basis of group sequential designs. Size, power and average sample size for these designs are discussed. A process for the specification of an early termination plan, advice on the quantification of prior beliefs, and illustrative examples are included.     

Confidence limits for probability of response in multistage phase II clinical trials

Herson (1979, Biometrics 35, 775-783) has given a method for designing one-arm k-stage phase II clinical trials, which permits early termination of the trial if the treatment is apparently ineffective, while retaining acceptable levels of power and significance. This paper gives a method for calculating the confidence limits on the response proportion, conditional on a particular study design.     

Sample sizes based on the log-rank statistic in complex clinical trials

The log-rank test is frequently used to compare survival curves. While sample size estimation for comparison of binomial proportions has been adapted to typical clinical trial conditions such as noncompliance, lag time, and staggered entry, the estimation of sample size when the log-rank statistic is to be used has not been generalized to these types of clinical trial conditions. This paper presents a method of estimating sample sizes for the comparison of survival curves by the log-rank statistic in the presence of unrestricted rates of noncompliance, lag time, and so forth. The method applies to stratified trials in which the above conditions may vary across the different strata, and does not assume proportional hazards. Power and duration, as well as sample sizes, can be estimated. The method also produces estimates for binomial proportions and the Tarone-Ware class of statistics.     

A sample size adjustment procedure for clinical trials based on conditional power

When designing clinical trials, researchers often encounter the uncertainty in the treatment effect or variability assumptions. Hence the sample size calculation at the planning stage of a clinical trial may also be questionable. Adjustment of the sample size during the mid-course of a clinical trial has become a popular strategy lately. In this paper we propose a procedure for calculating additional sample size needed based on conditional power, and adjusting the final-stage critical value to protect the overall type-I error rate. Compared to other previous procedures, the proposed procedure uses the definition of the conditional type-I error directly without appealing to an extra special function for it. It has better flexibility in setting up interim decision rules and the final-stage test is a likelihood ratio test.     

Application of predictive biosimulation within pharmaceutical clinical development: examples of significance for translational medicine and clinical trial design

The challenge of accurately predicting human clinical outcome based on preclinical data has led to a high failure rate of compounds in human clinical trials. A series of methods are described by which biosimulation can address these challenges and guide the design and evaluation of experimental and clinical protocols. Early compound development often proceeds on the basis of preclinical data from animal models. The systematic evaluation possible in a simulation can assist in the critical step of translating the preclinical outcomes to human physiology. Later in the process, clinical trials definitively establish a therapy's beneficial effects, as well as any adverse side effects. Biosimulation allows for the optimal design of clinical trials to ensure that key issues are addressed effectively and efficiently, and in doing so, improves the success rate of the trials.     

Corn stover feedstock trials to support predictive modeling

To be sustainable, feedstock harvest must neither degrade soil, water, or air resources nor negatively impact productivity or subsequent crop yields. Simulation modeling will help guide the development of sustainable feedstock production practices, but not without field validation. This paper introduces field research being conducted in six states to support Sun Grant Regional Partnership modeling. Our objectives are to (1) provide a fundamental understanding of limiting factor(s) affecting corn (Zea mays L.) stover harvest, (2) develop tools (e.g., equations, models, etc.) that account for those factors, and (3) create a multivariant analysis framework to combine models for all limiting factors. Sun Grant modelers will use this information to improve regional estimates of feedstock availability. A minimum data set, including soil organic carbon (SOC), total N, pH, bulk density (BD), and soil‐test phosphorus (P), and potassium (K) concentrations, is being collected. Stover yield for three treatments (0%, 50%, and 90% removal) and concentrations of N, P, and K in the harvested stover are being quantified to assess the impact of stover harvest on soil resources. Grain yield at a moisture content of 155 g kg^?1 averaged 9.71 Mg ha^?1, matching the 2008 national average. Stover dry matter harvest rates ranged from 0 to 7 Mg ha^?1. Harvesting stover increased N–P–K removal by an average of 42, 5, and 45 kg ha^?1 compared with harvesting only grain. Replacing those three nutrients would cost $53.68 ha^?1 based on 2009 fertilizer prices. This first‐year data and that collected in subsequent years is being used to develop a residue management tool that will ultimately link multiple feedstock supplies together in a landscape vision to help develop a comprehensive carbon management plan, quantify corn stover harvest effects on soil quality, and predict regional variability in feedstock supplies.     

Designs for clinical trials with time-to-event outcomes based on stopping guidelines for lack of benefit

Background

We present the design, methods and population characteristics of a large community trial that assessed the efficacy of a weekly supplement containing vitamin A or beta-carotene, at recommended dietary levels, in reducing maternal mortality from early gestation through 12 weeks postpartum. We identify challenges faced and report solutions in implementing an intervention trial under low-resource, rural conditions, including the importance of population choice in promoting generalizability, maintaining rigorous data quality control to reduce inter- and intra- worker variation, and optimizing efficiencies in information and resources flow from and to the field.

Methods

This trial was a double-masked, cluster-randomized, dual intervention, placebo-controlled trial in a contiguous rural area of ~435 sq km with a population of ~650,000 in Gaibandha and Rangpur Districts of Northwestern Bangladesh. Approximately 120,000 married women of reproductive age underwent 5-weekly home surveillance, of whom ~60,000 were detected as pregnant, enrolled into the trial and gave birth to ~44,000 live-born infants. Upon enrollment, at ~ 9 weeks' gestation, pregnant women received a weekly oral supplement containing vitamin A (7000 ug retinol equivalents (RE)), beta-carotene (42 mg, or ~7000 ug RE) or a placebo through 12 weeks postpartum, according to prior randomized allocation of their cluster of residence. Systems described include enlistment and 5-weekly home surveillance for pregnancy based on menstrual history and urine testing, weekly supervised supplementation, periodic risk factor interviews, maternal and infant vital outcome monitoring, birth defect surveillance and clinical/biochemical substudies.

Results

The primary outcome was pregnancy-related mortality assessed for 3 months following parturition. Secondary outcomes included fetal loss due to miscarriage or stillbirth, infant mortality under three months of age, maternal obstetric and infectious morbidity, infant infectious morbidity, maternal and infant micronutrient status, fetal and infant growth and prematurity, external birth defects and postnatal infant growth to 3 months of age.

Conclusion

Aspects of study site selection and its "resonance" with national and rural qualities of Bangladesh, the trial's design, methods and allocation group comparability achieved by randomization, field procedures and innovative approaches to solving challenges in trial conduct are described and discussed. This trial is registered with http://Clinicaltrials.gov as protocol NCT00198822.     

Repeated significance tests for clinical trials with a fixed number of patients and variable follow-up

Group-sequential tests may be applied to trials in which the number of patients is fixed, a response variable is measured for each patient at successive follow-up visits, and the accumulated responses are compared across treatment groups. The standard theory is inapplicable because the increments in the accumulated responses are no longer independent. An adjustment can be made to allow for the ratio of between-patient to within-patient variance and for possible first-order autocorrelation. The method is illustrated by reference to a dental trial.