A case for Bayesianism in clinical trials

This paper describes a Bayesian approach to the design and analysis of clinical trials, and compares it with the frequentist approach. Both approaches address learning under uncertainty. But they are different in a variety of ways. The Bayesian approach is more flexible. For example, accumulating data from a clinical trial can be used to update Bayesian measures, independent of the design of the trial. Frequentist measures are tied to the design, and interim analyses must be planned for frequentist measures to have meaning. Its flexibility makes the Bayesian approach ideal for analysing data from clinical trials. In carrying out a Bayesian analysis for inferring treatment effect, information from the clinical trial and other sources can be combined and used explicitly in drawing conclusions. Bayesians and frequentists address making decisions very differently. For example, when choosing or modifying the design of a clinical trial, Bayesians use all available information, including that which comes from the trial itself. The ability to calculate predictive probabilities for future observations is a distinct advantage of the Bayesian approach to designing clinical trials and other decisions. An important difference between Bayesian and frequentist thinking is the role of randomization.     

Pigeons prefer conditional stimuli over their absence: A comment on Roberts et al. (2009).

Recently, Roberts et al. (2009) have suggested that pigeons performing delayed matching-to-sample appear unwilling to request to see the sample again (or even for the first time) prior to choice, even if that choice would result in an increase in matching accuracy. In each of their four experiments, however, presentation (Experiments 3 & 4) or representation of the sample (Experiments 1 & 2) resulted in an added delay to reinforcement. Thus, the pigeons had to choose between an immediate reinforcer on about 50% of the trials and a delayed reinforcer on a significantly higher percentage of the trials. In the present research, when we equated the two alternatives for delay to reinforcement, we found that pigeons generally showed a significant preference for trials with a relevant sample over trials with an irrelevant sample. When the contingencies were reversed, most of the pigeons reversed their preference. Although these results do not present evidence for metacognition, they do show that pigeons are sensitive to the potential for a higher probability of reinforcement when delay to reinforcement is controlled. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Clinical trials of antibacterial agents: a practical guide to design and analysis. Statisticians in the Pharmaceutical Industry Working Party

Guidelines on the conduct of clinical trials of antibacterial agents produced by the US Food and Drug Administration, the British Society for Antimicrobial Chemotherapy, the Infectious Diseases Society of America and a European Working Party have been reviewed. Although very informative, these guidelines provide limited practical guidance on the design and statistical aspects of phase III studies of antimicrobial agents. This paper describes the differences between antibacterial trials and clinical studies in other therapeutic areas with regard to subjective endpoints, dual clinical and bacteriological endpoints, frequent protocol violations and difficulty of using placebo controls. The importance of a detailed protocol and planned analysis strategy is emphasized. The choice of comparator agents, practical issues with the blinding of trial materials and the documentation of patients excluded from study entry are discussed. The use of different patient groups and different endpoints in analyses are described. The principles of equivalence and their application to trials of antibacterial agents are discussed, together with an approach to calculating sample size. A variety of statistical analyses of results are compared for different situations indicating some of the problems that can arise. Different methods of presentation of study data are included with emphasis on regulatory submissions rather than scientific publications. Some graphical presentations are recommended and issues regarding data across different studies are discussed.     

Position of the egocentric reference and directional arm movements in right-brain-damaged patients

An increasing number of economic evaluations are being conducted alongside clinical trials. While this practice offers the prospect of collecting comprehensive and accurate cost data, it requires considerable time and effort. In the case of clinical data, key analytic decisions such as which data to collect and sample size are often made with reference to smaller (pilot) trials. However, this approach is not normally followed in the case of economic evaluation. This study was based on a recently completed health technology assessment comparing conventional radiotherapy with continuous hyperfractionated accelerated radiotherapy (CHART) for patients with head and neck cancer or carcinoma of the bronchus. In the full health technology assessment, cost data were available for 526 head and neck patients (314 CHART and 212 conventional therapy) and 286 bronchus patients (175 CHART and 109 conventional therapy). In order to simulate a pilot study, data were extracted for the patients recruited to both trials in the first 3 months. These were then compared with the full data set in order to assess whether such a pilot study would have given useful guidance on: a) the usefulness of undertaking a full study; b) the sample size required; and c) the important resource items for which comprehensive data collection would be required. Pilot studies can be helpful in determining the likely advantages of undertaking full economic evaluations and in identifying important resource items. Therefore, it is important that clinical researchers and research funding bodies create the necessary time window to enable such studies to take place. However, formal sample size calculations are more difficult to perform on limited data, since they also require knowledge of the unit cost (or prices) to be attached to the resource items and the correlation between costs and clinical effects.     

Carotid endarterectomy

Carotid endarterectomy has been a controversial matter since its introduction more than 40 years ago. In the last decade several clinical trials were performed to determine the efficacy of this operation in patients with carotid estenosis and hemispheric or ocular ischemic symptoms. In 1991 the interim results of the North American Symptomatic Carotid Endarterectomy Trial and the European Carotid Surgery Trial were reported, both trials demonstrating the beneficial effects of surgery in symptomatic patients with stenosis of greater than 70%. In 1994 the Asymptomatic Carotid Atherosclerosis Study reported their interim results in patients who have stenosis of greater than 60% in favor of endarterectomy, in centers with documented perioperative mortality and morbidity of less than 3%. The Asymptomatic Carotid Surgery Trial is still in progress. All this trials have restored the confidence on carotid endarterectomy.     

Inferior temporal mechanisms for invariant object recognition

The specific size and retinal location of an object are readily perceived, yet recognition of an object's identity is hardly affected by transformations of its size or location. To explore how such stimulus transformations are treated by known mechanisms for visual short-term memory in inferior temporal (IT) cortex, IT cells were recorded in monkeys performing a delayed matching-to-sample task. The stimuli were pictures of complex objects, and the monkeys ignored differences in size and retinal location when matching the test items to the sample held in memory. The sensory information communicated by cells was assessed in their responses to the sample stimuli, and mnemonic information was assessed in their responses to the test stimuli. In the sensory domain, the ordering of relative stimulus preferences for nearly all cells was invariant over changes in size or location; however, some cells nonetheless preferred stimuli of a given size or location. In the mnemonic domain, the responses of many cells were modulated according to whether the test stimulus matched the sample held in memory, and these memory effects were invariant over the relative sizes and locations of the stimuli. Thus, IT neuronal populations may mediate not only the recognition and memory of object identity, which are invariant over size and location, but also the perception of the transformations themselves.     

Bioethics for clinicians: 16. Dealing with demands for inappropriate treatment

Demands by Patients or their Families for treatment thought to be inappropriate by health care providers constitute an important set of moral problems in clinical practice. A variety of approaches to such cases have been described in the literature, including medical futility, standard of care and negotiation. Medical futility fails because it confounds morally distinct cases: demand for an ineffective treatment and demand for an effective treatment that supports a controversial end (e.g., permanent unconsciousness). Medical futility is not necessary in the first case and is harmful in the second. Ineffective treatment falls outside the standard of care, and thus health care workers have no obligation to provide it. Demands for treatment that supports controversial ends are difficult cases best addressed through open communication, negotiation and the use of conflict-resolution techniques. Institutions should ensure that fair and unambiguous procedures for dealing with such cases are laid out in policy statements.     

Population structure in Daphnia obtusa: quantitative genetic and allozymic variation

Quantitative genetic analyses for body size and for life history characters within and among populations of Daphnia obtusa reveal substantial genetic variance at both hierarchical levels for all traits measured. Simultaneous allozymic analysis on the same population samples indicate a moderate degree of differentiation: GST = 0.28. No associations between electrophoretic genotype and phenotypic characters were found, providing support for the null hypothesis that the allozymic variants are effectively neutral. Therefore, GST can be used as the null hypothesis that neutral phenotypic evolution within populations led to the observed differentiation for the quantitative traits, which I call QST. The results of this study provide evidence that natural selection has promoted diversification for body size among populations, and has impeded diversification for relative fitness. Analyses of population differentiation for clutch size, age at reproduction, and growth rate indicate that neutral phenotypic evolution cannot be excluded as the cause.     

Infection by Inermicapsifer madagascariensis (Davaine, 1870); Baer, 1956. A report of 2 cases]

OBJECTIVE: To study the relationship between glutathione S-transferase mu (GST mu) gene deletion and senile cataract (SC) susceptibility. METHOD: Polymerase chain reaction (PCR) method was used to investigate the rates of GST mu gene deletion in 59 cases with SC and 112 healthy controls. RESULTS: The rate of GST mu gene deletion in cases with SC was 69.5% which was significantly higher than that of the controls, 50.9% (P < 0.05). An analysis stratified by smoking and nonsmoking showed that GST mu gene deletion rate in smoking subjects with SC was higher. Because of the small sample size of this study, although the rate of GST mu gene deletion in smoking subjects with SC has reached 72.4%, that is not significantly different from that of the controls statistically (P > 0.05). CONCLUSION: SC correlates with GST mu gene deletion and GST mu gene deletion is one of the hereditary factors for susceptibility to SC.     

Sample size and power

This paper sets forth the basic concepts of the calculation of sample size and power in clinical research. It provides the reader with a basic understanding of the relationship between sample size and power and the components within the research, such as the variability of the measure being used as the primary outcome. The paper also discusses a number of general issues related to sample size and power, such as the importance of the difference between clinical and statistical significance, how one approaches trials attempting to establish the equivalence of clinical interventions, and the critical need for appropriate consultation.     

The role of the data manager in clinical cancer research. An opportunity for nurses

A clinical trial is a research study conducted in humans and designed to answer specific questions using scientifically controlled methods. These trials require considerable effort to assure that the data obtained are reliable, reproducible, and readily available. Data managers play a key role in this research effort. A nurse with a clinical background, computer knowledge, and some experience in the research environment is well suited for the role of data manager. The data manager performs a variety of tasks in this position that will enhance the quality of the data gathered in a research study. These responsibilities include designing forms, monitoring protocol accrual, abstracting data, entering data onto protocol-specific forms and/or specifically designed computerized data-entry screens, assuring the quality and the integrity of the data, and providing investigators with interim and summary reports. In addition, the data manager can be responsible for the management of a computerized clinical data base system, including the training of users and the designing of basic reports for the investigators. A nurse, functioning as a data manager, who understands research methodology, is detail oriented, and is well organized, could be a valuable asset to the clinical trials team in the successful management of any clinical study.     

Data monitoring committees: the moral case for maximum feasible independence

Since data monitoring committees (DMCs) began to be established in the 1970s, they have reviewed the clinical outcome data emerging from ongoing trials. The thesis of this essay is that DMCs most effectively promote the validity and credibility of randomized clinical trials when they perform this function with the maximum feasible independence. The essay argues that four types of individuals and groups should be excluded from the interim monitoring of outcome data: (1) investigators entering patients into a trial; (2) principal investigators or study chairs; (3) representatives of commercial firms connected with a trial; and (4) representatives of regulatory agencies. The role of statistical groups and officials of government funding agencies in the review of outcome data is also discussed.     

Sample size determination in complex clinical trials comparing more than two groups for survival endpoints

This paper presents a sample size formula for testing the equality of kappa (> or = 2) survival distributions using the Tarone-Ware class of test statistics in the presence of non-proportional hazards, time dependent losses, non-compliance and drop-in. This method extends the derivation by Lakatos of a sample size formula for comparing two survival distributions. A sample size formula is also presented for the stratified logrank test. We describe how one can utilize these generalized formulae in calculating sample sizes and assessing power in complex multi-arm clinical trials.     

A multiple decision procedure in clinical trials

In some multiple treatment arm clinical trials there is an order of preference for the treatments based on secondary considerations like toxicity or cost. In this paper, we consider the case where two or more treatments could have equal prior preference. This formulation includes the problem of comparing several equally preferred experimental treatments to one control, or the comparison of a combination with its components. Our decision procedures will guarantee a high selection probability for the correct treatment(s) when that selection is appropriate. We establish sample size requirements for our decision procedures which can be applied to clinical trials with normal, binomial, or right censored exponential endpoints.     

Why are missing quality of life data a problem in clinical trials of cancer therapy?

Assessment of health related quality of life has become an important endpoint in many cancer clinical trials. Because the participants of these trials often experience disease and treatment related morbidity and mortality, non-random missing assessments are inevitable. Examples are presented from several such trials that illustrate the impact of missing data on the analysis of QOL in these trials. The sensitivity of different analyses depends on the proportion of assessments that are missing and the strength of the association of the underlying reasons for missing data with disease and treatment related morbidity and mortality. In the setting of clinical trials of cancer therapy, the assumption that the data are missing completely at random (MCAR) and analyses of complete cases is usually unjustified. Further, the assumption of missing at random (MAR) may also be violated in many trials and models appropriate for non-ignorable missing data should be explored. Recommendations are presented to minimize missing data, to obtain useful documentation concerning the reasons for missing data and to perform sensitivity analyses.     

Practical Bayesian guidelines for phase IIB clinical trials

A Phase IIB clinical trial typically is a single-arm study aimed at deciding whether a new treatment E is sufficiently promising, relative to a standard therapy, S, to include in a large-scale randomized trial. Thus, Phase IIB trials are inherently comparative even though a standard therapy arm usually is not included. Uncertainty regarding the response rate theta s of S is rarely made explicit, either in planning the trial or interpreting its results. We propose practical Bayesian guidelines for deciding whether E is promising relative to S in settings where patient response is binary and the data are monitored continuously. The design requires specification of an informative prior for theta s, a targeted improvement for E, and bounds on the allowed sample size. No explicit specification of a loss function is required. Sampling continues until E is shown to be either promising or not promising relative to S with high posterior probability, or the maximum sample size is reached. The design provides decision boundaries, a probability distribution for the sample size at termination, and operating characteristics under fixed response probabilities with E.     

Intrusion of teeth in the combination implant-to-natural-tooth fixed partial denture: a review of the theories

Experimental designs in clinical investigation are discussed in this article. Guideline examples have been used in the area of Cardiology using always the same one only one whenever possible. We have looked for a different perspective from what is generally used in the discussion of the general characteristics of experimental designs, and more specifically of clinical trials and we deal with the aspects of clinical trials which are usually ignored due to their marginal character. We also discuss those characteristics which differentiate clinical trials in respect to other designs and types of questions which are answered by clinical trials. And we finally discuss various aspects such as randomization and its various types (simple, block, stratified, pre-randomized) and variable types of evaluating the answers, masking and the problems in its maintenance, with certain kinds of designs, sample size, etc. There is a brief mention of two particular cases: factorial and cross over designs are both discussed, mentioning their strong and weak points. Likewise, we discuss community trials as another experimental design and examples are provided. Finally, we discuss aspects of criteria: such as, When to stop the trials? or Who are the results applicable to?, and we suggest points to take into consideration when these decisions are made.     

An investment appraisal approach to clinical trial design

In this paper, a general investment appraisal model is presented which shows how pharmaceutical companies could take profit considerations into account when making decisions about the design of randomized controlled trials. A general model is presented based on the net present value method of investment appraisal. The approach is illustrated with a hypothetical example which shows how optimal (net present value maximizing) designs can be determined based on choices about sample size and endpoint measurement. The method could be extended to accommodate considerations about other trial design features, and could be used to determine a portfolio of studies which maximizes the expected return on a given development or trial budget. Furthermore, the approach could be used by pharmaceutical companies to evaluate the incremental costs and benefits of incorporating non-clinical objectives into trials, such as quality of life research and economic evaluation studies. A number of practical difficulties would need to be overcome to utilize the approach. Directions for further research are therefore highlighted centred on the key components of the model: a trial cost function, a product demand function, innovation diffusion processes and Bayesian approaches to trial design.     

Power and sample size calculations for studies involving linear regression

This article presents methods for sample size and power calculations for studies involving linear regression. These approaches are applicable to clinical trials designed to detect a regression slope of a given magnitude or to studies that test whether the slopes or intercepts of two independent regression lines differ by a given amount. The investigator may either specify the values of the independent (x) variable(s) of the regression line(s) or determine them observationally when the study is performed. In the latter case, the investigator must estimate the standard deviation(s) of the independent variable(s). This study gives examples using this method for both experimental and observational study designs. Cohen's method of power calculations for multiple linear regression models is also discussed and contrasted with the methods of this study. We have posted a computer program to perform these and other sample size calculations on the Internet (see http://www.mc.vanderbilt.edu/prevmed/psintro+ ++.htm). This program can determine the sample size needed to detect a specified alternative hypothesis with the required power, the power with which a specific alternative hypothesis can be detected with a given sample size, or the specific alternative hypotheses that can be detected with a given power and sample size. Context-specific help messages available on request make the use of this software largely self-explanatory.     

Evidence that pigeons represent Euclidean properties of space.

In the delayed matching of key location paradigm, pigeons' memory for spatial location is assessed by briefly illuminating one key of a square-shaped three-by-three matrix of pecking keys as the sample and then, after a retention interval, by illuminating all nine keys. A subject's choice of the sample, but not the distractor keys, was rewarded. With short retention intervals, pigeons correctly chose the sample on a high proportion of trials; however, errors were sometimes made. In the present research these errors were analyzed with multidimensional scaling and correlational techniques in order to make inferences about the structure of the pigeons' representation of the key matrix. The results of both analyses suggest that pigeons encode space in a Euclidean manner (i.e., for the pigeon the psychological distance between locations corresponds to Euclidean geometry distance). (PsycINFO Database Record (c) 2010 APA, all rights reserved)