On the Power of Fisher's Combination Test for Two Stage Sampling in the Presence of Nuisance Parameters

C-REGS 2 - Design and methodology of a high-quality comparative effectiveness observational trial

The main aim of this study is to systematically record Cerebrolysin treatment modalities and concomitant medication, according to local standards, in patients with moderate to severe neurological deficits after acute ischemic stroke and to assess the impact of these parameters on therapy outcome during early rehabilitation (day 21) and on day 90. An open observational treatment design based on the principles of high-quality comparative effectiveness research (HQCER) has been chosen to capture the therapies as applied in real-world clinical practice. HQCER opens a new horizon for strengthening the validity of the results from observational trials, thereby enhancing the associated level of evidence. Rigorous pre-specification of analytical procedures and tight risk-based centralized monitoring were additional measures to improve the impact of the observational approach. The value for real-world studies has become obvious, and such studies based on comparative effectiveness designs supplement the classical study designs by enabling the inclusion of larger proband numbers and more statistical reliability for practical use.

Two-stage adaptive enrichment design for testing an active factor

We propose an adaptive enrichment approach to test an active factor, which is a factor whose effect is non-zero in at least one subpopulation. We implement a two-stage play-the-winner design where all subjects in the second stage are enrolled from the subpopulation that has the highest observed effect in the first stage. We recommend a weighted Fisher's combination of the most powerful test for each stage, respectively: the first stage Hotelling's test and the second stage noncentral chi-square test. The test is further extended to cover binary outcomes and time-to-event outcomes.

Interplay Between Amphetamine and Activity Level in Gene Networks of the Mouse Striatum

The psychostimulant amphetamine can be prescribed to ameliorate the symptoms of narcolepsy, attention-deficit hyperactivity disorder and to facilitate weight loss. This stimulant can also have negative effects including toxicity and addiction risk. The impact of amphetamine on gene networks is partially understood and this study addresses this gap in consideration of the physical activity. The striata of mice exposed to either amphetamine or saline treatment were compared in a mouse line selected for home cage physical overactivity, a phenotype that can be mitigated with amphetamine, and in a contemporary control line using RNA-seq. Genes presenting opposite expression patterns between treatments across lines included a pseudogene of coiled-coil-helix-coiled-coil-helix domain containing 2 gene (Chchd2), ribonuclease P RNA component H1 (Rpph1), short stature homeobox 2 (Shox2), transient receptor potential melastatin 6 (Trpm6), and tumor necrosis factor receptor superfamily, member 9 (Tnfrsf9). Genes presenting consistent treatment patterns across lines, albeit at different levels of significance included cholecystokinin (Cck), vasoactive intestinal polypeptide (Vip), arginine vasopressin (Avp), oxytocin/neurophysin (Oxt), thyrotropin releasing hormone (Trh), neurotensin (Nts), angiotensinogen (Agt), galanin (Gal), prolactin receptor (Prlr), and calcitonin receptor (Calcr). Potassium inwardly rectifying channel, subfamily J, member 6 (Kcnj6), and retinoic acid-related (RAR)-related orphan receptor alpha (Rora) were similarly differentially expressed between treatments across lines. Functional categories enriched among the genes presenting line-dependent amphetamine effect included genes coding for neuropeptides and associated with memory and neuroplasticity and synaptic signaling, energy, and redox processes. A line-dependent association between amphetamine exposure and the synaptic signaling genes neurogranin (Nrgn) and synaptic membrane exocytosis 1(Rims1) was highlighted in the gene networks. Our findings advance the understanding of molecular players and networks affected by amphetamine in support of the development of activity-targeted therapies that may capitalize on the benefits of this psychostimulant.

Effects of a systemic enzyme therapy in healthy active adults after exhaustive eccentric exercise: a randomised, two-stage, double-blinded, placebo-controlled trial

Background

Systemic enzyme therapy may improve symptoms of exhaustive eccentric exercise due to anti-inflammatory properties.

Methods

In a randomised, placebo-controlled, two-stage clinical trial, systemic enzyme therapy (Wobenzym) was administered for 72 hours before and 72 hours following a day on which subjects performed an exhaustive eccentric exercise (isokinetic loading of the quadriceps). Efficacy criteria (maximal strength and pain) and time points were selected to account for the multidimensional nature of exercise-induced muscle damage symptoms. Subjects were randomised in a crossover (stage I, n=28) and parallel group design (stage II, n=44).

Results

Analysis of stage I data demonstrated a significant superiority (Mann-Whitney=0.6153; p=0.0332; one sided) for systemic enzyme therapy compared with placebo. Stage II was designed as a randomised controlled parallel group comparison. Heterogeneity (I²>0.5) between stages led to separate analyses of stage I (endurance-trained subjects) and stage II (strength-trained subjects). Combined analysis resulted in no evidence for corresponding treatment effects. Analysis of pooled biomarker data, however, demonstrated significant favourable effects for systemic enzyme therapy in both stages.

Conclusion

Systemic enzyme therapy before and after exhaustive eccentric exercise resulted in higher maximal concentric strength in the less strength-trained subjects (stage I) and in significant favourable effects on biomarkers (inflammatory, metabolic and immune) in all subjects. The application of these findings needs further evaluation.

Cerebrolysin Asian Pacific trial in acute brain injury and neurorecovery: design and methods

Traumatic brain injury (TBI) is one of the leading causes of injury-related death. In the United States alone, an estimated 1.7 million people sustain a TBI each year, and approximately 5.3 million people live with a TBI-related disability. The direct medical costs and indirect costs such as lost productivity of TBIs totaled an estimated $76.5 billion in the U.S. in the year 2000. Improving the limited treatment options for this condition remains challenging. However, recent reports from interdisciplinary working groups (consisting primarily of neurologists, neurosurgeons, neuropsychologists, and biostatisticians) have stated that to improve TBI treatment, important methodological lessons from the past must be taken into account in future clinical research. An evaluation of the neuroprotection intervention studies conducted over the last 30 years has indicated that a limited understanding of the underlying biological concepts and methodological design flaws are the major reasons for the failure of pharmacological agents to demonstrate efficacy. Cerebrolysin is a parenterally-administered neuro-peptide preparation that acts in a manner similar to endogenous neurotrophic factors. Cerebrolysin has a favorable adverse effect profile, and several meta-analyses have suggested that Cerebrolysin is beneficial as a dementia treatment. CAPTAIN is a randomized, double-blind, placebo-controlled, multi-center, multinational trial of the effects of Cerebrolysin on neuroprotection and neurorecovery after TBI using a multidimensional ensemble of outcome scales. The CAPTAIN trial will be the first TBI trial with a 'true' multidimensional approach based on full outcome scales, while avoiding prior weaknesses, such as loss of information through "dichotomization," or unrealistic assumptions such as "normal distribution."

The statistical analysis of a clinical trial when a protocol amendment changed the inclusion criteria

BACKGROUND

Sometimes, protocol amendments that change the inclusion and exclusion criteria are required in clinical trials. Then, the patient populations before and after the amendment may differ.

METHODS

We propose to perform separate statistical tests for the different phases, i.e. for the patients recruited before and after the amendment, and to combine the tests using Fisher's combination test. After a significant combination test a multiple testing procedure can be applied to identify the phase(s) to which a proof of efficacy refers. We assume that the amendment(s) are not based on any type of unblinded data. The proposed method is investigated within a simulation study.

RESULTS

The proposed combination approach is superior to the 'naïve' strategy to ignore the differences between the phases and pooling the data to perform just one statistical test. This superiority disappears when there are hardly any differences between the two phases.

CONCLUSION

When one or more protocol amendments change the inclusion and exclusion criteria, one should realize that the populations may differ. In this case, separate tests for the different phases together with a combination test are a powerful method that can be applied in a variety of settings. The (first) amendment should specify the combination test to be applied in order to combine the different phases.

Estimation in flexible two stage designs

Adaptive test designs for clinical trials allow for a wide range of data driven design adaptations using all information gathered until an interim analysis. The basic principle is to use a test statistics which is invariant with respect to the design adaptations under the null hypothesis. This allows for a control of the type I error rate for the primary hypothesis even for adaptations not specified a priori in the study protocol. Estimation is usually another important part of a clinical trial, however, is more difficult in adaptive designs. In this research paper we give an overview of point and interval estimates for flexible designs and compare methods for typical sample size rules. We also make some proposals for confidence intervals which have nominal coverage probability also after an unforeseen design adaptation and which contain the maximum likelihood estimate and the usual unadjusted confidence interval.

The advantages and disadvantages of adaptive designs for clinical trials

Flexible designs for clinical trials permit mid-trial design modifications, which are based on interim information from inside or outside the trial while meeting (regulatory) requirements for the control of the type I error rate. The basic principle is to combine stage standardized test statistics such as p-values or z-scores in a pre-specified way. The flexibility covers changes of sample sizes, treatment allocation ratios and the number of interim analyses, as well as the selection of treatments, doses and end points. The price to be paid is that non-standard test statistics must be used after an adaptation.

Issues in designing flexible trials

We outline the general framework of adaptive combination tests and discuss their relationship to flexible group sequential designs. An important field of applications is sample size reassessment. We discuss reassessment rules based on conditional power arguments using either the observed or the prefixed effect size. These rules tend to lead to large expected sample sizes for small actual effects. However, the application of a maximal bound for the second stage sample size leads to more favourable properties. Additionally, we consider an optimized reassessment rule in terms of expected sample sizes. Since the adaptive design does not use the classical test statistics for some types of sample size reassessments, the adaptive test may reject the null hypothesis while the classical one-sample test does not. We characterize sample size reassessment rules, where such inconsistencies are avoided. Finally, the extension of flexibility to the number of stages is explored. In the first interim analysis a second interim analysis is only planned if the chance to achieve a decision there is high. This leads to savings in the average number of interim analysis performed, without paying a noticeable price in terms of expected sample size.

Adaptive group sequential designs for clinical trials: combining the advantages of adaptive and of classical group sequential approaches

A general method is presented integrating the concept of adaptive interim analyses into classical group sequential testing. This allows the researcher to represent every group sequential plan as an adaptive trial design and to make design changes during the course of the trial after every interim analysis in the same way as with adaptive designs. The concept of adaptive trial designing is thereby generalized to a large variety of possible sequential plans.

Adaptive sample size calculations in group sequential trials

A method for group sequential trials that is based on the inverse normal method for combining the results of the separate stages is proposed. Without exaggerating the Type I error rate, this method enables data-driven sample size reassessments during the course of the study. It uses the stopping boundaries of the classical group sequential tests. Furthermore, exact test procedures may be derived for a wide range of applications. The procedure is compared with the classical designs in terms of power and expected sample size.

Combining different phases in the development of medical treatments within a single trial

In the development of medical treatments, identification of promising therapies and inference on selected treatments are usually performed in subsequent separate trials. An adaptive two-stage design is proposed for the situation of multiple treatments to be compared with a control, allowing integration of both steps within a single confirmatory trial controlling the multiple level alpha. After the interim analysis, the trial may be terminated early or is continued with a second stage, where the set of treatments may be reduced due to lack of efficacy or to safety problems. The procedure is highly flexible with respect to the distributional assumptions, stopping rules and selection criteria and allows a completely free recalculation of the sample size for the second stage. Simulations show that the method may be substantially more powerful than classical one-stage multiple treatment designs with the same total sample size. As in conventional strategies with a series of separate experiments, a reasonable selection strategy has to be applied in order to prevent proceeding with non-optimal treatments.