Bayesian Hierarchical Models for Subgroup Analysis.

In conventional subgroup analyses, subgroup treatment effects are estimated using data from each subgroup separately without considering data from other subgroups in the same study. The subgroup treatment effects estimated this way may be heterogenous with high variability due to small sample sizes in some subgroups and much different from the treatment effect in the overall population. A Bayesian hierarchical model (BHM) can be used to derive more precise, and less heterogenous estimates of subgroup treatment effects that are closer to the treatment effect in the overall population. BHM assumes exchangeability in treatment effect across subgroups after adjusting for effect modifiers and other relevant covariates. In this article, we will discuss the technical details for applying one-way and multi-way BHM using summary-level statistics, and patient-level data for subgroup analysis. Four case studies based on four new drug applications are used to illustrate the application of these models in subgroup analyses for continuous, dichotomous, time-to-event, and count endpoints.

Finding the (biomarker-defined) subgroup of patients who benefit from a novel therapy: No time for a game of hide and seek.

An important element of precision medicine is the ability to identify, for a specific therapy, those patients for whom benefits of that therapy meaningfully exceed the risks. To achieve this goal, treatment effect usually is examined across subgroups defined by a variety of factors, including demographic, clinical, or pathologic characteristics or by molecular attributes of patients or their disease. Frequently such subgroups are defined by the measurement of biomarkers. Even though such examination is necessary when pursuing this goal, the evaluation of treatment effect across a variety of subgroups is statistically fraught due to both the danger of inflated false-positive error rate from multiple testing and the inherent insensitivity to how treatment effects differ across subgroups.Pre-specification of subgroup analyses with appropriate control of false-positive (i.e. type I) error is recommended when possible. However, when subgroups are specified by biomarkers, which could be measured by different assays and might lack established interpretation criteria, such as cut-offs, it might not be possible to fully specify those subgroups at the time a new therapy is ready for definitive evaluation in a Phase 3 trial. In these situations, further refinement and evaluation of treatment effect in biomarker-defined subgroups might have to take place within the trial. A common scenario is that evidence suggests that treatment effect is a monotone function of a biomarker value, but optimal cut-offs for therapy decisions are not known. In this setting, hierarchical testing strategies are widely used, where testing is first conducted in a particular biomarker-positive subgroup and then is conducted in the expanded pool of biomarker-positive and biomarker-negative patients, with control for multiple testing. A serious limitation of this approach is the logical inconsistency of excluding the biomarker-negatives when evaluating effects in the biomarker-positives, yet allowing the biomarker-positives to drive the assessment of whether a conclusion of benefit could be extrapolated to the biomarker-negative subgroup.Examples from oncology and cardiology are described to illustrate the challenges and pitfalls. Recommendations are provided for statistically valid and logically consistent subgroup testing in these scenarios as alternatives to reliance on hierarchical testing alone, and approaches for exploratory assessment of continuous biomarkers as treatment effect modifiers are discussed.

Perspectives on informative Bayesian methods in pediatrics.

Bayesian methods have been proposed as a natural fit for pediatric extrapolation, as they allow the incorporation of relevant external data to reduce the required sample size and hence trial burden for the pediatric patient population. In this paper we will discuss our experience and perspectives with these methods in pediatric trials. We will present some of the background and thinking underlying pediatric extrapolation and discuss the use of Bayesian methods within this context. We will present two recent case examples illustrating the value of a Bayesian approach in this setting and present perspectives on some of the issues that we have encountered in these and other cases.

Innovations in Pediatric Therapeutics Development: Principles for the Use of Bridging Biomarkers in Pediatric Extrapolation.

Even with recent substantive improvements in health care in pediatric populations, considerable need remains for additional safe and effective interventions for the prevention and treatment of diseases in children. The approval of prescription drugs and biological products for use in pediatric settings, as in adults, requires demonstration of substantial evidence of effectiveness and favorable benefit-to-risk. For diseases primarily affecting children, such evidence predominantly would be obtained in the pediatric setting. However, for conditions affecting both adults and children, pediatric extrapolation uses scientific evidence in adults to enable more efficiently obtaining a reliable evaluation of an intervention's effects in pediatric populations. Bridging biomarkers potentially have an integral role in pediatric extrapolation. In a setting where an intervention reliably has been established to be safe and effective in adults, and where there is substantive evidence that disease processes in pediatric and adult settings are biologically similar, a 'bridging biomarker' should satisfy three additional criteria: effects on the bridging biomarker should capture effects on the principal causal pathway through which the disease process meaningfully influences 'feels, functions, survives' measures; secondly, the experimental intervention should not have important unintended effects on 'feels, functions, survives' measures not captured by the bridging biomarker; and thirdly, in statistical analyses in adults, the intervention's net effect on 'feels, functions, survives' measures should be consistent with what would be predicted by its level of effect on the bridging biomarker. A validated bridging biomarker has considerable potential utility, since an intervention's efficacy could be extrapolated from adult to pediatric populations if evidence in children establishes the intervention not only to be safe but also to have substantive effects on that bridging biomarker. Proper use of bridging biomarkers could increase availability of reliably evaluated therapies approved for use in pediatric settings, enabling children and their caregivers to make informed choices about health care.

Should responder analyses be conducted on continuous outcomes?

Continuous outcomes are often dichotomized to classify trial subjects as responders or nonresponders, with the difference in rates of response between treatment and control defined as the "responder effect." In this article, we caution that dichotomization of continuous interval outcomes may not be best practice. Defining clinical benefit or harm for continuous interval outcomes as the difference between the means of treatment and control, that is, the "continuous treatment effect," we examine the case where treatment and control outcomes are normally distributed and differ only in location. For this case, continuous treatment effects may be considered clinically relevant if they exceed a prespecified minimum clinically important difference. In contrast, using minimum clinically important differences as dichotomization thresholds will not ensure clinically relevant responder effects. For example, in some situations, increasing the threshold may actually relax the criterion for effectiveness by increasing the calculated responder effect. Using responder effects to quantitatively assess benefit or risk of investigational drugs for continuous interval outcomes presents interpretational challenges. In particular, when the dichotomization threshold is halfway between the treatment and control outcome means, the responder effect is at a maximum with a magnitude monotonically related to the number of standard deviations between the mean outcomes of treatment and control. Large responder effect benefits may therefore reflect clinically unimportant continuous treatment effects amplified by small standard deviations, and small responder effect risks may reflect either clinically important continuous treatment effects minimized by large standard deviations, or selection of a dichotomization threshold not providing maximum responder effect.

Bayesian Methods in Human Drug and Biological Products Development in CDER and CBER.

The Center for Drug Evaluation and Research (CDER) and the Center for Biologics Evaluation and Research (CBER) of the U.S. Food and Drug Administration (FDA) have been leaders in protecting and promoting the U.S. public health by helping to ensure that safe and effective drugs and biological products are available in the United States for those who need them. The null hypothesis significance testing approach, along with other considerations, is typically used to demonstrate the effectiveness of a drug or biological product. The Bayesian framework presents an alternative approach to demonstrate the effectiveness of a treatment. This article discusses the Bayesian framework for drug and biological product development, highlights key settings in which Bayesian approaches may be appropriate, and provides recent examples of the use of Bayesian approaches within CDER and CBER.

Retrieved-Dropout-Based multiple imputation for time-to-event data in cardiovascular outcome trials.

Recently, retrieved-dropout-based multiple imputation has been used in some therapeutic areas to address the treatment policy estimand, mostly for continuous endpoints. In this approach, data from subjects who discontinued study treatment but remained in study were used to construct a model for multiple imputation for the missing data of subjects in the same treatment arm who discontinued study. We extend this approach to time-to-event endpoints and provide a practical guide for its implementation. We use a cardiovascular outcome trial dataset to illustrate the method and compare the results with those from Cox proportional hazard and reference-based multiple imputation methods.

Resampling-based stepwise multiple testing procedures with applications to clinical trial data.

Endpoints in clinical trials are often highly correlated. However, the commonly used multiple testing procedures in clinical trials either do not take into consideration the correlations among test statistics or can only exploit known correlations. Westfall and Young constructed a resampling-based stepdown method that implicitly utilizes the correlation structure of test statistics in situations with unknown correlations. However, their method requires a "subset pivotality" assumption. Romano and Wolf proposed a more general stepdown method, which does not require such an assumption. There is at present little experience with the application of such methods in analyzing clinical trial data. We advocate the application of resampling-based multiple testing procedures to clinical trials data when appropriate. We have conjectured that the resampling-based stepdown methods can be extended to a stepup procedure under appropriate assumptions and examined the performance of both stepdown and stepup methods under a variety of correlation structures and distribution types. Results from our simulation studies support the use of the resampling-based methods under various scenarios, including binary data and small samples, with strong control of Family wise type I error rate (FWER). Under positive dependence and for binary data even under independence, the resampling-based methods are more powerful than the Holm and Hochberg methods. Last, we illustrate the advantage of the resampling-based stepwise methods with two clinical trial data examples: a cardiovascular outcome trial and an oncology trial.

Assessing and communicating heterogeneity of treatment effects for patient subpopulations: Panel discussion on considerations in design and analysis.

Clinical trials are primarily conducted to understand the average effects treatments have on patients. However, patients are heterogeneous in the severity of the condition and in ways that affect what treatment effect they can expect. It is therefore important to understand and characterize how treatment effects vary. The design and analysis of clinical studies play critical roles in evaluating and characterizing heterogeneous treatment effects. This panel discussed considerations in design and analysis under the recognition that there are heterogeneous treatment effects across subgroups of patients. Panel members discussed many questions including: What is a good estimate of the treatment effect in me, a 65-year-old, bald, Caucasian-American, male patient? What magnitude of heterogeneity of treatment effects (HTE) is sufficiently large to merit attention? What role can prior evidence about HTE play in confirmatory trial design and analysis? Is there anything described in the 21st Century Cures Act that would benefit from greater attention to HTE? An example of a Bayesian approach addressing multiplicity when testing for treatment effects in subgroups will be provided. We can do more or better at understanding heterogeneous treatment effects and providing the best information on heterogeneous treatment effects.

U.S. Food and Drug Administration approval summary: omacetaxine mepesuccinate as treatment for chronic myeloid leukemia.

On October 26, 2012, the U.S. Food and Drug Administration (FDA) granted accelerated approval to omacetaxine mepesuccinate (Synribo; Teva Pharmaceuticals USA, Inc., North Wales, PA, http://www.tevausa.com) for the treatment of adult patients with chronic phase (CP) or accelerated phase (AP) chronic myeloid leukemia (CML) with resistance and/or intolerance to two or more tyrosine kinase inhibitors (TKIs). The approval was based on the FDA review of data from 111 patients with CML in CP or in AP who had received two or more prior TKIs, including imatinib. Major cytogenetic response was achieved in 18% of patients with CP, with a median response duration of 12.5 months. Major hematologic response was achieved in 14% of patients with AP, with a median response duration of 4.7 months. The FDA safety evaluation was based on submitted data from 163 patients with CP or AP CML who had received at least one dose of omacetaxine mepesuccinate. The safety evaluation was limited by the single-arm design of the clinical trials as conducted in a small number of previously treated patients. The most common (≥20%) adverse reactions of any grade in enrolled patients included thrombocytopenia, anemia, neutropenia, diarrhea, nausea, fatigue, asthenia, injection site reaction, pyrexia, and infection. The FDA concluded that omacetaxine mepesuccinate has shown activity and a favorable benefit-to-risk profile for the studied population of adult patients with CML (CP or AP) with resistance and/or intolerance to two or more TKIs. Further evidence of response durability to verify clinical benefit is pending.

Evaluating and adjusting for premature censoring of progression-free survival.

The intent-to-treat principle, grouping subjects as they were randomized and following all subjects to the endpoint or the end of study, allows valid statistical comparisons. Progression-free survival (PFS) has been used as a decision-making endpoint in oncology. It can be difficult to have a meaningful intent-to-treat analysis of PFS as some studies have extensive loss to follow-up for PFS. In the analysis, subjects lost to follow-up for PFS have their PFS times censored, with the censoring treated as noninformative. We use remaining overall survival to investigate whether premature censoring for PFS is informative and the potential bias in treating such censoring as noninformative.

U.s. Food and Drug Administration approval: carfilzomib for the treatment of multiple myeloma.

The U.S. Food and Drug Administration (FDA) review leading to accelerated approval of carfilzomib is described. A single-arm trial enrolled 266 patients with multiple myeloma refractory to the most recent therapy who had received prior treatment with bortezomib and an immunomodulatory agent (IMID). Patients received carfilzomib by intravenous infusion over 2 to 10 minutes at a dose of 20 mg/m2 on days 1, 2, 8, 9, 15, and 16 of the 28 days of cycle 1, and at a dose of 27 mg/m2 on the same schedule in cycle 2 and subsequent cycles. The primary efficacy endpoint was overall response rate (ORR) as determined by an independent review committee using International Myeloma Working Group Uniform Response Criteria. The safety of carfilzomib was evaluated in 526 patients with multiple myeloma treated with various dosing regimens. The ORR was 23%. The median duration of response was 7.8 months. The most common adverse reactions associated with carfilzomib infusion were fatigue, anemia, nausea, thrombocytopenia, dyspnea, diarrhea, and fever. The most common serious adverse events were pneumonia, acute renal failure, fever, and congestive heart failure. Infusion reactions to carfilzomib could be reduced by pretreatment with dexamethasone and intravenous fluids. On July 20, 2012, the FDA granted accelerated approval of carfilzomib for the treatment of patients with multiple myeloma who have received at least two prior therapies including bortezomib and an IMID and who have shown disease progression while on therapy or within 60 days of completion of the last therapy.

U.S. Food and Drug Administration approval summary: brentuximab vedotin for the treatment of relapsed Hodgkin lymphoma or relapsed systemic anaplastic large-cell lymphoma.

The U.S. Food and Drug Administration (FDA) describes the accelerated approval of brentuximab vedotin for patients with relapsed Hodgkin lymphoma and relapsed systemic anaplastic large-cell lymphoma (sALCL). FDA analyzed the results of two single-arm trials, enrolling 102 patients with Hodgkin lymphoma and 58 patients with sALCL. Both trials had primary endpoints of objective response rate (ORR) and key secondary endpoints of response duration and complete response (CR) rate. For patients with Hodgkin lymphoma, ORR was 73% (95% CI, 65-83%); median response duration was 6.7 months, and CR was 32% (95% CI, 23-42%). For patients with sALCL, ORR was 86% (95% CI, 77-95%), median response duration was 12.6 months, and CR was 57% (95% CI, 44-70%). The most common adverse reactions were neutropenia, peripheral sensory neuropathy, fatigue, nausea, anemia, upper respiratory infection, diarrhea, pyrexia, rash, thrombocytopenia, cough, and vomiting. FDA granted accelerated approval of brentuximab vedotin for the treatment of patients with Hodgkin lymphoma after failure of autologous stem cell transplantation (ASCT) or after failure of at least two prior multiagent chemotherapy regimens in patients who are not ASCT candidates, and for the treatment of patients with sALCL after failure of at least one prior multiagent chemotherapy regimen.

Testing in a Prespecified Subgroup and the Intent-to-Treat Population.

In many settings, testing has been proposed to assess the effect of an experimental regimen within a biomarker-positive subgroup where it is biologically plausible that benefit is stronger in such patients, and in the overall population that also includes biomarker-negative subjects less likely to benefit from that regimen. A statistically favorable result in the biomarker-positive subgroup would lead to a claim for that subgroup, whereas a statistically favorable result for the overall population would lead to a claim that includes both biomarker subgroups. The latter setting is problematic when biomarker-negative patients truly do not benefit from the experimental regimen. When it is prespecified that biomarker-negative patients should not be included in the primary analysis of treatment effect in biomarker-positive patients because of the likelihood that treatment effects would differ between the 2 subgroups, it is logically inconsistent to include biomarker-positive patients in the primary analysis of treatment effect in biomarker-negative patients.

U.S. Food and Drug Administration approval: ruxolitinib for the treatment of patients with intermediate and high-risk myelofibrosis.

On November 16, 2011, the U.S. Food and Drug Administration (FDA) granted full approval to ruxolitinib, (Jakafi; Incyte Corp.), an inhibitor of the Janus kinases 1 and 2, for the treatment of patients with intermediate- or high-risk myelofibrosis, including primary myelofibrosis, postpolycythemia vera myelofibrosis, and postessential thrombocythemia myelofibrosis. This approval was based on the results of 2 large randomized phase III trials that enrolled patients with intermediate-2 or high-risk myelofibrosis and compared ruxolitinib with placebo (study 1) or best available therapy (study 2). The primary efficacy endpoint was the proportion of patients who experienced a reduction in spleen volume of ≥ 35% at 24 weeks (study 1) or 48 weeks (study 2). The key secondary endpoint in study 1 was the proportion of patients who experienced a ≥ 50% improvement from baseline in myelofibrosis total symptom score at 24 weeks. The results of these studies showed that a greater proportion of patients treated with ruxolitinib experienced a ≥ 35% reduction in spleen volume as compared with those treated with placebo (42% vs. 1%, P < 0.0001) or best available therapy (29% vs. 0%, P < 0.0001). A greater proportion of patients in study 1 experienced a ≥ 50% reduction in the myelofibrosis total symptom score during treatment with ruxolitinib than with placebo (46% vs. 5%, P < 0.0001). Ruxolitinib treatment was associated with an increased incidence of grades III and IV anemia, thrombocytopenia, and neutropenia. This is the first drug approved for myelofibrosis.

Some essential considerations in the design and conduct of non-inferiority trials.

BACKGROUND: Suppose a standard therapy (Standard) has been established to provide a clinically important reduction in risk of irreversible morbidity or mortality. In that setting, the safety and efficacy of an experimental intervention likely would be assessed in a clinical trial providing a comparison with Standard rather than a placebo arm. Such a trial often is designed to assess whether the efficacy of the experimental intervention is not unacceptably worse than that of Standard, and is called a non-inferiority trial. Formally, the non-inferiority trial usually is designed to rule out a non-inferiority margin, defined as the minimum threshold for what would constitute an unacceptable loss of efficacy. PURPOSE: Even though the literature has many important articles identifying various approaches to the design and conduct of non-inferiority trials, confusion remains especially regarding key considerations for selecting the non-inferiority margin. The purpose of this article is to provide improved clarity regarding these considerations. METHODS: We present scientific insights into many factors that should be addressed in the design and conduct of non-inferiority trials to enhance their integrity and reliability, and provide motivation for key considerations that guide the selection of non-inferiority margins. We also provide illustrations and insights from recent experiences. RESULTS: Two considerations are essential, and should be addressed in separate steps, in the formulation of the non-inferiority margin. First, the margin should be formulated using adjustments to account for bias or lack of reliability in the estimate of the effect of Standard in the non-inferiority trial setting. Second, the non-inferiority margin should be formulated to achieve preservation of an appropriate percentage of the effect of Standard. LIMITATIONS: The considerations, in particular regarding the importance of preservation of effect, might not apply to settings where it would be ethical as well as clinically relevant to include both Standard and placebo arms in the trial for direct comparisons with the experimental intervention arm. CONCLUSIONS: Non-inferiority trials with non-rigorous margins allow substantial risk for accepting inadequately effective experimental regimens, leading to the risk of erosion in quality of health care. The design and conduct of non-inferiority trials, including selection of non-inferiority margins, should account for many factors that can induce bias in the estimated effect of Standard in the non-inferiority trial and thus lead to bias in the estimated effect of the experimental treatment, for the need to ensure the experimental treatment preserves a clinically acceptable fraction of Standard's effect, and for the particular vulnerability of the integrity of a non-inferiority trial to the irregularities in trial conduct. Due to the inherent uncertainties in non-inferiority trials, alternative designs should be pursued whenever possible.

U.S. Food and drug administration approval: rituximab in combination with fludarabine and cyclophosphamide for the treatment of patients with chronic lymphocytic leukemia.

PURPOSE: To describe the clinical studies that led to the FDA approval of rituximab in combination with fludarabine and cyclophosphamide (FC) for the treatment of patients with chronic lymphocytic leukemia (CLL). MATERIALS AND METHODS: The results of two multinational, randomized trials in CLL patients comparing rituximab combined with fludarabine and cyclophosphamide versus FC were reviewed. The primary endpoint of both studies was progression-free survival (PFS). RESULTS: The addition of rituximab to FC decreased the risk of a PFS event by 44% in 817 previously untreated patients and by 24% in 552 previously treated patients. Median survival times could not be estimated. Exploratory analysis in patients older than 70 suggested that there was no benefit to patients when rituximab was added to FC. The safety profile observed in both trials was consistent with the known toxicity profile of rituximab, FC, or CLL. CONCLUSIONS: On the basis of the demonstration of clinically meaningful prolongation of PFS, the FDA granted regular approval to rituximab in combination with FC for the treatment of patients with CLL. The magnitude of the treatment effect in patients 70 years and older is uncertain.

U.S. Food and Drug Administration approval: ofatumumab for the treatment of patients with chronic lymphocytic leukemia refractory to fludarabine and alemtuzumab.

PURPOSE: To describe the data and analyses that led to the U.S. Food and Drug Administration (FDA) approval of ofatumumab (Arzerra, GlaxoSmithKline) for the treatment of patients with chronic lymphocytic leukemia (CLL) refractory to fludarabine and alemtuzumab. EXPERIMENTAL DESIGN: The FDA reviewed the results of a planned interim analysis of a single-arm trial, enrolling 154 patients with CLL refractory to fludarabine, and a supportive dose-finding, activity-estimating trial in 33 patients with CLL. Patients in the primary efficacy study received ofatumumab weekly for eight doses, then every 4 weeks for an additional four doses; patients in the supportive trial received four weekly doses. In the primary efficacy study, endpoints were objective response rate and response duration. RESULTS: For regulatory purposes, the primary efficacy population consisted of 59 patients with CLL refractory to fludarabine and alemtuzumab. In this subgroup, the investigator-determined objective response rate was 42% [99% confidence interval (CI), 26-60], with a median duration of response of 6.5 months (95% CI, 5.8-8.3); all were partial responses. The most common adverse reactions in the primary efficacy study were neutropenia, pneumonia, pyrexia, cough, diarrhea, anemia, fatigue, dyspnea, rash, nausea, bronchitis, and upper respiratory tract infections. Infusion reactions occurred in 44% of patients with the first infusion (300 mg) and 29% with the second infusion (2,000 mg). The most common serious adverse reactions were infections, neutropenia, and pyrexia. CONCLUSIONS: On October 26, 2009, the FDA granted accelerated approval to ofatumumab for the treatment of patients with CLL refractory to fludarabine and alemtuzumab, on the basis of demonstration of durable tumor shrinkage.

Issues in using progression-free survival when evaluating oncology products.

Several challenging and often controversial issues arise in oncology trials with the use of the end point progression-free survival (PFS), defined to be the time to detection of progressive disease or death. While this end point does not directly measure how a patient feels, functions, or survives, it does provide insights about whether an intervention affects the tumor burden process, the intended mechanism through which it is hoped that most anticancer agents will provide benefit. However, simply achieving statistically significant effects on PFS is insufficient to obtaining reliable evidence of important clinical benefit, and even is insufficient to justifying the conclusion that the experimental intervention is "reasonably likely to provide clinical benefit." The magnitude of the effect on PFS in addition to the statistical strength of evidence is of great importance in interpreting the reliability of the evidence regarding clinical efficacy. PFS has several important properties, including being a direct measure of the effect of treatment on the tumor burden process, being sensitive to cytostatic as well as cytotoxic mechanisms of interventions, and incorporating the clinically relevant event of death, increasing its sensitivity to influential harmful mechanisms and avoiding substantial bias that arises when deaths are censored. To obtain reliable evidence about the effect of an intervention on PFS and patient survival, randomized trials should be conducted where all patients are followed to progression and death, and where patients in a control arm do not cross-in at progression unless the experimental regimen has already been established to be effective rescue treatment.