Design and analysis considerations for utilizing a mapping function in a small sample, sequential, multiple assignment, randomized trials with continuous outcomes.

Small sample, sequential, multiple assignment, randomized trials (snSMARTs) are multistage trials with the overall goal of determining the best treatment after a fixed amount of time. In snSMART trials, patients are first randomized to one of three treatments and a binary (e.g. response/nonresponse) outcome is measured at the end of the first stage. Responders to first stage treatment continue their treatment. Nonresponders to first stage treatment are rerandomized to one of the remaining treatments. The same binary outcome is measured at the end of the first and second stages, and data from both stages are pooled together to find the best first stage treatment. However, in many settings the primary endpoint may be continuous, and dichotomizing this continuous variable may reduce statistical efficiency. In this article, we extend the snSMART design and methods to allow for continuous outcomes. Instead of requiring a binary outcome at the first stage for rerandomization, the probability of staying on the same treatment or switching treatment is a function of the first stage outcome. Rerandomization based on a mapping function of a continuous outcome allows for snSMART designs without requiring a binary outcome. We perform simulation studies to compare the proposed design with continuous outcomes to standard snSMART designs with binary outcomes. The proposed design results in more efficient treatment effect estimates and similar outcomes for trial patients.

Bayesian methods to compare dose levels with placebo in a small n, sequential, multiple assignment, randomized trial.

Clinical trials studying treatments for rare diseases are challenging to design and conduct due to the limited number of patients eligible for the trial. One design used to address this challenge is the small n, sequential, multiple assignment, randomized trial (snSMART). We propose a new snSMART design that investigates the response rates of a drug tested at a low and high dose compared with placebo. Patients are randomized to an initial treatment (stage 1). In stage 2, patients are rerandomized, depending on their initial treatment and their response to that treatment in stage 1, to either the same or a different dose of treatment. Data from both stages are used to determine the efficacy of the active treatment. We present a Bayesian approach where information is borrowed between stage 1 and stage 2. We compare our approach to standard methods using only stage 1 data and a log-linear Poisson model that uses data from both stages where parameters are estimated using generalized estimating equations. We observe that the Bayesian method has smaller root-mean-square-error and 95% credible interval widths than standard methods in the tested scenarios. We conclude that it is advantageous to utilize data from both stages for a primary efficacy analysis and that the specific snSMART design shown here can be used in the registration of a drug for the treatment of rare diseases.

Sample size determination for Bayesian analysis of small n sequential, multiple assignment, randomized trials (snSMARTs) with three agents.

The small n, Sequential, Multiple Assignment, Randomized Trial (snSMART) is a two-stage clinical trial design for rare diseases motivated by the comparison of three active treatments for isolated skin vasculitis in the ongoing clinical trial ARAMIS (a randomized multicenter study for isolated skin vasculitis, NCT09239573). In Stage 1, all patients are randomized to one of three treatments. In Stage 2, patients who respond to their initial treatment receive the same treatment again, while those who fail to respond are re-randomized to one of the two remaining treatments. A Bayesian method for estimating the response rate of each individual treatment in a three-arm snSMART demonstrated efficiency gains for a given sample size relative to other existing frequentist approaches. However, these efficiency gains are dependent upon knowing how many subjects are required to determine a specific difference in the treatment response rates. Because few sample size calculation methods for snSMARTs exist, we propose a Bayesian sample size calculation for an snSMART designed to distinguish the best treatment from the second-best treatment. Although our methods are based on asymptotic approximations, we demonstrate via simulations that our proposed sample size calculation approach produces the desired statistical power, even in small samples. Moreover, our methods and applet produce sample sizes quickly, thereby saving time relative to using simulations to determine the appropriate sample size. We compare our proposed sample size to an existing frequentist method based upon a weighted Z-statistic and demonstrate that the Bayesian method requires far fewer patients than the frequentist method for a study with the same design parameters.

Predicting progression to type 1 diabetes from ages 3 to 6 in islet autoantibody positive TEDDY children.

OBJECTIVE: The capacity to precisely predict progression to type 1 diabetes (T1D) in young children over a short time span is an unmet need. We sought to develop a risk algorithm to predict progression in children with high-risk human leukocyte antigen (HLA) genes followed in The Environmental Determinants of Diabetes in the Young (TEDDY) study. METHODS: Logistic regression and 4-fold cross-validation examined 38 candidate predictors of risk from clinical, immunologic, metabolic, and genetic data. TEDDY subjects with at least one persistent, confirmed autoantibody at age 3 were analyzed with progression to T1D by age 6 serving as the primary endpoint. The logistic regression prediction model was compared to two non-statistical predictors, multiple autoantibody status, and presence of insulinoma-associated-2 autoantibodies (IA-2A). RESULTS: A total of 363 subjects had at least one autoantibody at age 3. Twenty-one percent of subjects developed T1D by age 6. Logistic regression modeling identified 5 significant predictors - IA-2A status, hemoglobin A1c, body mass index Z-score, single-nucleotide polymorphism rs12708716_G, and a combination marker of autoantibody number plus fasting insulin level. The logistic model yielded a receiver operating characteristic area under the curve (AUC) of 0.80, higher than the two other predictors; however, the differences in AUC, sensitivity, and specificity were small across models. CONCLUSIONS: This study highlights the application of precision medicine techniques to predict progression to diabetes over a 3-year window in TEDDY subjects. This multifaceted model provides preliminary improvement in prediction over simpler prediction tools. Additional tools are needed to maximize the predictive value of these approaches.

Risk factors for chemotherapy-induced nausea in pediatric patients receiving highly emetogenic chemotherapy.

BACKGROUND: Little is known regarding risk factors for chemotherapy-induced nausea (CIN) in pediatric patients. PROCEDURE: A secondary analysis was conducted of a previously published multicenter, prospective, randomized, single-blind, sham-controlled trial assessing the efficacy of acupressure in preventing CIN in pediatric patients receiving highly emetogenic chemotherapy. The primary outcome was nausea severity, self-reported using the Pediatric Nausea Assessment Tool. The relationships between acute and delayed nausea severity and patient- (sex, race, age, and cancer diagnosis) and treatment-related (chemotherapy, antiemetic prophylaxis, CIN, and vomiting control) factors were analyzed by a proportional odds generalized estimating equation approach. The acute phase started with administration of the first and continued for 24 hours after the last chemotherapy dose. The delayed phase started at the end of the acute phase and continued until the next chemotherapy block (maximum seven days). RESULTS: In the acute and delayed phases, 165 and 144 patients provided data for analysis, respectively. Nonwhite race was significantly associated with higher acute phase nausea severity (OR, 1.7; 95% CI, 1.1-2.6). Poor CIN control in the acute phase (OR, 16; 95% CI, 4.0-64.6), diagnosis of a cancer other than a central nervous system (CNS) tumor (OR, 2.5; 95% CI, 1.2-5.3), and cisplatin administration (OR, 3.7; 95% CI, 2.1-6.0) were significantly associated with higher delayed phase nausea severity. CONCLUSION: Acute phase CIN was associated with nonwhite race. Delayed phase CIN was associated with poor acute phase CIN control, diagnosis of non-CNS cancer, and receipt of cisplatin. These findings will inform future antiemetic trial design.

Acupressure bands do not improve chemotherapy-induced nausea control in pediatric patients receiving highly emetogenic chemotherapy: A single-blinded, randomized controlled trial.

BACKGROUND: Chemotherapy-induced nausea and vomiting remain common, distressing side effects of chemotherapy. It has been reported that acupressure prevents chemotherapy-induced nausea in adults, but it has not been well studied in children. METHODS: In this multicenter, prospective, randomized, single-blind, sham-controlled trial, the authors compared acute-phase nausea severity in patients ages 4 to 18 years who were receiving highly emetic chemotherapy using standard antiemetic agents combined with acupressure wrist bands, the most common type of acupressure, versus sham bands. Patients wore acupressure or sham bands continuously on each day of chemotherapy and for up to 7 days afterward. Chemotherapy-induced nausea severity in the delayed phase and chemotherapy-induced vomiting control in the acute and delayed phases also were compared. RESULTS: Of the 187 patients randomized, 165 contributed nausea severity assessments during the acute phase. Acupressure bands did not reduce the severity of chemotherapy-induced nausea in the acute phase (odds ratio [OR], 1.33; 95% confidence limits, 0.89-2.00, in which an OR <1.00 favored acupressure) or in the delayed phase (OR, 1.23; 95% CL, 0.75-2.01). Furthermore, acupressure bands did not improve daily vomiting control during the acute phase (OR, 1.57; 95% CL, 0.95-2.59) or the delayed phase (OR, 0.84; 95% CL, 0.45-1.58). No serious adverse events were reported. CONCLUSIONS: Acupressure bands were safe but did not improve chemotherapy-induced nausea or vomiting in pediatric patients who were receiving highly emetic chemotherapy. Cancer 2018;124:1188-96. © 2017 American Cancer Society.

A Bayesian analysis of small n sequential multiple assignment randomized trials (snSMARTs).

Designing clinical trials to study treatments for rare diseases is challenging because of the limited number of available patients. A suggested design is known as the small n sequential multiple assignment randomized trial (snSMART), in which patients are first randomized to one of multiple treatments (stage 1). Patients who respond to their initial treatment continue the same treatment for another stage, while those who fail to respond are rerandomized to one of the remaining treatments (stage 2). The data from both stages are used to compare the efficacy between treatments. Analysis approaches for snSMARTs are limited, and we propose a Bayesian approach that allows for borrowing of information across both stages. Through simulation, we compare the bias, root-mean-square error, width, and coverage rate of 95% confidence/credible interval of estimators from of our approach to estimators produced from (i) standard approaches that only use the data from stage 1, and (ii) a log-Poisson model using data from both stages whose parameters are estimated via generalized estimating equations. We demonstrate the root-mean-square error and width of 95% confidence/credible intervals of our estimators are smaller than the other approaches in realistic settings, so that the collection and use of stage 2 data in snSMARTs provide improved inference for treatments of rare diseases.

Maternal use of dietary supplements during pregnancy is not associated with coeliac disease in the offspring: The Environmental Determinants of Diabetes in the Young (TEDDY) study.

Perinatal exposure to nutrients and dietary components may affect the risk for coeliac disease (CD). We investigated the association between maternal use of vitamin D, n-3 fatty acids (FA) and Fe supplements during pregnancy and risk for CD autoimmunity (CDA) and CD in the offspring. Children at increased genetic risk were prospectively followed from birth in The Environmental Determinants of Diabetes in the Young (TEDDY) study. CDA was defined as having persistently positive tissue transglutaminase autoantibodies (tTGA). Diagnosis of CD was either biopsy-confirmed or considered likely if having persistently elevated levels of tTGA>100 AU. Of 6627 enrolled children, 1136 developed CDA at a median 3·1 years of age (range 0·9-10) and 409 developed CD at a median 3·9 years of age (range 1·2-11). Use of supplements containing vitamin D, n-3 FA and Fe was recalled by 66, 17 and 94 % of mothers, respectively, at 3-4 months postpartum. The mean cumulative intake over the entire pregnancy was 2014 µg vitamin D (sd 2045 µg), 111 g n-3 FA (sd 303 g) and 8806 mg Fe (sd 7017 mg). After adjusting for country, child's human leucocyte antigen genotype, sex, family history of CD, any breast-feeding duration and household crowding, Cox's proportional hazard ratios did not suggest a statistically significant association between the intake of vitamin D, n-3 FA or Fe, and risk for CDA or CD. Dietary supplementation during pregnancy may help boost nutrient intake, but it is not likely to modify the risk for the disease in the offspring.

Glutamic acid not beneficial for the prevention of vincristine neurotoxicity in children with cancer.

BACKGROUND: Vincristine causes known side effects of peripheral sensory, motor, autonomic and cranial neuropathies. No preventive interventions are known. PROCEDURE: We performed a randomized, placebo-controlled, double-blind trial of oral glutamic acid as a preventive agent in pediatric patients with cancer who would be receiving vincristine therapy for at least 9 consecutive weeks (Stratum 1 = Wilms tumor and rhabdomyosarcoma) or 4 consecutive weeks in conjunction with steroids (Stratum 2 = Acute lymphoblastic leukemia and non-Hodgkin lymphoma). At designated time points, a scored neurologic exam using the Modified Balis Pediatric Scale of Peripheral Neuropathies was performed to document neurologic toxicity. RESULTS: Between 2007 and 2012, 250 patients were enrolled (Stratum 1 = 50, Stratum 2 = 200). The glutamic acid treated group did not have a significantly lower percentage of neurotoxicity compared to placebo treated group either overall or within stratum or age subgroups. The only subgroup which was suggestive of treatment effect was for age. Patients 13 years or older showed a larger benefit in favor of glutamic acid (P = 0.055) compared to patients less than 13 years (P = 1.00). Constipation was the most frequently reported (14%) Grade II or higher neurotoxicity. CONCLUSION: Vincristine-associated neurotoxicity in pediatric oncology remains a frequent complication of chemotherapy for multiple diagnoses with an approximate 30% of patients affected. Glutamic acid is not effective for prevention in pre-adolescents. There is a suggestion of benefit in patients 13 years or older, but the study was not designed to provide adequate power to test the treatment effect within this age group alone.

A sequential enriched design for target patient population in psychiatric clinical trials.

High placebo response is widely believed to be one major reason why many psychiatric clinical trials fail to demonstrate drug efficacy. In order to alleviate this problem, research has developed several enrichment designs, including the parallel design with a placebo lead-in phase, the sequential parallel design, and a recently proposed two-way enriched design. While these designs have been evaluated and discussed individually, their effectiveness against each other has not been rigorously compared. The current study examines the various enrichment designs simultaneously. Building on their strengths, we introduce a new improved design named' sequential enriched design' (SED) aimed at removing not only patients with high placebo response but also patients who do not respond to any treatment from the study. The SED begins with a double-blind placebo lead-in phase followed by a traditional parallel design in the first stage. Only patients who respond to the drug in the first stage are re-randomized to the drug or placebo at the second stage. We simulate data for a mixed population composed of four subgroups of patients who are predetermined as to whether they respond to drug or not as well as to placebo or not. By focusing on the target patients whose responses reflect the drug's efficacy,we evaluate the bias, mean squared error, and power for different designs. We demonstrate that the SED produces a less biased estimate for the target treatment effect and yields reasonably high power in general compared with the other designs.

Power prior models for estimating response rates in a small n, sequential, multiple assignment, randomized trial.

A small n, sequential, multiple assignment, randomized trial (snSMART) is a small sample, two-stage design where participants receive up to two treatments sequentially, but the second treatment depends on response to the first treatment. The parameters of interest in an snSMART are the first-stage response rates of the treatments, but outcomes from both stages can be used to obtain more information from a small sample. A novel way to incorporate the outcomes from both stages uses power prior models, in which first stage outcomes from an snSMART are regarded as the primary (internal) data and second stage outcomes are regarded as supplemental data (co-data). We apply existing power prior models to snSMART data, and we also develop new extensions of power prior models. All methods are compared to each other and to the Bayesian joint stage model (BJSM) via simulation studies. By comparing the biases and the efficiency of the response rate estimates among all proposed power prior methods, we suggest application of Fisher's Exact Test or the Bhattacharyya's overlap measure to an snSMART to estimate the response rates in an snSMART, which both have performance mostly as good or better than the BJSM. We describe the situations where each of these suggested approaches is preferred.

Estimation of treatment effect for the sequential parallel design.

The sequential parallel clinical trial is a novel clinical trial design being used in psychiatric diseases that are known to have potentially high placebo response rates. The design consists of an initial parallel trial of placebo versus drug augmented by a second parallel trial of placebo versus drug in the placebo non-responders from the initial trial. Statistical research on the design has focused on hypothesis tests. However, an equally important output from any clinical trial is the estimate of treatment effect and variability around that estimate. In the sequential parallel trial, the most important treatment effect is the effect in the overall population. This effect can be estimated by considering only the first phase of the trial, but this ignores useful information from the second phase of the trial. We develop estimates of treatment effect that incorporate data from both phases of the trial. Our simulations and a real data example suggest that there can be substantial gains in precision by incorporating data from both phases. The potential gains appear to be greatest in moderate-sized trials, which would typically be the case in phase II trials.

Genetic Subtype-Phenotype Analysis of Growth Hormone Treatment on Psychiatric Behavior in Prader-Willi Syndrome.

Prader-Willi syndrome (PWS) is a complex multisystemic condition caused by a lack of paternal expression of imprinted genes from the 15q11.2-q13 region. Limited literature exists on the association between molecular classes, growth hormone use, and the prevalence of psychiatric phenotypes in PWS. In this study, we analyzed nine psychiatric phenotypes (depressed mood, anxiety, skin picking, nail picking, compulsive counting, compulsive ordering, plays with strings, visual hallucinations, and delusions) recognized in PWS and investigated associations with growth hormone treatment (GHT), deletions (DEL) and uniparental disomy (UPD) in a cohort of 172 individuals with PWS who met the criteria for analysis. Associations were explored using Pearson chi-square tests and univariable and multivariable logistic regression analyses to control for confounding exposures. This observational study of the largest dataset of patients with PWS to date suggested the following genetic subtype and phenotype correlations in psychiatric behaviors: (1) skin picking was more frequent in those with DEL vs. UPD; (2) anxiety was more common in those with UPD vs. DEL; and (3) an increased frequency of anxiety was noted in the UPD group treated with GHT compared to the DEL group. No other significant associations were found between the genetic subtype or GHT including for depressed mood, nail picking, compulsive counting, compulsive ordering, playing with strings, and visual hallucinations. Further studies will be required before any conclusions can be reached.

Protocol for a randomized multicenter study for isolated skin vasculitis (ARAMIS) comparing the efficacy of three drugs: azathioprine, colchicine, and dapsone.

BACKGROUND: Skin-limited forms of vasculitis, while lacking systemic manifestations, can persist or recur indefinitely, cause pain, itch, or ulceration, and be complicated by infection or scarring. High-quality evidence on how to treat these conditions is lacking. The aim of this comparative effectiveness study is to determine the optimal management of patients with chronic skin-limited vasculitis. METHODS: ARAMIS is a multicenter, sequential, multiple assignment randomized trial with an enrichment design (SMARTER) aimed at comparing the efficacy of three drugs-azathioprine, colchicine, and dapsone-commonly used to treat various forms of isolated skin vasculitis. ARAMIS will enroll patients with isolated cutaneous small or medium vessel vasculitis, including cutaneous small vessel vasculitis, immunoglobulin A (IgA) vasculitis (skin-limited Henoch-Schönlein purpura), and cutaneous polyarteritis nodosa. Patients not responding to the initial assigned therapy will be re-randomized to one of the remaining two study drugs (Stage 2). Those with intolerance or contraindication to a study drug can be randomized directly into Stage 2. Target enrollment is 90 participants, recruited from international centers affiliated with the Vasculitis Clinical Research Consortium. The number of patients enrolled directly into Stage 2 of the study will be capped at 10% of the total recruitment target. The primary study endpoint is the proportion of participants from the pooled study stages with a response to therapy at month 6, according to the study definition. DISCUSSION: ARAMIS will help identify effective agents for skin-limited forms of vasculitis, an understudied group of diseases. The SMARTER design may serve as an example for future trials in rare diseases. TRIAL REGISTRATION: ClinicalTrials.gov: NCT02939573. Registered on 18 October 2016.

A small n sequential multiple assignment randomized trial design for use in rare disease research.

BACKGROUND: Clinical trials in rare diseases are difficult to conduct due to the limited number of patients available with each disorder. We developed a Phase 2 trial which is a small n sequential multiple assignment randomized trial (snSMART) design to test several treatments for a rare disease for which no standard therapy exists. PURPOSE: This paper illustrates the design, sample size estimation and operating characteristics of an snSMART. METHODS: We investigate the performance of a class of weighted Z statistics via computer simulations. RESULTS: We demonstrate the increase in power over traditional single stage designs, and indicate how the power changes as a function of the weight given to each stage. CONCLUSION: The snSMART design is promising in a rare disease setting where several alternative treatments are under consideration and small sample sizes are necessary.

A two-way enriched clinical trial design: combining advantages of placebo lead-in and randomized withdrawal.

A new clinical trial design, designated the two-way enriched design (TED), is introduced, which augments the standard randomized placebo-controlled trial with second-stage enrichment designs in placebo non-responders and drug responders. The trial is run in two stages. In the first stage, patients are randomized between drug and placebo. In the second stage, placebo non-responders are re-randomized between drug and placebo and drug responders are re-randomized between drug and placebo. All first-stage data, and second-stage data from first-stage placebo non-responders and first-stage drug responders, are utilized in the efficacy analysis. The authors developed one, two and three degrees of freedom score tests for treatment effect in the TED and give formulae for asymptotic power and for sample size computations. The authors compute the optimal allocation ratio between drug and placebo in the first stage for the TED and compare the operating characteristics of the design to the standard parallel clinical trial, placebo lead-in and randomized withdrawal designs. Two motivating examples from different disease areas are presented to illustrate the possible design considerations.

An open-label safety and pharmacokinetics study of duloxetine in pediatric patients with major depression.

OBJECTIVE: This preliminary, 32-week study assessed the safety, tolerability, and pharmacokinetics of duloxetine in pediatric patients (aged 7-17 years) with major depressive disorder. METHODS: Patients received flexible duloxetine doses of 20-120 mg once daily, with dose changes made based on clinical improvement and tolerability. Pharmacokinetic samples were collected across all duloxetine doses, and data were analyzed using population modeling. Primary outcome measures included treatment-emergent adverse events (TEAEs), vital signs, and Columbia-Suicide Severity Rating Scale (C-SSRS). RESULTS: Of the 72 enrolled patients, 48 (66.7%) completed acute treatment (18 weeks) and 42 (58.3%) completed extended treatment. Most patients (55/72; 76%) required doses ≥ 60 mg once daily to optimize efficacy based on investigator judgment and Clinical Global Impressions-Severity score. Body weight and age did not significantly affect duloxetine pharmacokinetic parameters. Typical duloxetine clearance in pediatric patients was ≈ 42%-60% higher than that in adults. Four patients (5.6%) discontinued due to TEAEs. Many (36/72, 50%) patients experienced potentially clinically significant (PCS) elevations in blood pressure, with most cases (21/36, 58%) being transient. As assessed via C-SSRS, one nonfatal suicidal attempt occurred, two patients (2.8%) experienced worsening of suicidal ideation, and among the 19 patients reporting suicidal ideation at baseline, 17 (90%) reported improvement in suicidal ideation. CONCLUSION: Results suggested that pediatric patients generally tolerated duloxetine doses of 30 to 120 mg once daily, although transient PCS elevations in blood pressure were observed in many patients. Pharmacokinetic results suggested that adjustment of total daily dose based on body weight or age is not warranted for pediatric patients and different total daily doses may not be warranted for pediatric patients relative to adults.

Recent developments in improving signal detection and reducing placebo response in psychiatric clinical trials.

Recent (2007-2010) empirical and theoretical literature on associations of trial design features with signal detection and placebo response were investigated, along with data and analytic considerations. Trials with greater percentages of patients randomized to placebo had larger average drug-placebo differences in two comprehensive meta-analyses (MDD and Schizophrenia). Excluding patients with large responses during double-blind placebo lead-ins resulted in small increases in drug-placebo differences. Core factor subscales of the HAMD yielded larger drug-placebo differences than the HAMD total score. Direct likelihood-based (MMRM) and similar analyses provided better control of false positive and false negative results than LOCF and BOCF. Theoretical considerations suggested that the number of sites and number of countries can influence power, depending on the correlation structure in the data and on how sites and countries are chosen. Use of centralized ratings reduced placebo response and improved drug-placebo differences. However, the number of comparisons was too small to draw conclusions. Use of patient ratings and reducing the number of study visits reduced placebo response, but their effects on signal detection were unclear. Practical experience with novel designs such as the sequential parallel approach hold promise for improvements in signal detection. Given the complexities of signal detection and placebo response, no single strategy is likely to fully solve the problem and combinations of approaches may be most useful. Utilizing appropriate analytic techniques and randomizing an adequate fraction of patients to placebo are perhaps the most broadly applicable approaches.

An examination of the efficiency of the sequential parallel design in psychiatric clinical trials.

BACKGROUND: Psychiatric clinical trials have a high failure rate, even among agents which are known to be effective. Because of this high failure rate, a novel clinical trial design has been proposed which incorporates a second phase in which non-responders to placebo are randomly reassigned to drug or placebo. PURPOSE: The purpose of this research is to examine the efficiency of this new design compared to the conventional two arm clinical trial. We consider both binary and continuous endpoints. METHODS: The limiting distribution of a class of weighted average test statistics is obtained for the binary case which allows analytic calculation of the power for a given set of parameters. For the continuous case, we examine the efficiency of seemingly unrelated regression and a weighted average statistic via simulation. RESULTS: The novel design reduces the sample size 20-25% compared to the standard design under a wide range of parameters. LIMITATIONS: There are no actual trials with the novel design therefore assumptions of the effect size across two periods for actual psychiatric agents is unknown. CONCLUSIONS: The new design reduces sample size which in turn should reduce the cost of clinical trials. Further refinements of the design are possible including alternative test statistics and incorporation of additional data from placebo responders.