Response-adaptive Randomization Research Articles

Empirical meropenem versus piperacillin/tazobactam for adult patients with sepsis (EMPRESS) trial: Protocol.

Piperacillin/tazobactam may be associated with less favourable outcomes than carbapenems in patients with severe bacterial infections, but the certainty of evidence is low. The Empirical Meropenem versus Piperacillin/Tazobactam for Adult Patients with Sepsis (EMPRESS) trial is an investigator-initiated, international, parallel-group, randomised, open-label, adaptive clinical trial with an integrated feasibility phase. We will randomise adult, critically ill patients with sepsis to empirical treatment with meropenem or piperacillin/tazobactam for up to 30 days. The primary outcome is 30-day all-cause mortality. The secondary outcomes are serious adverse reactions within 30 days; isolation precautions due to resistant bacteria within 30 days; days alive without life support and days alive and out of hospital within 30 and 90 days; 90- and 180-day all-cause mortality and 180-day health-related quality of life. EMPRESS will use Bayesian statistical models with weak to somewhat sceptical neutral priors. Adaptive analyses will be conducted after follow-up of the primary outcome for the first 400 participants concludes and after every 300 subsequent participants, with adaptive stopping for superiority/inferiority and practical equivalence (absolute risk difference <2.5%-points) and response-adaptive randomisation. The expected sample sizes in scenarios with no, small or large differences are 5189, 5859 and 2570 participants, with maximum 14,000 participants and ≥99% probability of conclusiveness across all scenarios. EMPRESS will compare the effects of empirical meropenem against piperacillin/tazobactam in adult, critically ill patients with sepsis. Due to the pragmatic, adaptive design with high probability of conclusiveness, the trial results are expected to directly inform clinical practice.

Implementing and assessing Bayesian response-adaptive randomisation for backfilling in dose-finding trials

Traditional approaches in dose-finding trials, such as the continual reassessment method, focus on identifying the maximum tolerated dose. In contemporary early-phase dose-finding trials, especially in oncology with targeted agents or immunotherapy, a more relevant aim is to identify the lowest dose level that maximises efficacy whilst remaining tolerable. Backfilling, defined as the practice of assigning patients to dose levels lower than the current highest tolerated dose, has been proposed to gather additional pharmacokinetic, pharmacodynamic and biomarker data to recommend the most appropriate dose to carry forward for subsequent studies.The first formal framework [5] for backfilling proposed randomising backfill patients with equal probability among those doses below the dose level where the study is currently at. Here, we propose to use Bayesian response-adaptive randomisation to backfill patients. This patient-oriented approach to backfilling aims to allocate more patients to dose levels in the backfill set with higher expected efficacy based on emerging data. The backfill set constitutes of the doses below the dose the dose-finding algorithm is at. At study completion, collective patient data inform the dose-response curve, suggesting an optimal dose level balancing toxicity and efficacy.Our simulation study across diverse clinical trial settings demonstrates that a backfilling strategy using Bayesian response-adaptive randomisation can result in a patient-oriented patient assignment procedure which simultaneously enhances the likelihood of correctly identifying the most appropriate dose level. This contribution offers a methodological framework and practical implementation for patient-oriented backfilling, encompassing design and analysis considerations in early-phase trials.

Leveraging machine learning: Covariate-adjusted Bayesian adaptive randomization and subgroup discovery in multi-arm survival trials

Clinical trials evaluate the safety and efficacy of treatments for specific diseases. Ensuring these studies are well-powered is crucial for identifying superior treatments. With the rise of personalized medicine, treatment efficacy may vary based on biomarker profiles. However, researchers often lack prior knowledge about which biomarkers are linked to varied treatment effects. Fixed or response-adaptive designs may not sufficiently account for heterogeneous patient characteristics, such as genetic diversity, potentially reducing the chance of selecting the optimal treatment for individuals. Recent advances in Bayesian nonparametric modeling pave the way for innovative trial designs that not only maintain robust power but also offer the flexibility to identify subgroups deriving greater benefits from specific treatments. Building on this inspiration, we introduce a Bayesian adaptive design for multi-arm trials focusing on time-to-event endpoints. We introduce a covariate-adjusted response adaptive randomization, updating treatment allocation probabilities grounded on causal effect estimates using a random intercept accelerated failure time BART model. After the trial concludes, we suggest employing a multi-response decision tree to pinpoint subgroups with varying treatment impacts. The performance of our design is then assessed via comprehensive simulations.

Abstract 2389: Empowering early drug development in neoadjuvant non-small cell lung cancer studies using an innovative proof-of-concept platform trial design

Abstract Several platform trial designs have recently been proposed in oncology. However, developing an efficient one in the neoadjuvant non-small cell lung cancer (NSCLC) is not easy due to the difficulties in patient recruitment and limited relevant data. These obstacles hinder the inclusion of a control arm, thereby losing the ability to make an informed Go/No-Go decision, and to assess prognostic and predictive biomarkers. To overcome these challenges, we have developed an innovative and efficient proof-of-concept platform trial design that aims to empower drug development in early stage of neoadjuvant NSCLC. The proposed platform trial incorporates available experimental agents, allowing for new agents to be added when available. Within the master protocol structure, a small control arm is included, only about 20% of experimental arm size, and is shared by all experimental arms for the analysis purpose. Consequently, the resulting direct comparison with the control arm enables an informed Go/No-Go decision-making, while the total sample size and budget impacts are minimized. The flexibility of Go/No-Go decision-making is further enhanced in a 3-outcome decision-making framework where a consider zone is introduced for physicians to examine the totality of data. Two innovative statistical techniques are incorporated: Bayesian dynamic borrowing for current control, and response-adaptive randomization (RAR). The former helps reduce the sample size, and the latter aims to optimize patient allocation and improve the ability to identify promising agents. Simulation results demonstrate that the direct comparison sharply reduces the false positive rate below 10%, compared to a single-arm design setting. The effective sample size of the control arm is statistically augmented through Bayesian dynamic borrowing. The patient allocation is guided based on the agent’s efficacy data with a well-calibrated RAR. The promising agent receives meaningfully more patients than if a fixed-randomization is used, while the variability in patient allocation is decreased. Compared to a traditional design, our innovative design boosts the probability of identifying promising agent by up to 2-fold. To conclude, this research develops an innovative platform trial design to improve the success of drug development in early stage NSCLC. The master protocol structure, inclusion of a small control arm, and dynamic borrowing, increase the plausibility of conducting a trial in the neoadjuvant population. Advanced statistical features optimize the patient allocation and enhance the ability to identify promising drugs. Lastly, the proposed design can be easily applied to other oncology indications with appropriate modifications. Citation Format: Zhe Chen, Phillip A. Dennis, Ji Lin. Empowering early drug development in neoadjuvant non-small cell lung cancer studies using an innovative proof-of-concept platform trial design [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 2389.

Doubly adaptive biased coin design to improve Bayesian clinical trials with time-to-event endpoints.

Clinical trialists often face the challenge of balancing scientific questions with other design features, such as improving efficiency, minimizing exposure to inferior treatments, and simultaneously comparing multiple treatments. While Bayesian response adaptive randomization (RAR) is a popular and effective method for achieving these objectives, it is known to have large variability and a lack of explicit theoretical results, making its use in clinical trials a subject of concern. It is desirable to propose a design that targets the same allocation proportion as Bayesian RAR and achieves the above objectives but addresses the concerns over Bayesian RAR. We propose the frequentist doubly adaptive biased coin designs (DBCD) targeting ethical allocation proportions from the Bayesian framework to satisfy different objectives in clinical trials with time-to-event endpoints. We derive the theoretical properties of the proposed adaptive randomization design and show through comprehensive numerical simulations that it can achieve ethical objectives without sacrificing efficiency. Our combined theoretical and numerical results offer a strong foundation for the practical use of RAR in real clinical trials.

Uncertainty directed factorial clinical trials

Summary The development and evaluation of novel treatment combinations is a key component of modern clinical research. The primary goals of factorial clinical trials of treatment combinations range from the estimation of intervention-specific effects, or the discovery of potential synergies, to the identification of combinations with the highest response probabilities. Most factorial studies use balanced or block randomization, with an equal number of patients assigned to each treatment combination, irrespective of the specific goals of the trial. Here, we introduce a class of Bayesian response-adaptive designs for factorial clinical trials with binary outcomes. The study design was developed using Bayesian decision-theoretic arguments and adapts the randomization probabilities to treatment combinations during the enrollment period based on the available data. Our approach enables the investigator to specify a utility function representative of the aims of the trial, and the Bayesian response-adaptive randomization algorithm aims to maximize this utility function. We considered several utility functions and factorial designs tailored to them. Then, we conducted a comparative simulation study to illustrate relevant differences of key operating characteristics across the resulting designs. We also investigated the asymptotic behavior of the proposed adaptive designs. We also used data summaries from three recent factorial trials in perioperative care, smoking cessation, and infectious disease prevention to define realistic simulation scenarios and illustrate advantages of the introduced trial designs compared to other study designs.

Bayesian response adaptive randomization design with a composite endpoint of mortality and morbidity.

Allocating patients to treatment arms during a trial based on the observed responses accumulated up to the decision point, and sequential adaptation of this allocation, could minimize the expected number of failures or maximize total benefits to patients. In this study, we developed a Bayesian response-adaptive randomization (RAR) design targeting the endpoint of organ support-free days (OSFD) for patients admitted to the intensive care units. The OSFD is a mixture of mortality and morbidity assessed by the number of days of free of organ support within a predetermined post-randomization time-window. In the past, researchers treated OSFD as an ordinal outcome variable where the lowest category is death. We propose a novel RAR design for a composite endpoint of mortality and morbidity, for example, OSFD, by using a Bayesian mixture model with a Markov chain Monte Carlo sampling to estimate the posterior probability distribution of OSFD and determine treatment allocation ratios at each interim. Simulations were conducted to compare the performance of our proposed design under various randomization rules and different alpha spending functions. The results show that our RAR design using Bayesian inference allocated more patients to the better performing arm(s) compared to other existing adaptive rules while assuring adequate power and type I error rate control across a range of plausible clinical scenarios.

Effects of Allocation Method and Time Trends on Identification of the Best Arm in Multi-Arm Trials

Many trial designs, such as dose-finding trials, shared-control designs, or adaptive platform trials, investigate multiple therapies simultaneously. Often these trials seek to identify the best arm and compare it to a control. Adaptive trials are commonly considered in this space, focusing on methods that drop arms or adjust allocation in response to accumulating information. These methods continue to be compared in the literature, most recently with an emphasis on the effect of time trends during the experiment. Here we compare several methods, considering their performance with and without time trends present. The four procedures are: (a) fixed allocation, (b) arm dropping based on p-values (two variants), (c) arm dropping based on the posterior probability each arm is best (two variants), and (d) response-adaptive randomization. These procedures are compared in terms of their ability to identify the best arm, statistical power, accuracy of estimation, and potential benefit to participants inside the trial. We find arm dropping based on the probability each arm is best and RAR among the best options from the methods considered. Arm dropping based on p-values performs moderately worse, and fixed allocation is much worse on all metrics within this context.

A two armed optimal response adaptive randomization for ordinal categorical responses with possible misclassification

A two-treatment optimal target proportion is developed extending the idea of Hu et al. (2006) for phase III clinical trials, where the treatment outcomes are ordinal categorical in nature. Some response-adaptive procedures targeting this proportion are studied assuming the presence of some possible misclassification in the patient responses. The concept of asymptotically best design is also proposed in this setup. Two data studies, one from a clinical trial of patients with sports-related knee injury and another with postoperative nausea and vomiting (PONV), are also included for the assessment of the proposed procedures in real situations.

REMAP Periop: a randomised, embedded, multifactorial adaptive platform trial protocol for perioperative medicine to determine the optimal enhanced recovery pathway components in complex abdominal surgery patients within a US healthcare system

IntroductionImplementation of enhanced recovery pathways (ERPs) has resulted in improved patient-centred outcomes and decreased costs. However, there is a lack of high-level evidence for many ERP elements. We have designed...

Conducting a bayesian multi-armed trial with response adaptive randomization for comparative effectiveness of medications for CSPN

BackgroundResponse adaptive randomization is popular in adaptive trial designs, but the literature detailing its execution is lacking. These designs are desirable for patients/stakeholders, particularly in comparative effectiveness research, due to the potential benefits including improving participant buy-in by providing more participants with better treatment during the trial. Frequentist approaches have often been used, but adaptive designs naturally fit the Bayesian methodology; it was developed to deal with data as they come in by updating prior information. MethodsPAIN-CONTRoLS was a comparative-effectiveness trial utilizing Bayesian response adaptive randomization to four drugs, nortriptyline, duloxetine, pregabalin, or mexiline, for cryptogenic sensory polyneuropathy (CSPN) patients. The aim was to determine which treatment was most tolerable and effective in reducing pain. Quit and efficacy rates were combined into a utility function to develop a single outcome, which with treatment sample size, drove the adaptive randomization. Prespecified interim analyses allowed the study to stop for early success or update the randomization probabilities to the better-performing treatments. ResultsSeven adaptations to the randomization occurred before the trial ended due to reaching the maximum sample size, with more participants receiving nortriptyline and duloxetine. At the end of the follow-up, nortriptyline and duloxetine had lower probabilities of participants that had stopped taking the study medication and higher probabilities were efficacious. Mexiletine had the highest quit rate, but had an efficacy rate higher than pregabalin. ConclusionsResponse adaptive randomization has become a popular trial tool, especially for those utilizing Bayesian methods for analyses. By illustrating the execution of a Bayesian adaptive design, using the PAIN-CONTRoLS trial data, this paper continues the work to provide literature for conducting Bayesian response adaptive randomized trials.

Effects of duration of follow-up and lag in data collection on the performance of adaptive clinical trials.

Different combined outcome-data lags (follow-up durations plus data-collection lags) may affect the performance of adaptive clinical trial designs. We assessed the influence of different outcome-data lags (0-105 days) on the performance of various multi-stage, adaptive trial designs (2/4 arms, with/without a common control, fixed/response-adaptive randomisation) with undesirable binary outcomes according to different inclusion rates (3.33/6.67/10 patients/day) under scenarios with no, small, and large differences. Simulations were conducted under a Bayesian framework, with constant stopping thresholds for superiority/inferiority calibrated to keep type-1 error rates at approximately 5%. We assessed multiple performance metrics, including mean sample sizes, event counts/probabilities, probabilities of conclusiveness, root mean squared errors (RMSEs) of the estimated effect in the selected arms, and RMSEs between the analyses at the time of stopping and the final analyses including data from all randomised patients. Performance metrics generally deteriorated when the proportions of randomised patients with available data were smaller due to longer outcome-data lags or faster inclusion, that is, mean sample sizes, event counts/probabilities, and RMSEs were larger, while the probabilities of conclusiveness were lower. Performance metric impairments with outcome-data lags ≤45 days were relatively smaller compared to those occurring with ≥60 days of lag. For most metrics, the effects of different outcome-data lags and lower proportions of randomised patients with available data were larger than those of different design choices, for example, the use of fixed versus response-adaptive randomisation. Increased outcome-data lag substantially affected the performance of adaptive trial designs. Trialists should consider the effects of outcome-data lags when planning adaptive trials.

Response-adaptive randomization for multiarm clinical trials using context-dependent information measures.

Theoretical-information approach applied to the clinical trial designs appeared to bring several advantages when tackling a problem of finding a balance between power and expected number of successes (ENS). In particular, it was shown that the built-in parameter of the weight function allows finding the desired trade-off between the statistical power and number of treated patients in the context of small population PhaseII clinical trials. However, in real clinical trials, randomized designs are more preferable. The goal of this research is to introduce randomization to a deterministic entropy-based sequential trial procedure generalized to multiarm setting. Several methods of randomization applied to an entropy-based design are investigated in terms of statistical power and ENS. Namely, the four design types are considered: (a) deterministic procedures, (b) naive randomization using the inverse of entropy criteria as weights, (c) block randomization, and (d) randomized penalty parameter. The randomized entropy-based designs are compared to randomized Gittins index (GI) and fixed randomization (FR). After the comprehensive simulation study, the following conclusion on block randomization is made: for both entropy-based and GI-based block randomization designs the degree of randomization induced by forward-looking procedures is insufficient to achieve a decent statistical power. Therefore, we propose an adjustment for the forward-looking procedure that improves power with almost no cost in terms of ENS. In addition, the properties of randomization procedures based on randomly drawn penalty parameter are also thoroughlyinvestigated.

P11.29.B UPDATE ON GBM AGILE: A GLOBAL, PHASE 2/3 ADAPTIVE PLATFORM TRIAL TO EVALUATE MULTIPLE REGIMENS IN NEWLY DIAGNOSED AND RECURRENT GLIOBLASTOMA

Abstract BACKGROUND GBM AGILE (Glioblastoma Adaptive, Global, Innovative Learning Environment) is a biomarker based, multi-arm, international, seamless Phase 2/3 platform trial designed to rapidly identify experimental therapies that improve overall survival and confirm efficacious experimental therapies and associated biomarker signatures to support new drug approvals and registration. GBM AGILE is a collaboration between academic investigators, patient organizations and industry to support new drug applications for newly diagnosed (ND) and recurrent GBM. METHODS The primary objective of GBM AGILE is to identify therapies that effectively improve the overall survival in patients with ND or recurrent GBM. Bayesian response adaptive randomization is used within subtypes of the disease to assign participants to investigational arms based on their performance. New experimental therapies are added as information about promising new drugs is identified, while therapies are removed as they complete their evaluation. GBM AGILE has screened over 1400 patients and enrollment rates are 3 to 4 times greater than traditional GBM trials, with active sites averaging 0.75 to 1 patients/site/month. There are 41 active sites in the US, 4 active sites in Canada and 3 active sites in Europe with a total of 15 sites planned for Switzerland, France and Germany. Expansion to Australia is currently underway. GBM AGILE operates under a Master Protocol which allows multiple drugs from different pharmaceutical/biotech companies to be evaluated simultaneously and/or over time against a common control. Along with an adaptive trial design, shared control arm and operational processes to serve the goal of helping patients receive optimal care in a fast and efficient manner, GBM AGILE incorporates new design and operational elements to enhance efficiencies, including more recently dose finding and enhanced safety management components. The dose finding phase allows for an initial evaluation of the experimental study drug in combination with radiotherapy and temozolomide, and/or lomustine in a limited number of patients at a select number of study sites within the trial in order to ensure that there are no critical safety signals before expansion to a larger subset of patients for enhanced safety monitoring followed by broader inclusion of the combination at all global study sites. The investigational drugs that have employed the dose finding phase and enhanced safety monitoring process have tolerable safety profile with toxicities that are monitorable, reversible, and not related to the control arm treatments. Through the use of improved and flexible processes, GBM AGILE continues to serve as a global trial that supports the efficient and rapid incorporation and evaluation of new experimental therapies for patients with GBM. Clinical trial information: NCT03970447.

The Design of Nested Adaptive Clinical Trials of Multiple Organ Dysfunction Syndrome Children in a Single Study.

Describe the statistical design of the Personalized Immunomodulation in Sepsis-induced Multiple Organ Dysfunction Syndrome (MODS) (PRECISE) study. Children with sepsis-induced MODS undergo real-time immune testing followed by assignment to an immunophenotype-specific study cohort. Interventional cohorts include the granulocyte macrophage-colony stimulating factor (GM-CSF) for the Reversal of Immunoparalysis in Pediatric Sepsis-induced MODS (GRACE)-2 trial, which uses the drug GM-CSF (or placebo) to reverse immunoparalysis; and the Targeted Reversal of Inflammation in Pediatric Sepsis-induced MODS (TRIPS) trial, which uses the drug anakinra (or placebo) to reverse systemic inflammation. Both trials have adaptive components and use a statistical framework in which frequent data monitoring assesses futility and efficacy, allowing potentially earlier stopping than traditional approaches. Prespecified simulation-based stopping boundaries are customized to each trial to preserve an overall one-sided type I error rate. The TRIPS trial also uses response-adaptive randomization, updating randomization allocation proportions to favor active arms that appear more efficacious based on accumulating data. Twenty-four U.S. academic PICUs. Septic children with specific immunologic derangements during ongoing dysfunction of at least two organs. The GRACE-2 trial compares GM-CSF and placebo in children with immunoparalysis. The TRIPS trial compares four different doses of anakinra to placebo in children with moderate to severe systemic inflammation. Both trials assess primary efficacy using the sum of the daily pediatric logistic organ dysfunction-2 score over 28 days. Ranked summed scores, with mortality assigned the worst possible value, are compared between arms using the Wilcoxon Rank Sum test (GRACE-2) and a dose-response curve (TRIPS). We present simulation-based operating characteristics under several scenarios to demonstrate the behavior of the adaptive design. The adaptive design incorporates innovative statistical features that allow for multiple active arms to be compared with placebo based on a child's personal immunophenotype. The design increases power and provides optimal operating characteristics compared with traditional conservative methods.

Two-stage response adaptive randomization designs for multi-arm trials with binary outcome

ABSTRACT In recent years, adaptive randomization methods have gained significant popularity in clinical research and trial design due to their ability to provide both efficiency and flexibility in adjusting the statistical procedures of ongoing clinical trials. For a study to compare multiple treatments, a multi-arm two-stage design could be utilized to select the best treatment from the first stage and further compare that treatment with control in the second stage. The traditional design used equal randomization in both stages. To better utilize the interim results from the first stage, we propose to develop response adaptive randomization two-stage designs for a multi-arm clinical trial with binary outcome. Two allocation methods are considered: (1) an optimal allocation based on a sequential design; (2) the play-the-winner rule. Optimal multi-arm two-stage designs are obtained under three criteria: minimizing the expected number of failures, minimizing the average expected sample size, and minimizing the expected sample size under the null hypothesis. Simulation studies show that the proposed adaptive design based on the play-the-winner rule has good performance. A phase II trial for patients with pancreas adenocarcinoma and a germline BRCAPALB2 mutation was used to illustrate the application of the proposed response adaptive randomization designs.

An optimal sequential design in ethical allocation with an adaptive interim analysis

The present article provides a distribution-free test procedure for comparing the effectiveness of two competing treatments A and B, say, in a clinical trial. Here, the relative treatment effect is measured by the functional , where X and Y are respectively the response variables corresponding to two treatments, A and B. The treatment comparison is done through a testing of hypothesis regarding θ under a patient-benefit oriented two-stage response-adaptive design with an interim analysis in which an optimal sequential sampling scheme with equal randomisation is adopted in stage 1 and a response-adaptive randomisation is employed in stage 2 with the objective of allocating more patients to more promising treatment. The performance of the proposed procedure is compared with that of various other competitive procedures.

Oral paclitaxel and dostarlimab with or without trastuzumab in early-stage, high-risk breast cancer: Results from the neoadjuvant ISPY 2 TRIAL.

LBA612 Background: I-SPY2 is a multicenter, phase 2 trial using response-adaptive randomization within biomarker subtypes including MammaPrint (MP) status to evaluate novel neoadjuvant agents in high-risk breast cancer. The primary endpoint is pathologic complete response (pCR). Oral Paclitaxel and encequidar (OPE) is an oral combination of paclitaxel (P) with a p-glycoprotein pump inhibitor, encequidar. Dostarlimab (D) is an intravenous (IV) PD-1 inhibitor. Methods: Women with tumors ≥ 2.5cm and MP high risk cancers (MP1 = MP high; MP2 = MP ultra-high) were treated starting Oct 5, 2020. Treatment included OPE (Oral P 205mg/m2 + encequidar 12.9mg) on days 1-3 weekly x 12 and D 500 mg IV given q 3 weeks x 4, followed by doxorubicin/cyclophosphamide (AC) q 2-3 weeks x 4. Patients with HER2+ disease received IV weekly trastuzumab (T) during the first 12 weeks. The control arm was weekly IV P x 12 with or without trastuzumab followed by AC q 2-3 weeks x 4. OPE + D was eligible to graduate [85% chance of success in a 300-person phase 3 neoadjuvant trial with a pCR endpoint] in any of the pre-defined signatures. Results: 113 (78 HR+HER2-, 17 HR-HER2- and 18 HER2+ patients) received OPE + D +/- T. The control arm included 388 historical controls (201 HR+Her2-, 156 HR-HER2-, 31 HER2+). 77 patients (70 HR+ and 7 HR-) were MP1 and 36 patients (24 HR+ and 12 HR-) were MP2. Safety events of note for OPE + D versus IV P include increased rates of nausea (85% vs. 72%) diarrhea (77% vs. 41%). There was no significant difference in rates of neutropenia (23% vs.17%). Peripheral neuropathy (37% vs. 64%) and alopecia (59% vs. 66%) were significantly decreased. Immune related adverse events (irAEs) were lower than expected. Conclusions: Although both OPE and D have both been shown to have efficacy in other settings, combination therapy with OPE + D did not graduate in any of the predefined subtypes. In the HR+ signature where we would not expect a benefit of D, we see equal response to OPE with decreased rates of peripheral neuropathy and alopecia, which suggest this oral agent may be an attractive alternative to IV P in this subgroup and is under consideration in ISPY 2.2. We did not observe the expected improvement in pCR rates seen with PD-1 inhibitors in the HR- or MP2 subtypes (over P alone historic control). In addition, the irAEs were less than expected. Together these findings suggest interference of OPE with D. A potential mechanism of interference could be change in microbiome with the use of OPE vs. IV P, as the microbiome is known to influence the efficacy of immunotherapy. The source of interference is being investigated. Clinical trial information: NCT01042379 . [Table: see text]

Oral paclitaxel, carboplatin, and dostarlimab (OPE/Cb/D) without and with trastuzumab in early-stage, high-risk breast cancer: Results from the neoadjuvant I-SPY 2 TRIAL.

LBA520 Background: I-SPY 2 is a multicenter trial using response-adaptive randomization within biomarker subtypes including MammaPrint (MP) risk to evaluate novel neoadjuvant agents in high-risk breast cancer. Oral paclitaxel and encequidar (OPE) is an oral combination of paclitaxel (P) with a p-glycoprotein pump inhibitor, encequidar, to enhance gastrointestinal (GI) absorption. Dostarlimab (D) is an anti-PD-1 monoclonal antibody. Methods: Women with tumors ≥ 2.5cm and MP high-risk cancers were screened and treated starting Oct 5, 2020. Treatment included Oral Paclitaxel 205mg/m2 and encequidar 12.9 mg on days 1-3, Carboplatin (Cb) AUC 1.5 on day 1 weekly x 12, and Dostarlimab (D) 500 mg every 3 weeks x 4, followed by doxorubicin/ cyclophosphamide (AC) every 2-3 weeks x 4. The control arm was IV P weekly x 12 followed by AC every 2-3 weeks x 4. For patients with HER2+ disease, weekly Trastuzumab (T) was administered during the first 12 weeks. The arm was eligible for graduation [&gt; 85% chance of success in a 300-person phase 3 neoadjuvant trial with a pathologic complete response (pCR) endpoint] in 10 predefined signatures. Results: 106 patients (44 HR+HER2-, 56 HR-HER2- (TN), 6 HER2+) received OPE/Cb/D ± T. The control arm included 388 historical controls (201 HR+HER2-, 156 TN, 31 HER2+). 22 patients (20 HR+, 2 HR-) in OPE/Cb/D were MP1 (MP high) and 84 patients (29 HR+, 55 HR-) were MP2 (MP ultra-high). OPE/Cb/D graduated in the TN signature and accrual was stopped. Conclusions: OPE/Cb/D graduated in the TN signature with a higher predicted pCR rate compared to control. OPE and D have been, individually, shown to have efficacy in other settings. The lower-than-expected pCR rate and lower irAEs with triplet therapy (taxane, platinum, immune checkpoint inhibitor [ICI]) in TN compared to prior IV chemo + ICI arms on I-SPY 2 suggests a possible interference of OPE with ICI. Changes in gut microbiome is being investigated as an explanation. Clinical trial information: NCT01042379 . [Table: see text]

Comment: Group Sequential Designs with Response-Adaptive Randomisation

Group sequential Phase III trial designs enable early stopping for positive or negative study outcomes. Response-adaptive randomisation can be included in such designs with the sampling ratio in each group of subjects determined by the current treatment effect estimate. We demonstrate the potential of adaptive randomisation to reduce the number of patients receiving the inferior treatment, even when there is a delay in observing each patient’s response. We also observe that using a fixed but unequal sampling ratio may offer a simpler way to achieve the same objectives.