Extensions to the two-stage randomized trial design for testing treatment, self-selection, and treatment preference effects to binary outcomes

Likelihood based inferences for trials incorporating participant's treatment choice

Randomized clinical trials are the gold standard for clinical trials as they reduce bias and minimize variability between different arms of a study. One of the drawbacks of these designs is their lack of flexibility to incorporate participant's treatment choice, which may reduce recruitment rates and/or reduce participant's tolerance if they receive a non-preferred treatment. Designs incorporating choice allow a subset of participants to choose their preferred treatment. Most of the current methods to analyze these types of designs are based on an ANOVA approach that do not allow for inclusion of covariates in the model. In this paper, we propose an alternative approach based on likelihood methods that can be used with a broad class of distributions and allow for inclusion of covariates and multiple study arms in the model. Using simulations, we evaluate these methods for a variety of continuous and categorical outcomes. Finally, we illustrate these methods by analyzing change in six minute walking distance from a behavioral intervention study for women with heart disease.

Group sequential two-stage preference designs

The two-stage preference design (TSPD) enables inference for treatment efficacy while allowing for incorporation of patient preference to treatment. It can provide unbiased estimates for selection and preference effects, where a selection effect occurs when patients who prefer one treatment respond differently than those who prefer another, and a preference effect is the difference in response caused by an interaction between the patient's preference and the actual treatment they receive. One potential barrier to adopting TSPD in practice, however, is the relatively large sample size required to estimate selection and preference effects with sufficient power. To address this concern, we propose a group sequential two-stage preference design (GS-TSPD), which combines TSPD with sequential monitoring for early stopping. In the GS-TSPD, pre-planned sequential monitoring allows investigators to conduct repeated hypothesis tests on accumulated data prior to full enrollment to assess study eligibility for early trial termination without inflating type I error rates. Thus, the procedure allows investigators to terminate the study when there is sufficient evidence of treatment, selection, or preference effects during an interim analysis, thereby reducing the design resource in expectation. To formalize such a procedure, we verify the independent increments assumption for testing the selection and preference effects and apply group sequential stopping boundaries from the approximate sequential density functions. Simulations are then conducted to investigate the operating characteristics of our proposed GS-TSPD compared to the traditional TSPD. We demonstrate the applicability of the design using a study of Hepatitis C treatment modality.

Analysis of survival outcomes using likelihood ratio test in trials incorporating patient's treatment choice

Methods for designing and analyzing multiple arms survival trials that incorporate patient's treatment choice are needed. In these trials, patients are randomized into two groups, random and choice. Participants in the choice group choose their treatment, which is not a current standard practice in randomized clinical trials. In this paper, we propose a new method based on the likelihood function to design and analyze these trials with time to event outcomes in the presence of non-informative right censoring. We use simulations to evaluate the methods for Weibull outcomes, complete and censored. Finally, we provide an illustration for designing a study in which we discuss some design considerations and demonstrate the methods.

Design and analysis of partially randomized preference trials with propensity score stratification

While the two-stage randomized design allows us to unbiasedly evaluate the impact of patients' treatment preference on the outcome of interest, it may not always be practical to implement in clinical practice; patients with a strong preference may not be willing to be randomized. The more pragmatic, partially randomized preference design (PRPD) allows patients who are unwilling to be randomized, but willing to state their preference, to receive their preferred treatment in lieu of the first-stage randomization in the two-stage design, at the cost of potentially introducing bias in estimating the effects of interest. In this article, we consider the application of propensity score stratification (PSS) in a PRPD to recreate a conditional first-stage randomization based on observed covariates, enabling the estimation and inference of the overall treatment, selection and preference effects with minimum bias. We additionally derive a set of closed-form sample size formulas for detecting all three effects of interest in a PSS-PRPD. Simulation studies demonstrate the bias reduction properties of the PSS-PRPD, and validate the accuracy of the proposed sample size formulas. Our results show that 5 to 10 propensity score strata may be needed to correct for biases in effect estimates, and the exact number of strata needed to achieve the best match between the empirical power and formula prediction may depend on the degree of effect heterogeneity. Finally, we demonstrate our proposed formulas by estimating the required sample sizes to detect treatment, selection and preference effects in the context of the Harapan Study.

Study Designs to Assess Real-World Interventions to Prevent COVID-19

Background: In the face of the novel virus SARS-CoV-2, scientists and the public are eager for evidence about what measures are effective at slowing its spread and preventing morbidity and mortality. Other than mathematical modeling, studies thus far evaluating public health and behavioral interventions at scale have largely been observational and ecologic, focusing on aggregate summaries. Conclusions from these studies are susceptible to bias from threats to validity such as unmeasured confounding, concurrent policy changes, and trends over time. We offer recommendations on how to strengthen frequently applied study designs which have been used to understand the impact of interventions to reduce the spread of COVID-19, and suggest implementation-focused, pragmatic designs that, moving forward, could be used to build a robust evidence base for public health practice. Methods: We conducted a literature search of studies that evaluated the effectiveness of non-pharmaceutical interventions and policies to reduce spread, morbidity, and mortality of COVID-19. Our targeted review of the literature aimed to explore strengths and weaknesses of implemented studies, provide recommendations for improvement, and explore alternative real-world study design methods to enhance evidence-based decision-making. Results:Study designs such as pre/post, interrupted time series, and difference-in-differences have been used to evaluate policy effects at the state or country level of a range of interventions, such as shelter-in-place, face mask mandates, and school closures. Key challenges with these designs include the difficulty of disentangling the effects of contemporaneous changes in policy and correctly modeling infectious disease dynamics. Pragmatic study designs such as the SMART (Sequential, Multiple-Assignment Randomized Trial), stepped wedge, and preference designs could be used to evaluate community re-openings such as schools, and other policy changes. Conclusions: As the epidemic progresses, we need to move from post-hoc analyses of available data (appropriate for the beginning of the pandemic) to proactive evaluation to ensure the most rigorous approaches possible to evaluate the impact of COVID-19 prevention interventions. Pragmatic study designs, while requiring initial planning and community buy-in, could offer more robust evidence on what is effective and for whom to combat the global pandemic we face and future policy decisions.

Two-stage randomized trial design for testing treatment, preference, and self-selection effects for count outcomes

While the traditional clinical trial design lays emphasis on testing the treatment effect between randomly assigned groups, it ignores the role of patient preference for a particular treatment in the trial. Yet, for healthcare providers who seek to optimize the patient-centered treatment strategy, the evaluation of a patient's psychology toward each treatment could be a key consideration. The two-stage randomized trial design allows researchers to test patient's preference and selection effects, in addition to the treatment effect. The current methodology for the two-stage design is limited to continuous and binary outcomes; this article extends the model to include count outcomes. The test statistics for preference, selection, and treatment effects are derived. Closed-form sample size formulae are presented for each effect. Simulations are presented to demonstrate the properties of the unstratified and stratified designs. Finally, we apply methods to the use of antimicrobials at the end of life to demonstrate the applicability of the methods.

Relative efficiencies of alternative preference-based designs for randomised trials

Recent work has shown that outcomes in clinical trials can be affected by which treatment the trial participants would select if they were allowed to do so, and if they do or do not actually receive that treatment. These influences are known as selection and preference effects, respectively. Unfortunately, they cannot be evaluated in conventional, parallel group trials because patient preferences remain unknown. However, several alternative designs have been proposed, to measure and take account of patient preferences. In this paper, we discuss three preference-based designs (the two-stage, fully randomised, and partially randomised designs). In conventional trials, only the treatment effect is estimable, while the preference-based designs have the potential to estimate some or all of the selection and preference effects. The relative efficiency of these designs is affected by several factors, including the proportion of participants who are undecided about treatments, or who are unable or unwilling to state a preference; the relative preference rate between the treatments being compared, among patients who do have a preference; and the ratio of patients randomised to each treatment. We also discuss the advantages and disadvantages of these designs under different scenarios.

Accounting for health literacy and intervention preferences when reducing unhealthy snacking: protocol for an online randomised controlled trial

INTRODUCTION

Health literacy describes the cognitive and social skills that individuals use to access, understand and act on health information. Health literacy interventions typically take the 'universal precautions approach' where all consumers are presented with simplified materials. Although this approach can improve knowledge and comprehension, its impact on complex behaviours is less clear. Systematic reviews also suggest that health literacy interventions underuse volitional strategies (such as planning) that play an important role in behaviour change. A recent study found volitional strategies may need to be tailored to the participant's health literacy. The current study aims to replicate these findings in a sample of people who have diabetes and/or are overweight or obese as measured by body mass index, and to investigate the most effective method of allocating an action plan to a participant to reduce unhealthy snacking.

METHODS AND ANALYSIS

We plan to recruit approximately 2400 participants at baseline. Participants will receive one of two alternative online action plans intended to reduce unhealthy snacking ('standard' action plan or 'literacy-sensitive' action plan). Participants will be randomised to a method of allocation to an action plan: (1) random allocation; (2) allocation by health literacy screening tool or (3) allocation by participant selection. Primary outcome is self-reported serves of unhealthy snacks during the previous month. Multiple linear regression will evaluate the impact of health literacy on intervention effectiveness. The analysis will also identify independent contributions of each action plan, method of allocation, health literacy and participant selections on unhealthy snacking at 4-week follow-up.

ETHICS AND DISSEMINATION

This study was approved by the University of Sydney Human Research Ethics Committee (2017/793). Findings will be disseminated through peer-reviewed international journals, conferences and updates with collaborating public health bodies (Diabetes New South Wales (NSW) & Australian Capital Territory (ACT), and Western Sydney Local Health District).

TRIAL REGISTRATION NUMBER

ACTRN12618001409268; Pre-results.