RESUMO
INTRODUCTION: Bayesian adaptive designs for clinical trials have gained popularity in the recent years due to the flexibility and efficiency that they offer. We consider the scenario where the outcome of interest comprises events with relatively low risk of occurrence and different case definitions resulting in varying control group risk assumptions. This is a scenario that occurs frequently for infectious diseases in global health research. METHODS: We propose a Bayesian adaptive design that incorporates different case definitions of the outcome of interest that vary in stringency. A set of stopping rules are proposed where superiority and futility may be concluded with respect to different outcome definitions and therefore maintain a realistic probability of stopping in trials with low event rates. Through a simulation study, a variety of stopping rules and design configurations are compared. RESULTS: The simulation results are provided in an interactive web application that allows the user to explore and compare the design operating characteristics for a variety of assumptions and design parameters with respect to different outcome definitions. The results for select simulation scenarios are provided in the article. DISCUSSION: Bayesian adaptive designs offer the potential for maximizing the information learned from the data collected through clinical trials. The proposed design enables monitoring and utilizing multiple composite outcomes based on rare events to optimize the trial design operating characteristics.
Assuntos
Futilidade Médica , Projetos de Pesquisa , Humanos , Teorema de Bayes , Simulação por Computador , Probabilidade , Ensaios Clínicos como AssuntoRESUMO
Bayesian methods are often suggested as a solution for issues encountered in small sample research, however, Bayesian methods often require informative priors to outperform classical methods in these settings. Specifying accurate priors with respect to the true value of the parameter of interest is challenging and inaccurate informative priors can have detrimental effects on conclusions from the statistical analysis. This paper proposes an objective procedure for creating informative priors for mediation analysis based on a historical data set; the only requirements for implementing the procedure are that the data from the current study constitute a representative sample from the population of interest, and that the historical and current data sets contain measures of the same covariates and independent variable, mediator, and outcome. The simulation study findings show that the proposed method leads to appropriate amount of borrowing from the historical data set, which leads to increases in precision and power when the historical data and current data are exchangeable, and does not induce bias when the historical and current studies are not exchangeable. The proposed method is illustrated using data from the project PROsetta Stone, and we provide rstan code for implementing the proposed method.
Assuntos
Análise de Mediação , Modelos Estatísticos , Teorema de Bayes , Viés , Simulação por ComputadorRESUMO
Bayesian adaptive designs have gained popularity in all phases of clinical trials with numerous new developments in the past few decades. During the COVID-19 pandemic, the need to establish evidence for the effectiveness of vaccines, therapeutic treatments, and policies that could resolve or control the crisis emphasized the advantages offered by efficient and flexible clinical trial designs. In many COVID-19 clinical trials, because of the high level of uncertainty, Bayesian adaptive designs were considered advantageous. Designing Bayesian adaptive trials, however, requires extensive simulation studies that are generally considered challenging, particularly in time-sensitive settings such as a pandemic. In this article, we propose a set of methods for efficient estimation and uncertainty quantification for design operating characteristics of Bayesian adaptive trials. Specifically, we model the sampling distribution of Bayesian probability statements that are commonly used as the basis of decision making. To showcase the implementation and performance of the proposed approach, we use a clinical trial design with an ordinal disease-progression scale endpoint that was popular among COVID-19 trials. However, the proposed methodology may be applied generally in the clinical trial context where design operating characteristics cannot be obtained analytically.
Les plans adaptatifs bayésiens ont gagné en popularité dans toutes les phases d'essais cliniques grâce à d'importants développements réalisés au cours des dernières décennies. Pendant la pandémie COVID19, la nécessité d'établir des preuves de l'efficacité des vaccins, des traitements thérapeutiques et des politiques susceptibles de résoudre ou de contrôler la crise a mis en évidence les avantages offerts par des plans d'essais cliniques efficaces et flexibles. En raison du niveau élevé d'incertitude présent dans de nombreux essais cliniques COVID19, les plans adaptatifs bayésiens ont été considérés comme avantageux. Cela dit, la conception d'essais adaptatifs bayésiens nécessite de vastes études de simulation qui sont généralement considérées comme difficiles, en particulier dans des contextes sensibles au facteur temps comme lors d'une pandémie. Les auteurs de cet article proposent un ensemble de méthodes d'estimation efficace et de quantification de l'incertitude pour la conception d'essais adaptatifs bayésiens. En particulier, une modélisation de la distribution d'échantillonnage des énoncés de probabilité bayésienne est proposée. Cette dernière est couramment requise lors de la prise de décisions. Pour illustrer la mise en Åuvre et la performance de l'approche proposée, les auteurs ont utilisé un plan d'essai clinique avec un critère d'évaluation ordinal de l'évolution de la maladie, plan relativement populaire dans les essais COVID19. Aussi, la méthodologie proposée est assez générale pour être appliquée dans le contexte d'essais cliniques dont les caractéristiques opérationnelles du plan correspondant ne peuvent pas être obtenues de manière analytique.
RESUMO
Response adaptive randomized clinical trials have gained popularity due to their flexibility for adjusting design components, including arm allocation probabilities, at any point in the trial according to the intermediate results. In the Bayesian framework, allocation probabilities to different treatment arms are commonly defined as functionals of the posterior distributions of parameters of the outcome distribution for each treatment. In a non-conjugate model, however, repeated updates of the posterior distribution can be computationally intensive. In this article, we propose an adaptation of sequential Monte Carlo for efficiently updating the posterior distribution of parameters as new outcomes are observed in a general adaptive trial design. An efficient computational tool facilitates implementation of more flexible designs with more frequent interim looks that can in turn reduce the required sample size and expected number of failures in clinical trials. Moreover, more complex statistical models that reflect realistic modeling assumptions can be used for analysis of trial results.
Assuntos
Pesquisa Biomédica/métodos , Bioestatística/métodos , Modelos Estatísticos , Ensaios Clínicos Controlados Aleatórios como Assunto/métodos , Projetos de Pesquisa , Humanos , Método de Monte CarloRESUMO
In conventional randomized controlled trials, adjustment for baseline values of covariates known to be at least moderately associated with the outcome increases the power of the trial. Recent work has shown a particular benefit for more flexible frequentist designs, such as information adaptive and adaptive multi-arm designs. However, covariate adjustment has not been characterized within the more flexible Bayesian adaptive designs, despite their growing popularity. We focus on a subclass of these which allow for early stopping at an interim analysis given evidence of treatment superiority. We consider both collapsible and non-collapsible estimands and show how to obtain posterior samples of marginal estimands from adjusted analyses. We describe several estimands for three common outcome types. We perform a simulation study to assess the impact of covariate adjustment using a variety of adjustment models in several different scenarios. This is followed by a real-world application of the compared approaches to a COVID-19 trial with a binary endpoint. For all scenarios, it is shown that covariate adjustment increases power and the probability of stopping the trials early, and decreases the expected sample sizes as compared to unadjusted analyses.
Assuntos
Projetos de Pesquisa , Teorema de Bayes , Ensaios Clínicos Controlados Aleatórios como Assunto , Tamanho da Amostra , Simulação por ComputadorRESUMO
Background: Omalizumab is an anti-immunoglobulin E monoclonal antibody used to treat moderate to severe chronic idiopathic urticaria, asthma, and nasal polyps. Recent research suggested that omalizumab may enhance the innate antiviral response and have anti-inflammatory properties. Objective: We aimed to investigate the efficacy and safety of omalizumab in adults hospitalized for coronavirus disease 2019 (COVID-19) pneumonia. Methods: This was a phase II randomized, double blind, placebo-controlled trial comparing omalizumab with placebo (in addition to standard of care) in hospitalized patients with COVID-19. The primary endpoint was the composite of mechanical ventilation and/or death at day 14. Secondary endpoints included all-cause mortality at day 28, time to clinical improvement, and duration of hospitalization. Results: Of 41 patients recruited, 40 were randomized (20 received the study drug and 20 placebo). The median age of the patients was 74 years and 55.0% were male. Omalizumab was associated with a 92.6% posterior probability of a reduction in mechanical ventilation and death on day 14 with an adjusted odds ratio of 0.11 (95% credible interval 0.002-2.05). Omalizumab was also associated with a 75.9% posterior probability of reduced all-cause mortality on day 28 with an adjusted odds ratio of 0.49 (95% credible interval, 0.06-3.90). No statistically significant differences were found for the time to clinical improvement and duration of hospitalization. Numerically fewer adverse events were reported in the omalizumab group and there were no drug-related serious adverse events. Conclusions: These results suggest that omalizumab could prove protective against death and mechanical ventilation in hospitalized patients with COVID-19. This study could also support the development of a phase III trial program investigating the antiviral and anti-inflammatory effect of omalizumab for severe respiratory viral illnesses requiring hospital admission. ClinicalTrials.gov ID: NCT04720612.
RESUMO
INTRODUCTION: In the COVID-19 pandemic, healthcare workers (HCWs) were at high risk of infection due to their exposure to COVID infections. HCWs were the backbone of our healthcare response to this pandemic; every HCW withdrawn or lost due to infection had a substantial impact on our capacity to deliver care. Primary prevention was a key approach to reduce infection. Vitamin D insufficiency is highly prevalent in Canadians and worldwide. Vitamin D supplementation has been shown to significantly decrease the risk of respiratory infections. Whether this risk reduction would apply to COVID-19 infections remained to be determined. This study aimed to determine the impact of high-dose vitamin D supplementation on incidence of laboratory-confirmed COVID-19 infection rate and severity in HCWs working in high COVID incidence areas. METHODS AND ANALYSIS: PROTECT was a triple-blind, placebo-controlled, parallel-group multicentre trial of vitamin D supplementation in HCWs. Participants were randomly allocated in a 1:1 ratio in variable block size to intervention (one oral loading dose of 100 000 IU vitamin D3+10 000 IU weekly vitamin D3) or control (identical placebo loading dose+weekly placebo). The primary outcome was the incidence of laboratory-confirmed COVID-19 infection, documented by RT-qPCR on salivary (or nasopharyngeal) specimens obtained for screening or diagnostic purposes, as well as self-obtained salivary specimens and COVID-19 seroconversion at endpoint. Secondary outcomes included disease severity; duration of COVID-19-related symptoms; COVID-19 seroconversion documented at endpoint; duration of work absenteeism; duration of unemployment support; and adverse health events. The trial was terminated prematurely, due to recruitment difficulty. ETHICS AND DISSEMINATION: This study involves human participants and was approved by the Research Ethics Board (REB) of the Centre hospitalier universitaire (CHU) Sainte-Justine serving as central committee for participating institutions (#MP-21-2021-3044). Participants provided written informed consent to participate in the study before taking part. Results are being disseminated to the medical community via national/international conferences and publications in peer-reviewed journals. TRIAL REGISTRATION NUMBER: https://clinicaltrials.gov/ct2/show/NCT04483635.
Assuntos
COVID-19 , Humanos , SARS-CoV-2 , Pandemias/prevenção & controle , Canadá/epidemiologia , Vitamina D/uso terapêutico , Vitaminas/uso terapêutico , Resultado do Tratamento , Ensaios Clínicos Controlados Aleatórios como Assunto , Estudos Multicêntricos como AssuntoRESUMO
Background: Adaptive designs and platform designs are among two common clinical trial innovations that are increasingly being used to manage medical intervention portfolios and attain faster regulatory approvals. Planning of adaptive and platform trials necessitate simulations to understand how a set of adaptation rules will likely affect the properties of the trial. Clinical trial simulations, however, remain a black box to many clinical trials researchers who are not statisticians. Results: In this article we introduce a simple intuitive open-source browser-based clinical trial simulator for planning adaptive and platform trials. The software application is implemented in RShiny and features a graphical user interface that allows the user to set key clinical trial parameters and explore multiple scenarios such as varying treatment effects, control response and adherence, as well as number of interim looks and adaptation rules. The software provides simulation options for a number of designs such as dropping treatment arms for futility, adding a new treatment arm (i.e., platform design), and stopping a trial early based on superiority. All available adaptations are based on underlying Bayesian probabilities. The software comes with a number of graphical outputs to examine properties of individual simulated trials. The main output is a comparison of trial design performance across several simulations, graphically summarizing type I error (false positive risk), power, and expected cost/time to completion of the considered designs. Conclusion: We have developed and validated an intuitive highly efficient clinical trial simulator for planning of clinical trials. The software is open-source and caters to clinical trial investigators who do not have the statistical capacity for trial simulations available in their team. The software can be accessed via any web browser via the following link: https://mtek.shinyapps.io/hect/.
RESUMO
BACKGROUND: Enrollment of participants to control arms in clinical trials can be challenging. This is particularly an issue in oncology trials where the standard-of-care is shifting rapidly and several promising experimental treatments are undergoing phase III testing. Novel methods for utilizing external control data may mitigate these challenges, but applied examples are sparse. Here, we therefore illustrate how Bayesian dynamic borrowing of external individual patient level control data from similar clinical trials can often reduce randomization to the control intervention without substantially trading-off precision. We further explore which types of scenarios yield viable trade-offs, and which do not. PATIENTS AND METHODS: We obtained individual patient data on patients being treated with second-line therapy for non-small cell lung cancer from Project Data Sphere with minimal in/exclusion criteria restrictions, and applied Bayesian hierarchical models with uninformative priors to generate illustrative synthetic control groups. RESULTS: Four phase III clinical trials were identified and utilized in our analysis. Even when studies which are knowingly incongruent with one another are selected to generate a synthetic control, the nature of this methodology minimizes improper borrowing from historical data. The use of a small concurrent control group within a trial greatly reduces penalized selection, and our results demonstrate the ability to reduce allocation to the control group by up to 80% with a minimal increase in uncertainty when closely matched historical data is available. CONCLUSION: Dynamic borrowing using Bayesian hierarchical models with uninformative priors represents a novel approach to utilizing external controls for comparative estimates using single arm evidence.
RESUMO
BACKGROUND: HIV infection has profound clinical and economic costs at the household level. This is particularly important in low-income settings, where access to additional sources of income or loans may be limited. While several microfinance interventions have been proposed, unconditional cash grants, a strategy to allow participants to choose how to use finances that may improve household security and health, has not previously been evaluated. METHODS: We examined the effect of an unconditional cash transfer to HIV-infected individuals using a 2â×â2 factorial randomized trial in two rural districts in Uganda. Our primary outcomes were changes in CD4 cell count, sexual behaviors, and adherence to ART. Secondary outcomes were changes in household food security and adult mental health. We applied a Bayesian approach for our primary analysis. RESULTS: We randomized 2170 patients as participants, with 1081 receiving a cash grant. We found no important intervention effects on CD4 T-cell counts between groups [mean difference 35.48, 95% credible interval (CrI) -59.9 to 1131.6], food security [odds ratio (OR) 1.22, 95% CrI: 0.47 to 3.02], medication adherence (OR 3.15, 95% CrI: 0.58 to 18.15), or sexual behavior (OR 0.45 95% CrI: 0.12 to 1.55), or health expenditure in the previous 3 weeks (mean difference $2.65, 95% CrI: -9.30 to 15.69). In secondary analysis, we detected an effect of mental planning on CD4 cell count change between groups (104.2 cells, 9% CrI: 5.99 to 202.16). We did not have data on viral load outcomes. CONCLUSION: Although all outcomes were associated with favorable point estimates, our trial did not demonstrate important effects of unconditional cash grants on health outcomes of HIV-positive patients receiving treatment.
Assuntos
Antirretrovirais/uso terapêutico , Características da Família , Organização do Financiamento , Infecções por HIV/tratamento farmacológico , Infecções por HIV/economia , Gastos em Saúde , Adolescente , Adulto , Idoso , Contagem de Linfócito CD4 , Feminino , Humanos , Masculino , Adesão à Medicação , Pessoa de Meia-Idade , Pobreza , População Rural , Comportamento Sexual , Resultado do Tratamento , Uganda , Carga Viral , Adulto JovemRESUMO
Randomized clinical trials (RCT) increasingly investigate combination therapies. Strong biological rationale or early clinical evidence commonly suggest that the effect of the combination treatment is importantly greater than the maximum effect of any of the individual treatments. While these relationships are commonly well-accepted, RCTs do not incorporate them into the design or analysis plans. We therefore propose a simple Bayesian framework for incorporating the known relationships that the effectiveness of a combination treatment exceeds that of any individual treatment, but does not necessarily exceed the sum of individual effects. We term the collation of these two relationships 'fractional additivity'. We performed a binary outcome simulation study of a response adaptive randomized three-arm clinical trial with treatment arms A, B, and A&B that allowed for dropping an inferior treatment arm and terminating the trial early for superiority during any of 4 interim analyses. We compared the Bayesian fractional additivity model to a conventional analysis by measuring the expected proportion of failures, sample size at trial termination, time to termination, and root mean squared error of final estimates. We also compared the fractional additivity model to a 'full additivity' model where the effect of A&B was assumed to be the sum of the effect of A and B. In simulation scenarios where important fractional additivity or full additivity existed, the Bayesian fractional additivity model yielded a 3-4% relative reduction in expected number of failures, and a 30%-50% relative reduction in sample size at trial termination compared to a conventional analysis. These results held true even when the Bayesian fractional additivity model employed a biased prior. The full additivity model had slightly higher gains, but too frequently terminated the trial at the first interim look. In scenarios where no or weak fractional additivity exists, the expected sample size and time to termination were similar for the Bayesian fractional additivity model with a moderately optimistic bias about fractional additivity and the conventional model. Lastly, the fractional additivity model generally yielded similar or lower root mean squared error compared to the other models. In conclusion, our proposed Bayesian fractional additivity model provides an efficient approach for estimating effects of combination treatments in clinical trials. The approach is not only highly applicable in adaptive clinical trials, but also provides added power in a conventional RCT.