Aligning Treatment Policy Estimands and Estimators—A Simulation Study in Alzheimer’s Disease

Estimation of Treatment Policy Estimands for Continuous Outcomes Using Off-Treatment Sequential Multiple Imputation

The estimands framework outlined in ICH E9 (R1) describes the components needed to precisely define the effects to be estimated in clinical trials, which includes how post-baseline 'intercurrent' events (IEs) are to be handled. In late-stage clinical trials, it is common to handle IEs like 'treatment discontinuation' using the treatment policy strategy and target the treatment effect on outcomes regardless of treatment discontinuation. For continuous repeated measures, this type of effect is often estimated using all observed data before and after discontinuation using either a mixed model for repeated measures (MMRM) or multiple imputation (MI) to handle any missing data. In basic form, both these estimation methods ignore treatment discontinuation in the analysis and therefore may be biased if there are differences in patient outcomes after treatment discontinuation compared with patients still assigned to treatment, and missing data being more common for patients who have discontinued treatment. We therefore propose and evaluate a set of MI models that can accommodate differences between outcomes before and after treatment discontinuation. The models are evaluated in the context of planning a Phase 3 trial for a respiratory disease. We show that analyses ignoring treatment discontinuation can introduce substantial bias and can sometimes underestimate variability. We also show that some of the MI models proposed can successfully correct the bias, but inevitably lead to increases in variance. We conclude that some of the proposed MI models are preferable to the traditional analysis ignoring treatment discontinuation, but the precise choice of MI model will likely depend on the trial design, disease of interest and amount of observed and missing data following treatment discontinuation.

Handling Partially Observed Trial Data After Treatment Withdrawal: Introducing Retrieved Dropout Reference-Base Centred Multiple Imputation

The ICH E9(R1) Addendum (International Council for Harmonization 2019) suggests treatment-policy as one of several strategies for addressing intercurrent events such as treatment withdrawal when defining an estimand. This strategy requires the monitoring of patients and collection of primary outcome data following termination of randomised treatment. However, when patients withdraw from a study early before completion this creates true missing data complicating the analysis. One possible way forward uses multiple imputation to replace the missing data based on a model for outcome on- and off-treatment prior to study withdrawal, often referred to as retrieved dropout multiple imputation. This article introduces a novel approach to parameterising this imputation model so that those parameters which may be difficult to estimate have mildly informative Bayesian priors applied during the imputation stage. A core reference-based model is combined with a retrieved dropout compliance model, using both on- and off-treatment data, to form an extended model for the purposes of imputation. This alleviates the problem of specifying a complex set of analysis rules to accommodate situations where parameters which influence the estimated value are not estimable, or are poorly estimated leading to unrealistically large standard errors in the resulting analysis. We refer to this new approach as retrieved dropout reference-base centred multiple imputation.

Estimands in CNS trials - A review of strategies for addressing intercurrent events

Background

The estimands framework represents a significant innovation for the design, conduct, analysis, and interpretation of clinical trials. An aim of the framework is to increase precision and transparency on the handling of intercurrent events (IEs), defined as events occurring after treatment initiation and affecting the endpoint. While the experience in constructing and reporting estimands in the published literature is limited, developers performing confirmatory studies are already making use of the new paradigm, allowing to survey the strategies proposed by applicants and endorsed by regulators.

Methods

To identify strategies for handling IEs in confirmatory central nervous system (CNS) trials, we searched scientific advice letters issued by the European Medicines Agency (EMA) between 2017 and 2022. We developed a categorisation of the IEs and classified, according to the strategies defined in the framework, the strategies proposed by the Applicants and recommended by the agency. Strategies proposed and recommended were summarised by category of IEs, and the rationale for the choices was analysed qualitatively.

Results

In total, 170 IEs were identified in 52 confirmatory trials. A clear preference for the treatment policy strategy for treatment discontinuation and for the hypothetical strategy for pandemic-related disruptions was identified. For other categories of IEs, there are more mixed patterns.

Discussion

This study highlights the multidimensional nature of choosing a strategy for an IE. For different occurring IEs in confirmatory CNS trials different strategies are of regulatory interest, depending on the trial objective, underlying disease properties, rarity of disease, as well as frequency and timing of IEs and their relatedness to the disease.

Defining Clinical Trial Estimands: A Practical Guide for Study Teams with Examples Based on a Psychiatric Disorder

While the ICH E9(R1) Addendum on "Estimands and Sensitivity Analysis in Clinical Trials" was released in late 2019, the widespread implementation of defining and reporting estimands across clinical trials is still in progress and the engagement of non-statistical functions in this process is also in progress. Case studies are sought after, especially those with documented clinical and regulatory feedback. This paper describes an interdisciplinary process for implementing the estimand framework, devised by the Estimands and Missing Data Working Group (a group with clinical, statistical, and regulatory representation) of the International Society for CNS Clinical Trials and Methodology. This process is illustrated by specific examples using various types of hypothetical trials evaluating a treatment for major depressive disorder. Each of the estimand examples follows the same template and features all steps of the proposed process, including identifying the trial stakeholder(s), the decisions they need to make about the investigated treatment in their specific role and the questions that would support their decision making. Each of the five strategies for handling intercurrent events are addressed in at least one example; the featured endpoints are also diverse, including continuous, binary and time to event. Several examples are presented that include specifications for a potential trial design, key trial implementation elements needed to address the estimand, and main and sensitivity estimator specifications. Ultimately this paper highlights the need to incorporate multi-disciplinary collaborations into implementing the ICH E9(R1) framework.

Natural cubic splines for the analysis of Alzheimer's clinical trials

Mixed model repeated measures (MMRM) is the most common analysis approach used in clinical trials for Alzheimer's disease and other progressive diseases measured with continuous outcomes over time. The model treats time as a categorical variable, which allows an unconstrained estimate of the mean for each study visit in each randomized group. Categorizing time in this way can be problematic when assessments occur off-schedule, as including off-schedule visits can induce bias, and excluding them ignores valuable information and violates the intention to treat principle. This problem has been exacerbated by clinical trial visits which have been delayed due to the COVID19 pandemic. As an alternative to MMRM, we propose a constrained longitudinal data analysis with natural cubic splines that treats time as continuous and uses test version effects to model the mean over time. Compared to categorical-time models like MMRM and models that assume a proportional treatment effect, the spline model is shown to be more parsimonious and precise in real clinical trial datasets, and has better power and Type I error in a variety of simulation scenarios.

An online program with individualized vs automated support for significant others of depressed individuals - study protocol of a randomized controlled trial

BACKGROUND

Due to budget restrictions in mental health care, non-professional caregivers are increasingly burdened with the emotional and practical care for their depressed relatives. However, informal family caregiving is mostly a stressful role with negative consequences on the physical and mental health of the caretakers to the extent that they have an elevated risk of experiencing psychiatric disorders themselves. While psychoeducation for relatives of depressed individuals showed positive results both in terms of the caretakers' strain and the depressive symptoms of the affected person, there are major barriers to participate in presence in those programs. Digital programs might be a viable alternative. We found no empirically evaluated digital program available for informal caregivers of depressed patients.

METHODS

An online program for relatives of depressed individuals has been developed including four interactive modules on 1) psychoeducation, 2) how to strengthen the relationship with the depressed person, 3) how to deal with the depressive symptoms of the patient, and 4) find the right balance between caring for the depressed person and self-care. We investigate if this self-help program is more effective when used with individualized versus automated e-mail support, and if both supported conditions are more effective than treatment-as-usual (TAU in form of written information material) in terms of the risk of mental diseases in caregivers. The primary outcome is the reduction of the caregiver's nonspecific mental distress as measured by the change of the Kessler Psychological Distress Scale score from baseline to four weeks after randomization. Caregivers (n = 500:500:250) will be randomized to one of the three conditions.

DISCUSSION

Psychological support for caregivers of individuals with mental disorders such as depression should be offered as part of integrated services. There is a huge potential to develop and implement interactive online approaches to support informal caregivers of patients with depression to function in their multiple roles and to help them to remain healthy.

TRIAL REGISTRATION

DRKS, DRKS00025241 . Registered 5 Mai 2021.

Marking 2-Years of New Thinking in Clinical Trials: The Estimand Journey

The ICH E9(R1) addendum on Estimands and Sensitivity Analyses in Clinical Trials has introduced a new estimand framework for the design, conduct, analysis, and interpretation of clinical trials. We share Pharmaceutical Industry experiences of implementing the estimand framework in the first two years since the final guidance became available with key lessons learned and highlight what else needs to be done to continue the journey in embedding the estimand framework in clinical trials. Emerging best practices and points to consider on strategies for implementing a new estimand thinking process are provided. Whilst much of the focus of implementing ICH E9(R1) to date has been on defining estimands, we highlight some of the important aspects relating to the choice of statistical analysis methods and sensitivity analyses to ensure estimands can be estimated robustly with minimal bias. In particular, we discuss the implications if complete follow-up is not possible when the treatment policy strategy is being used to handle intercurrent events. ICH E9(R1) was introduced just before the start of the COVID-19 pandemic, but a positive outcome from the pandemic has been an acceleration in the adoption of the estimand framework, including differentiating intercurrent events related or not related to the pandemic. In summary, much has been learned on the estimand journey and continued sharing of case studies will help to further advance the understanding and increase awareness across all clinical researchers of the estimand framework.

Estimation of a treatment policy estimand for time to event data using data collected post discontinuation of randomised treatment

Discontinuation from randomised treatment is a common intercurrent event in clinical trials. When the target estimand uses a treatment policy strategy to deal with this intercurrent event, data after cessation of treatment is relevant to estimate the estimand and all efforts should be made to collect such data. Missing data may nevertheless occur due to participants withdrawing from the study and assumptions regarding the values for data that are missing are required for estimation. A missing-at-random assumption is commonly made in this setting, but it may not always be viewed as appropriate. Another potential approach is to assume missing values are similar to data collected after treatment discontinuation. This idea has been previously proposed in the context of recurrent event data. Here we extend this approach to time-to-event outcomes using the hazard function. We propose imputation models that allow for different hazard rates before and after treatment discontinuation and use the posttreatment discontinuation hazard to impute events for participants with missing follow-up periods due to study withdrawal. The imputation models are fitted as Andersen-Gill models. We illustrate the proposed methods with an example of a clinical trial in patients with chronic obstructive pulmonary disease.

Standard and reference-based conditional mean imputation

Clinical trials with longitudinal outcomes typically include missing data due to missed assessments or structural missingness of outcomes after intercurrent events handled with a hypothetical strategy. Approaches based on Bayesian random multiple imputation and Rubin's rules for pooling results across multiple imputed data sets are increasingly used in order to align the analysis of these trials with the targeted estimand. We propose and justify deterministic conditional mean imputation combined with the jackknife for inference as an alternative approach. The method is applicable to imputations under a missing-at-random assumption as well as for reference-based imputation approaches. In an application and a simulation study, we demonstrate that it provides consistent treatment effect estimates with the Bayesian approach and reliable frequentist inference with accurate standard error estimation and type I error control. A further advantage of the method is that it does not rely on random sampling and is therefore replicable and unaffected by Monte Carlo error.