Applying the Principal Stratum Strategy in Equivalence Trials: A Case Study.

In the context of clinical trials, there is interest in the treatment effect for subpopulations of patients defined by intercurrent events, namely disease-related events occurring after treatment initiation that affect either the interpretation or the existence of endpoints. With the principal stratum strategy, the ICH E9(R1) guideline introduces a formal framework in drug development for defining treatment effects in such subpopulations. Statistical estimation of the treatment effect can be performed based on the principal ignorability assumption using multiple imputation approaches. Principal ignorability is a conditional independence assumption that cannot be directly verified; therefore, it is crucial to evaluate the robustness of results to deviations from this assumption. As a sensitivity analysis, we propose a joint model that multiply imputes the principal stratum membership and the outcome variable while allowing different levels of violation of the principal ignorability assumption. We illustrate with a simulation study that the joint imputation model-based approaches are superior to naive subpopulation analyses. Motivated by an oncology clinical trial, we implement the sensitivity analysis on a time-to-event outcome to assess the treatment effect in the subpopulation of patients who discontinued due to adverse events using a synthetic dataset. Finally, we explore the potential usage and provide interpretation of such analyses in clinical settings, as well as possible extension of such models in more general cases.

A randomized trial allows estimation of the causal effect of an intervention compared to a control in the overall population and in subpopulations defined by baseline characteristics. Often, however, clinical questions also arise regarding the treatment effect in subpopulations of patients, which would experience clinical or disease related events post-randomization. Events that occur after treatment initiation and potentially affect the interpretation or the existence of the measurements are called intercurrent events in the ICH E9(R1) guideline. If the intercurrent event is a consequence of treatment, randomization alone is no longer sufficient to meaningfully estimate the treatment effect. Analyses comparing the subgroups of patients without the intercurrent events for intervention and control will not estimate a causal effect. This is well known, but post-hoc analyses of this kind are commonly performed in drug development. An alternative approach is the principal stratum strategy, which classifies subjects according to their potential occurrence of an intercurrent event on both study arms. We illustrate with examples that questions formulated through principal strata occur naturally in drug development and argue that approaching these questions with the ICH E9(R1) estimand framework has the potential to lead to more transparent assumptions as well as more adequate analyses and conclusions. In addition, we provide an overview of assumptions required for estimation of effects in principal strata. Most of these assumptions are unverifiable and should hence be based on solid scientific understanding. Sensitivity analyses are needed to assess robustness of conclusions.

BackgroundThe Estimands framework, introduced in the Addendum to ICH E9, provides a structured method to define treatment effects in clinical trials. The main novelty of the framework is the discussion of intercurrent events as part of the treatment effect definition. It is widely believed that the application of the framework to non-inferiority and equivalence trials deserves specific consideration.MethodsTo examine the current practices of using the estimand framework in non-inferiority and equivalence trials, we reviewed the scientific advice provided by the European Medicines Agency to drug developers in 2022. This review aimed to determine how often the estimands framework is used by drug developers and/or recommended by EMA and to describe what intercurrent events and handling strategies are being proposed by drug developers and recommended by EMA.ResultsThe use of the framework varied substantially by clinical development phases. While it was used for phase 3 trials in 47% (25/53) by developers, it was used in 5% (1/19) of the phase 1 trials. For 39% (11/28) of the trials where developers did not use the estimands framework in phase 3, there was no regulatory recommendation to adopt the framework in the response. The most discussed intercurrent event in our sample was ‘treatment discontinuation’ (n = 47), for which developers most often proposed either a treatment policy strategy (17/47, 36%) or a hypothetical strategy (11/47, 23%). In contrast, EMA most often recommended the use of two co-primary estimands with two different strategies (22/47, 47%).ConclusionsGenerally, the proposed and recommended strategies depend on the clinical setting and the respective intercurrent event. Developers almost always proposed a single primary estimand, whereas EMA often recommended two co-primary estimands differing in the strategies used to handle some or all the intercurrent events. Further interaction between academia, industry and regulators is necessary to progress the implementation process of the estimands framework for non-inferiority and equivalence trials.Supplementary InformationThe online version contains supplementary material available at 10.1186/s13063-025-09068-2.

BackgroundPublished in 2019, a new addendum to the ICH E9 guideline presents the estimand framework as a systematic approach to ensure alignment among clinical trial objectives, trial execution/conduct, statistical analyses, and interpretation of results. The use of the estimand framework for describing clinical trial objectives has yet to be extensively considered in the context of patient-reported outcomes (PROs). We discuss the application of the estimand framework to PRO objectives when designing clinical trials in the future, with a focus on PRO outcomes in oncology trial settings as our example.MainWe describe the components of an estimand and take a naïve PRO trial objective to illustrate how to apply attributes described in the estimand framework to inform construction of a detailed clinical trial objective and its related estimand. We discuss identifying potential post-randomization events that alter the interpretation of the endpoint or render its observation impossible (also defined as intercurrent events) in the context of PRO endpoints, and the implications of how to handle intercurrent events in the construction of the PRO objective. Using a simple objective statement, “What is the effect of treatment X on patient’s quality of life?”, we build up an example estimand statement and also use a previously published phase III oncology clinical trial to illustrate how an estimand for a PRO objective could have been written to align to the estimate framework.ConclusionThe use of the estimand framework, as described in the new ICH E9 (R1) addendum guideline will become a key common framework for developing clinical trial objectives for evaluating effects of treatment. In the context of considering PROs, the framework provides an opportunity to more precisely specify and build the rationale for patient-focused objectives. This will help to ensure that clinical trials used for registration are designed and analysed appropriately, enabling all stakeholders to accurately interpret conclusions about the treatment effects for patient-focused outcomes.

We consider three (strong, moderate and mild) predictive biomarker scenarios with varying prevalence. As such, there is no treatment effect in the biomarker negative (g −) patient subpopulation. Relative to g −, there is a four-fold profound treatment effect in the biomarker positive (g +) patient subpopulation, a strongly predictive scenario; a three-fold large g + subpopulation treatment effect, a moderately predictive scenario; and a two-fold modest g + subpopulation treatment effect, a mildly predictive scenario. In this paper, we focus on binary endpoint in prescribing treatment effect. Using a Breiman’s (Mach. Learn. 24:123–140, 1996) machine learning voting algorithm via a k-fold cross-validated approach applied by Freidlin et al. (Clin. Cancer Res. 16:691–698, 2010), a predictive biomarker may be developed. We consider development or discovery of a genomic biomarker using microarray gene expressions data in randomized controlled trials and validate the biomarker’s predictive performance in an independent data set. We investigate the classification performance characteristics of a binary genomic composite biomarker (expected to be predictive of treatment effects) including sensitivity, specificity, accuracy, positive predictive value and negative predictive value as a function of true sensitive prevalence. In doing so, we report the finding based on three representative tuning parameter sets with varying degree of rigor in their choices of the parameters ranging from highly rigorous, moderately rigorous to mildly rigorous. We articulate the rationales on the choices of tuning parameter sets. We also study the impacts of misclassification of genomic biomarker classifiers on their assessment of treatment effects in the positive and negative patient subpopulations, and all-comer patients. We elucidate via simulation studies on approaches to improve sensitivity when a biomarker is highly specific but poorly sensitive, a scenario that is most likely to lead to an incorrect test conclusion of an applicable significant treatment effect in a specific patient subpopulation or both positive and negative subpopulations. We explore when it will be beneficial to develop a binary predictive biomarker and conclude that hypothesis test inferences for the g + subpopulation treatment effect in the dual hypotheses setting (all-comer and g + alone) cannot be relied upon if the biomarker classifier is only highly specific and poorly sensitive or resulting in poor negative predictive value. The converse dual hypotheses (all-comer and g − alone) have the same concern, viz. highly sensitive and poorly specific or resulting in poor positive predictive value. In addition, we compare the predictive performance of a biomarker classifier between use of direct selection and selection from a candidate pool shedding favorable lights of direct selection approach where biological or mechanistic plausibility can be relied upon. Further research is needed if accurate classifier is required irrespective of prevalence level.

BackgroundPatient-reported outcomes (PROs) play an increasing role in the evaluation of oncology treatments. At the same time, single-arm trials are commonly included in regulatory approval submissions. Because of the high risk of biases, results from single-arm trials require careful interpretation. This benefits from a clearly defined estimand, or target of estimation. In this case study, we demonstrated how the ICH E9 (R1) estimand framework can be implemented in SATs with PRO endpoints.MethodsFor the global quality of life outcome in a real single-arm lung cancer trial, a range of possible estimands was defined. We focused on the choice of the variable of interest and strategies to deal with intercurrent events (death, treatment discontinuation and disease progression). Statistical methods were described for each estimand and the corresponding results on the trial data were shown.ResultsEach intercurrent event handling strategy resulted in its own estimated mean global quality of life over time, with a specific interpretation, suitable for a corresponding clinical research aim. In the setting of this case study, a ‘while alive’ strategy for death and a ‘treatment policy’ strategy for non-terminal intercurrent events were deemed aligned with a descriptive research aim to inform clinicians and patients about expected quality of life after the start of treatment.ConclusionsThe results show that decisions made in the estimand framework are not trivial. Trial results and their interpretation strongly depend on the chosen estimand. The estimand framework provides a structure to match a research question with a clear target of estimation, supporting specific clinical decisions. Adherence to this framework can help improve the quality of data collection, analysis and reporting of PROs in SATs, impacting decision making in clinical practice.

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.

Background/Aims:Randomised clinical trials assessing treatment effects on health outcomes (e.g. quality of life) can be affected by data truncation by death, where some patients die before their outcome measure is assessed and their data become undefined after death. The ICH E9(R1) addendum on estimands discusses four strategies for handling such terminal intercurrent events: hypothetical, composite, while-alive, and principal stratum. While the addendum emphasises the importance of aligning statistical methods of analysis (i.e. estimators) with estimands, it does not provide specific guidance and consideration on the choice of estimators in practice. We aim to (1) demonstrate how some statistical methods commonly used in trials can be used to estimate different intercurrent event strategies for handling data truncation by death; and (2) describe how missing outcome data (e.g. due to missed assessments or loss to follow-up) can be handled for each estimator.Method:We use data from SCORAD, a non-inferiority randomised trial comparing single-fraction versus multifraction radiotherapy on ambulatory status at 8 weeks (primary outcome) among patients with spinal canal compression from metastatic cancer. Here, we estimate the effect of radiotherapy on quality of life (secondary outcome), quantified by the difference in mean global health status between the two groups at 8 weeks. We outline the strategies for handling death and describe a selection of commonly used estimators corresponding to each strategy. The handling of missing data is considered and demonstrated as part of the estimation process.Results:The hypothetical strategy, targeting a treatment effect assuming patients had not died, can be estimated using linear mixed models (a likelihood approach) or multiple imputation (a method commonly used for handling missing data). The composite and while-alive strategies relate to the ‘outcome’ attribute of the estimand; the former incorporates death into the definition of the primary outcome, the latter only uses outcome data before death. These can be estimated by re-defining the outcome, for example, assigning a value reflecting poor global health status post-death, or using the last global health status observed before death. The principal stratum strategy, targeting a treatment effect among patients who would not die under either treatment, can be estimated by an analysis of survivors under specific assumptions. Missing data can be handled with linear mixed models or multiple imputation.Conclusions:Regarding death as an intercurrent event in the process of defining the estimand for the trial will help clarify the choice of suitable estimators. When choosing the estimators, it is important to consider the assumptions required by the estimators as well as their plausibility given the setting of the trial.

Time-to-event endpoints, such as progression free survival (PFS) and overall survival (OS), are critical in assessing therapeutic efficacy in oncology drug development. However, their quality and interpretability are frequently challenged by a range of factors, from protocol design and intercurrent events (ICE) to inconsistent data collection and missing follow-up data. These methodological and operational complexities can obscure the true treatment effect. Discontinuation of study treatment, initiation of subsequent anticancer therapy, lost to follow-up and withdrawal of consent can introduce significant bias, limiting the robustness of survival endpoints and complicating regulatory decision making. Adopting a prospective ICH E9(R1) estimand framework helps mitigate risks associated with data collection, analysis methodology and interpretability. This facilitates clearer discussions with regulators and stakeholders. Although both the FDA guidance on oncology endpoints and the EMA guideline on anticancer medicinal product evaluation outline key principles in evaluating PFS and OS endpoints, integration of ICH E9(R1) offers a harmonized strategy that is important for the design and conduct of randomized late phase oncology clinical trials. In this article, we investigate the quality and interpretability of the endpoints of PFS and OS according to the ICH E9(R1) framework and present some practical recommendations for designing and conducting robust oncology clinical trials.

The estimand framework as defined by the ICH E9(R1) addendum aims to clearly define “the treatment effect reflecting the clinical question posed by the trial objective”. It intends to achieve this goal of a clear definition by specifying the 5 estimand attributes: treatment conditions, population, endpoints, handling of intercurrent events (IEs), and population-level summary. However, hybrid clinical/observational research like External Comparators (ECs) leads to new reflections on existing attributes and to considerations for additional ones. Specifically, treatment conditions and exposure may be more difficult to handle in the EC, and especially Standard of Care (SoC) treatment needs detailed attention. The external population typically cannot be based on the classical Intention-to-treat population and constitutes also an approximation only. Endpoints may not be comparable across cohorts, and IEs may be more different than in an RCT setting, such that the hypothetical treatment policy according to the ICH E9(R1) addendum may become of greater interest especially for long-term endpoints. Finally, the necessary assumptions for some population-level summaries (e.g., the proportional hazards assumption) can become more fragile when joining data from different sources due to induced heterogeneity. Finally, it is shown that the baseline definition and the marginal estimator are candidates for additional estimand attributes in case the estimand framework is revised to account for observational study needs.

BackgroundPhase 3 randomized clinical trials within Alzheimer’s Disease (AD) typically last over 18 months. Post‐baseline participants can use additional treatment for Alzheimer’s disease, potentially impacting the cognitive ability as evaluated by the primary endpoint. Consequently, this could overestimate or underestimate the treatment effect, depending on the distribution of usage between treatment arms.MethodThe ICH E9 (R1) addendum’s estimand framework provide a means of precisely defining the clinical question of interest, in particular detailing how intercurrent events such as ‘use of additional AD medication’ should be handled and how to interpret the estimated treatment effect. Donohue et al (2020) suggested to use a treatment policy strategy for initiation of symptomatic treatments, based on the observation that placebo subjects did not experience an improvement after initiation of symptomatic treatment. The EMA guideline for Alzheimer’s disease (2018), recommends using a hypothetical strategy for initiation of symptomatic treatment.ResultUse of additional AD medication will qualify as an intercurrent event only as long as the medication is considered to have an effect. Symptomatic AD medication is assumed to have no effect when the patient is no longer exposed. Therefore, we suggest to allow for the intercurrent event ‘use of additional AD medication’ to have both a start and a stop date, and, when applying a hypothetical strategy, only measurements that are considered affected by the intercurrent event will be substituted by outcomes corresponding to the hypothetical scenario were additional AD medication has not been initiated.ConclusionUsing estimands clarifies the interpretation of treatment effects in clinical trials allowing usage of additional AD medication.

Background/aimsTuberculosis remains one of the leading causes of death from an infectious disease globally. Both choices of outcome definitions and approaches to handling events happening post-randomisation can change the treatment effect being estimated, but these are often inconsistently described, thus inhibiting clear interpretation and comparison across trials.MethodsStarting from the ICH E9(R1) addendum’s definition of an estimand, we use our experience of conducting large Phase III tuberculosis treatment trials and our understanding of the estimand framework to identify the key decisions regarding how different event types are handled in the primary outcome definition, and the important points that should be considered in making such decisions. A key issue is the handling of intercurrent (i.e. post-randomisation) events (ICEs) which affect interpretation of or preclude measurement of the intended final outcome. We consider common ICEs including treatment changes and treatment extension, poor adherence to randomised treatment, re-infection with a new strain of tuberculosis which is different from the original infection, and death. We use two completed tuberculosis trials (REMoxTB and STREAM Stage 1) as illustrative examples. These trials tested non-inferiority of new tuberculosis treatment regimens versus a control regimen. The primary outcome was a binary composite endpoint, ‘favourable’ or ‘unfavourable’, which was constructed from several components.ResultsWe propose the following improvements in handling the above-mentioned ICEs and loss to follow-up (a post-randomisation event that is not in itself an ICE). First, changes to allocated regimens should not necessarily be viewed as an unfavourable outcome; from the patient perspective, the potential harms associated with a change in the regimen should instead be directly quantified. Second, handling poor adherence to randomised treatment using a per-protocol analysis does not necessarily target a clear estimand; instead, it would be desirable to develop ways to estimate the treatment effects more relevant to programmatic settings. Third, re-infection with a new strain of tuberculosis could be handled with different strategies, depending on whether the outcome of interest is the ability to attain culture negativity from infection with any strain of tuberculosis, or specifically the presenting strain of tuberculosis. Fourth, where possible, death could be separated into tuberculosis-related and non-tuberculosis-related and handled using appropriate strategies. Finally, although some losses to follow-up would result in early treatment discontinuation, patients lost to follow-up before the end of the trial should not always be classified as having an unfavourable outcome. Instead, loss to follow-up should be separated from not completing the treatment, which is an ICE and may be considered as an unfavourable outcome.ConclusionThe estimand framework clarifies many issues in tuberculosis trials but also challenges trialists to justify and improve their outcome definitions. Future trialists should consider all the above points in defining their outcomes.

Strategy is the art of using the existing skills and resources of an organization to achieve its goals through effective relationships with the environment in the most favorable conditions. In building a culture of quality and competitiveness, the principal is a leader who has an important role. Principals must have a serious attitude and a high work ethic so that they can produce mature strategies. The strategy aims to make change truly materialized by the birth of new innovations that have an impact on improving the quality and competitiveness of education in schools.The focus of this research is 1) how is the principal's strategic planning in improving the quality culture and school competitiveness at SMA Brawijaya Smart School Malang? 2) how is the implementation of the principal's strategy in improving the quality culture and school competitiveness in SMA Brawijaya Smart School Malang? 3) how are the results of the principal's strategy in improving the quality culture and school competitiveness at SMA Brawijaya Smart School Malang?The research method used is a qualitative research method with a case study approach. Qualitative research is a form of research in which data is collected and analyzed in the field to draw conclusions. The case study approach is intended to describe an in-depth study of how the principal's strategy in improving the quality culture and school competitiveness at SMA Brawijaya Smart School Malang.This study shows the results that: 1) Principal's Strategic Planning in Improving Quality Culture and School Competitiveness at SMA Brawijaya Smart School Malang, namely: a) The principal's plan or strategy is realized in the form of self-planning and strategic plan in accordance with the vision, mission, and school goals. b) Decisions on the strategic plan are taken through a meeting together with the deputy head which is held once a week, the principal holds a meeting with the vice principal and together with the teacher through an official meeting which is held once a month. b) Planning in quality culture applied in SMA Brawijaya Smart School Malang is SMART quality culture. c) Plan for school competitiveness by providing excellent service, improving teacher and employee performance, and implementing superior programs. 2) Implementation of the Principal's Strategy in Improving the Quality Culture and School Competitiveness, namely: a) The principal tries to facilitate the talents and interests of students through the procurement of superior programs and provides 16 kinds of extracurricular activities. b) Improving superior programs that are always improved, providing quality teachers, providing optimal educational support facilities, very strategic school locations, and making schools that are directly proportional to price and service. c) Teachers and education staff provide a lot of information and are open to parents and the community. 3) The results of the principal's strategy in improving the quality culture and school competitiveness are that: a) there are several obstacles in the leadership of the principal but the principal tries to evaluate it through meetings with the vice principal as well as teachers and staff. b) Successfully won various competitions, ranging from academic to non-academic. c) Ranked 13th based on LTMPT with the highest average UTBK score that competes with other public/private SMA/MA in Malang city, thus making SMA Brawijaya Smart School Malang as one of the favorite private schools in Malang City.

Over the past decades, the primary interest in vaccine efficacy evaluation has mostly been on the effect observed in trial participants complying with the protocol requirements (per protocol analysis). The ICH E9 (R1) addendum provides a structured framework to formulate the clinical questions of interest and formalize them as estimands. In this paper, the estimand framework is retrospectively implemented in a human papillomavirus (HPV) phase 3 trial, where the vaccine efficacy was originally estimated on the per protocol set. We focus on two strategies for dealing with the presence of intercurrent events: the hypothetical and the principal stratum strategies. We address the interpretation of these two estimands, their estimation as well as articulation of the underlying identifiability assumptions. Finally, we leverage the results of the HPV application to formulate general considerations regarding the implementation of the ICH E9 (R1) addendum in vaccine efficacy studies.

Missing data are not intercurrent events; missing data are consequences of intercurrent events. When planning clinical trials with potential missing data, a conventional approach is two stage: (1) to calculate a required sample size N without considering missing data; (2) to adjust the sample size using [Formula: see text], where r is the expected missing data rate. However, this approach is not estimand oriented. Clinical trial design should be aligned with estimand. Sample size calculation is a key step in clinical trial design, so methods for sample size calculation should be aligned with estimand. ICH E9(R1) summarizes five strategies for dealing with intercurrent events. We consider five basic approaches for sample size calculation when planning clinical trials with intercurrent events, with each approach aligned with one of these five strategies. We extend the approaches to scenarios where some combination of multiple strategies is applied to deal with intercurrent events. Being aligned with estimands and strategies for dealing with intercurrent events, these methods can be used for sample size calculations when planning clinical trials with intercurrent events.