Pharmaceutical Statistics最新文献

{"title":"Use of Composite Priors for Assurance of Sequential Therapy Trials: Practical Experiences Using Binary Endpoint Data.","authors":"Jonathan Wright, Li Ye","doi":"10.1002/pst.70125","DOIUrl":"10.1002/pst.70125","url":null,"abstract":"<p><p>Accurately calculating assurance can play an important role in quantifying the confidence in the success of a clinical trial. Formulation of prior distributions and the use of assurance can therefore play a vital part in drug development planning and decision-making. Although approaches in developing priors and calculating probability of success (assurance) have been readily reported, the application for studies incorporating sequential treatment therapy-where multiple medications or therapeutic regimens are administered consecutively to maximise therapeutic efficacy and minimise adverse effects-is less well defined. Challenges relating to eliciting a prior for a single treatment effect across a sequential therapy include reliance on individual experts' subjective beliefs about translating multiple mechanisms of actions into a single overall treatment effect and the inability to capture nuances across and inconsistency in combining individual treatment component effects. In this paper, we outline a comprehensive quantitative framework for developing a composite prior distribution (from individual component priors) and calculating the assurance for study designs involving sequential treatment. We demonstrate how this framework, which employs both prior elicitation and data-driven prior development methods, was applied in two phase 2 study designs with sequential treatment regimens using a binary endpoint. We also discuss the optimal conditions for these methods and compare the benefits and challenges with a conventional holistic prior elicitation and assurance framework.</p>","PeriodicalId":19934,"journal":{"name":"Pharmaceutical Statistics","volume":"25 5","pages":"e70125"},"PeriodicalIF":1.5,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13571898/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148963351","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Applying the Promising Zone Method to Biomarker-Based Adaptive Designs: A Word of Caution.","authors":"Jingzhao Wang, Ruobing Li, Jun Zhao, Zhimin Tang, Jianhong Pan","doi":"10.1002/pst.70118","DOIUrl":"10.1002/pst.70118","url":null,"abstract":"<p><p>Sample size re-estimation based on interim data has become an increasingly important component of adaptive clinical trial designs. Many novel anti-cancer therapies under development demonstrate enhanced efficacy in biomarker-defined subpopulations rather than the overall population. To address the inherent uncertainty in the predictive value of biomarkers, biomarker-based adaptive designs have gained considerable interest. Given the complexity of these designs, it is critical to evaluate whether existing sample size re-estimation methods maintain adequate control of the overall Type I error rate. In this paper, we focus on the promising zone method applied within biomarker-based adaptive designs. We show that the promising zone method can produce Type I error inflation when embedded in biomarker-based adaptive designs, with the magnitude of inflation depending on the underlying true treatment effect in the biomarker-positive subgroup and specific design parameters such as the biomarker subgroup prevalence, the interim analysis timing, and the maximum inflation factor. We derive exact analytical results for normally distributed endpoints and extend these findings to time-to-event (TTE) endpoints through the asymptotic normal approximation of the log-rank test statistic, with the conclusions supported by simulation studies. We also discuss regulatory considerations for the implementation of such complex adaptive designs in confirmatory settings.</p>","PeriodicalId":19934,"journal":{"name":"Pharmaceutical Statistics","volume":"25 5","pages":"e70118"},"PeriodicalIF":1.5,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13562987/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148930646","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Robustness of the Pairwise-Fitting Approach Under Missing at Random Dropout: A Case and Simulation Study.","authors":"Dries De Witte, Geert Verbeke, Thomas Neyens, Ariel Alonso Abad, Geert Molenberghs","doi":"10.1002/pst.70115","DOIUrl":"10.1002/pst.70115","url":null,"abstract":"<p><p>In many studies, multiple longitudinal outcomes are collected, and interest lies in studying the association between these outcomes. Joint modeling is then required, but full likelihood estimation becomes infeasible as the number of outcomes increases. To address this, the pairwise-fitting approach was developed. However, the robustness of this pseudo-likelihood-based approach under missing at random (MAR) remains unclear. We investigate the impact of MAR dropout on the pairwise-fitting approach through a case and simulation study and compare the results to full likelihood estimation. In the simulation study, we simulate three continuous longitudinal outcomes so that full likelihood estimation remains computationally feasible, allowing a comparison with the pairwise fitting approach. Various settings are examined, including random intercept and random intercept-and-slope models, in which we vary the standard deviation of the error terms and the degree of correlation between random effects. Our results show that bias remains limited in random intercept models and in most random intercept-and-slope models. However, when the standard deviation of the error terms becomes large compared to that of the random effects, some bias appears in the covariances between the random effects of the outcomes not driving dropout. This bias is mitigated using multiple imputation. As a case study, we analyzed data from a schizophrenia study using both full likelihood and pseudo-likelihood approaches and compared the results.</p>","PeriodicalId":19934,"journal":{"name":"Pharmaceutical Statistics","volume":"25 5","pages":"e70115"},"PeriodicalIF":1.5,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13524844/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148851109","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hierarchical Composite Endpoints for Dose Optimization in Early Phase Oncology Trials.","authors":"Yuxiang Wu, Xiaohan Guo, Ray Li, Christophe Le Corre","doi":"10.1002/pst.70123","DOIUrl":"10.1002/pst.70123","url":null,"abstract":"<p><p>The FDA-initiated Project Optimus has emphasized the need for dose optimization (DO) in oncology drug development, moving beyond the traditional maximum tolerated dose paradigm. Evaluating the balance of benefit and risk is central to DO. In this paper, we propose a novel benefit-risk assessment framework for DO in early-phase oncology trials, utilizing hierarchical composite endpoints (HCEs). The HCE approach enables integration of multiple endpoints within a clinically prioritized hierarchy. Generalized pairwise comparison is then used to compare patient outcomes across candidate dose levels in DO cohorts, providing interpretable metrics to guide dose selection. Our method addresses key practical challenges of existing methods by enabling straightforward, qualitative clinical inputs and integrating various DO-related evidence. The framework also supports uncertainty quantification and sensitivity analysis to ensure robust assessment. Additionally, we extend the HCE method to incorporate pharmacokinetic data through a probabilistic index model, allowing drug exposure to support dose selection. Extensive simulation studies demonstrate that the proposed method achieves superior performance in selecting optimal doses compared to utility-score-based methods, particularly in scenarios requiring careful balancing of efficacy and safety. Application to real-world trial data for DO in HER-2 positive nonsmall cell lung cancer further illustrates the method's practical utility and robustness.</p>","PeriodicalId":19934,"journal":{"name":"Pharmaceutical Statistics","volume":"25 5","pages":"e70123"},"PeriodicalIF":1.5,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13571895/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148963316","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Sample Size Reduction by Applying ML Based Causal Inference Methods.","authors":"Ahrim Youn, Gang Han, Emma Gerard, Neeraj Poonia, Sergio Olmos, Bingzhi Zhang, Meehyung Cho, Andres Houseman","doi":"10.1002/pst.70105","DOIUrl":"10.1002/pst.70105","url":null,"abstract":"<p><p>We conducted a comprehensive comparative analysis of causal machine learning (ML) methods to assess their utility in improving the efficiency of clinical trial designs with or without historical data. Specifically, we compared standard ANCOVA analysis used in a Randomized Controlled Trial (RCT) with several causal ML methods, including PROCOVA, TMLE, DML, and GRF. PROCOVA is gaining popularity in RCT design and requires a historical data for prognostic scores, but other methods can be applied with or without such data. Our primary focus was on strict RCT setting without borrowing historical control data, though we also explored the impact of borrowing data. The historical data used consisted of placebo data from two Phase 3 Ophthalmology studies with a continuous primary endpoint. We employed a generative AI approach, specifically Generative Adversarial Networks (GANs), to simulate RCT data from the historical data under various scenarios, varying treatment effects with and without treatment effect heterogeneity, RCT sizes, and bias. Results showed that causal ML methods can increase power even without borrowing historical data. For example, TMLE increased effective sample size by 21% in one scenario. In scenarios with borrowing of controls, PROCOVA increased power while controlling type 1 error, showing robustness to model misspecification.</p>","PeriodicalId":19934,"journal":{"name":"Pharmaceutical Statistics","volume":"25 5","pages":"e70105"},"PeriodicalIF":1.5,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13427638/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148648578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Impact of Enrollment Strategies on the Performance of Time-To-Event Dose-Escalation Designs for Phase I Drug Combination Oncology Trials.","authors":"Xiaowen Tian, Michael Sweeting, Kristine Broglio","doi":"10.1002/pst.70119","DOIUrl":"10.1002/pst.70119","url":null,"abstract":"<p><p>Dose-escalation trials make sequential dosing decisions for cohorts of patients based on accumulating toxicity data, often in the form of dose-limiting toxicities (DLTs). Challenges arise due to the necessity of complete follow-up for accurate dosing decisions. There are many settings where patients may become available to be enrolled before there is complete DLT information from the patients already in the trial. In radiotherapy trials, for example, the DLT assessment window is far longer than traditional chemotherapies and waiting for complete DLT information can result in impractically long trial durations. This issue can be exacerbated in escalation trials of dose-combinations, where the space to be explored and the sample sizes are generally larger. The time-to-event (TITE) approach, which utilizes partial follow-up data, has been effective in reducing trial lengths while ensuring accuracy and safety. Whether TITE methods are beneficial depends critically on the relationship between the DLT assessment window length and patient inter-arrival time, characterized by the assessment-to-interarrival (A/I) ratio. However, the impact of the rate of accrual into the trial and the size of each dosing cohort have not been carefully considered because it is widely assumed that accrual rates will be slow and the A/I ratio will be small. We use comprehensive simulation studies based on a dose-combination case-study and show that accrual rates corresponding to larger A/I ratios can result in poor accuracy and safety, while a dosing cohort size of one can additionally induce unfavorable operating characteristics. To address this issue, we propose a modification to the TITE design where the trial is paused if there are a certain number of non-completers. We demonstrate that this simple modified approach is robust across the range of A/I ratios investigated and has non-inferior operating characteristics to a non-TITE design while providing meaningful reductions in trial duration.</p>","PeriodicalId":19934,"journal":{"name":"Pharmaceutical Statistics","volume":"25 5","pages":"e70119"},"PeriodicalIF":1.5,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13574719/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148970707","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Accelerated Stability Studies: A Frequentist-Bayesian Hybrid Simulation Approach Implemented in the AccelStab R Package.","authors":"Bernard G Francq, Nikolaos Giannelos, Raymundo Sanchez, Marilena Paludi","doi":"10.1002/pst.70116","DOIUrl":"10.1002/pst.70116","url":null,"abstract":"<p><p>Stability assessment of vaccine drug products typically requires years of data collection. Accelerated stability studies offer a practical alternative by leveraging high-temperature data collected over shorter time periods. We model degradation using arbitrary nth order kinetics and derive a closed-form solution that enables extrapolation across time and temperature. We compare interval estimation methods including the delta method, bootstrap resampling, and Bayesian inference and propose a frequentist-Bayesian hybrid (FBH) posterior approximation framework based on a multivariate Student's t-distribution. FBH is closely related to objective Bayesian inference under noninformative priors in simple Gaussian settings and fully propagates uncertainty in both model parameters and residual variance. Simulation results show that FBH outperforms standard approaches by consistently achieving nominal coverage, particularly in small-sample settings where competing methods exhibit undercoverage. The approach provides well-calibrated confidence and prediction intervals while maintaining computational efficiency comparable to analytical methods and avoiding the cost of full posterior sampling. The methodology is illustrated using two vaccine development case studies and implemented in the AccelStab R package.</p>","PeriodicalId":19934,"journal":{"name":"Pharmaceutical Statistics","volume":"25 5","pages":"e70116"},"PeriodicalIF":1.5,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13545001/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148892262","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Bayesian Optimal Interval Design Considering Efficacy and Toxicity in Early Phase Basket Trials.","authors":"Tomoyuki Kakizume, Kentaro Takeda, Masataka Taguri, Satoshi Morita","doi":"10.1002/pst.70108","DOIUrl":"10.1002/pst.70108","url":null,"abstract":"<p><p>Oncology drug development has increasingly shifted toward determining optimal biological doses rather than maximum tolerated doses (MTDs), particularly for targeted therapies and immunotherapies that exhibit complex dose-efficacy relationships. Concurrently, basket trials have emerged as an efficient approach for evaluating investigational treatments across multiple cancer types sharing common molecular targets. We propose the BOIN-ETB design, a model-assisted dose-finding design that addresses optimal dose (OD) identification in phase I/II basket trials by incorporating both toxicity and efficacy endpoints. The proposed approach employs common toxicity boundaries across cancer types while implementing cancer-specific efficacy boundaries to account for differential efficacy responses between baskets. OD selection utilizes utility functions that quantify efficacy-toxicity trade-offs. Through comprehensive simulation studies across Fourteen realistic scenarios, the BOIN-ETB design demonstrates robust performance in identifying true ODs while maintaining acceptable safety profiles across diverse cancer populations. The design provides superior consistency compared to alternative approaches, particularly in scenarios with heterogeneous dose-efficacy relationships between cancer types, making it well-suited for contemporary oncology dose-finding basket trials.</p>","PeriodicalId":19934,"journal":{"name":"Pharmaceutical Statistics","volume":"25 4","pages":"e70108"},"PeriodicalIF":1.5,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148397446","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Knowledge Base of Designs and Statistical Methods for Adaptive Clinical Dose-Finding Trials.","authors":"Rob Kessels, Yongxi Long, Rene Spijker, Ewoud Schuit, Marieke Hollestelle, Chris van Lieshout, Neeltje Steeghs, Sjoerd G Elias, Peter M van de Ven","doi":"10.1002/pst.70074","DOIUrl":"10.1002/pst.70074","url":null,"abstract":"<p><p>Adaptive clinical dose-finding trials aim to identify an optimal drug dose for use in subsequent phase II and III trials. In adaptive dose-finding trials, dose levels for newly included patients are informed by outcomes of patients that received the drug earlier in the trial. The body of methodological research on adaptive dose-finding trials is extensive, but a clear overview is lacking. The goal of this paper is to provide a knowledge base of designs and statistical methods for adaptive clinical dose-finding trials by means of a literature review. We identified 315 adaptive dose-finding trial methodology articles of which the majority was inspired by oncology. Recent methods focused on identification of an optimal dose considering both toxicity and efficacy endpoints, and addressing challenges related to subgroup-specific dose-finding, dose-finding for combination therapies, and incorporation of delayed outcomes in dose-finding. These developments are driven by the emergence of newer classes of cancer drugs, such as targeted therapies and immunotherapies, and by initiatives like Project Optimus. Most articles focused on model-based designs, like the Continual Reassessment Method (CRM), but recent years have seen a strong increase in model-assisted or interval-based designs, including Toxicity Probability Interval (TPI) and Bayesian Optimal Interval (BOIN) designs and expansions thereof. Considering the increasing availability and large variety of adaptive dose-finding trial designs, it is challenging for researchers to find relevant designs tailored to their needs. Therefore, we provide an interactive map summarizing the classification of our results to facilitate the identification of relevant designs/methods, which we will update regularly.</p>","PeriodicalId":19934,"journal":{"name":"Pharmaceutical Statistics","volume":"25 4","pages":"e70074"},"PeriodicalIF":1.5,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147974280","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Harmonic Fowlkes-Mallows Index for Medical Diagnostics Tests and Optimal Cut-Off Point Selection of Binary Diseases.","authors":"Parthkumar Rabari, Purbasha Biswas, Jing X Kersey, Hani Samawi","doi":"10.1002/pst.70104","DOIUrl":"10.1002/pst.70104","url":null,"abstract":"<p><p>Accurately distinguishing between healthy and diseased states is fundamental to clinical diagnostics. This paper introduces the Harmonic Fowlkes-Mallows (HFM) index, a novel and robust metric for assessing diagnostic accuracy and identifying optimal cut-off points. The proposed HFM index integrates performance across both positive and negative classes by combining the traditional Fowlkes-Mallows Index (FM) with the proposed Negative Fowlkes-Mallows Index (NFM), using a weighted harmonic mean. Unlike conventional measures such as the F1-score or Youden Index, HFM provides a more comprehensive evaluation of classification performance by simultaneously addressing sensitivity and specificity. Additionally, it incorporates a tunable β parameter to adjust for asymmetries in class importance. Through simulation studies, the HFM index demonstrates strong performance in binary classification tasks and proves effective in selecting optimal decision thresholds. To further demonstrate its practical utility, we apply the HFM index to real-world breast cancer data and compare its performance with other diagnostic accuracy measures.</p>","PeriodicalId":19934,"journal":{"name":"Pharmaceutical Statistics","volume":"25 4","pages":"e70104"},"PeriodicalIF":1.5,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148284197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}