In the Interim...

• The Not So Promising Zone Design

  In this episode of "In the Interim…", Dr. Scott Berry examines the mathematical foundations and efficiency claims of the promising zone design for adaptive sample size in clinical trials. Scott unpacks the conditional power thresholds that trigger sample size increases without the need to adjust alpha, as originally presented by Mehta & Pocock. He systematically demonstrates, via simulation, that the promising zone rarely provides meaningful efficiency gains over fixed designs and is consistently outperformed by group sequential designs that allocate alpha across multiple analyses. Using a driving-route analogy, Scott highlights the practical flaw in making pivotal trial decisions earlier than necessary due to arbitrary statistical rules rather than observing current data. He underlines that at Berry; simulation efforts have yet to reveal a scenario where the promising zone design is more efficient than a thoughtfully constructed group sequential or Goldilocks trial. The episode urges trialists to simulate, compare, and optimize—not to accept appealing mathematical tricks without rigorous evaluation.Key HighlightsExplanation of the promising zone’s conditional power mechanism and alpha control.Simulation-based comparison of power and average sample size across design types.Direct comparison of group sequential vs. promising zone designs.Discussion of futility rules and their impact on design choice.Commentary on Goldilocks designs for incomplete data.For more, visit: https://www.berryconsultants.com/

  --------  

  39:39

  --------

  39:39
• A Visit with Dr. Janet Wittes

  Episode 30 of “In the Interim…” features Dr. Janet Wittes, Fellow of the American Statistical Association, past president of the Society of Clinical Trials, and founder of Statistics Collaborative, in discussion with Dr. Scott Berry. Dr. Wittes details her progression from Radcliffe biochemistry to Harvard statistics, shaped by targeted mentorship and her family’s insistence on advanced scientific training. She describes teaching at Hunter College, her NIH/NHLBI tenure overseeing extensive DSMB work, and the launch of Statistics Collaborative 32 years ago, building the business with her children and their peers. The episode explores her consulting on clinical trial design for orphan and neglected diseases—malaria, dengue, leishmania, ALS—and vaccine development, with technical commentary on adaptive trial methods, operational issues in low-resource contexts, and decision-making for small-sample trials. Dr. Wittes reflects on statistical leadership, ongoing DSMB involvement, and the importance of evidence-driven public health. She underscores the need for contextual and cultural awareness in trial design, illustrated by her Lilith magazine story on kosher certification and challenges in stakeholder understanding. Discussion covers career obstacles, the evolution of clinical science, vaccine advocacy, and the critical role of diversity and practical on-site knowledge in advancing statistical research.Key HighlightsEarly academic transition from biochemistry to statistics.Serendipitous transition from academic career at Hunter College to Branch Chief of biostatistics at NIH/NHLBI.Founding Statistics Collaborative, business growth with children, and specialization in orphan disease trials.Consulting expertise in adaptive design, small-sample challenges, tropical and vaccine studies.Continued advocacy for vaccines, scientific rigor, and ethical public health practice.Importance of representation and context in science, demonstrated by real-world consulting examples.

  --------  

  40:50

  --------

  40:50
• Bayesian Clinical Trials with Frank Harrell

  In this episode of "In the Interim…", Dr. Scott Berry chats with Frank Harrell, a professor of Biostatistics at Vanderbilt University and W.J. Dixon Award winner. Harrell describes his transition from frequentist to Bayesian clinical trial design, prompted by a decisive meeting with Dr. Don Berry, informed by David Spiegelhalter’s published work. The dialogue addresses persistent academic opposition to Bayesian methods, operational constraints in trial implementation, regulatory work at FDA, and technical Bayesian modeling details.Key HighlightsHarrell credits Don Berry’s direct influence for converting him to Bayesian methods during his early career at Duke, despite entrenched academic resistance.Discusses early cardiovascular research at Duke, experiences with large multicenter trials, and later founding Vanderbilt’s Biostatistics department.Details the compromise of using Bayesian interim monitoring and frequentist primary analyses under NIH and regulatory mandates.Outlines design and publication of the ORBITA cardiovascular trial (Imperial College London), using all-Bayesian longitudinal ordinal methodology—Lancet reviewers required all analyses remain Bayesian, rejecting inclusion of a mixing frequentist and Bayesian analyses.Critiques simulation of Type 1 error within Bayesian trial designs.Addresses deficiencies in eliciting utilities for clinical endpoints, underscoring operational challenges in longitudinal ordinal modeling and ethical imperatives for efficient early stopping.

  --------  

  47:20

  --------

  47:20
• A Visit with Dr. Derek Angus

  In this episode of “In the Interim…”, Dr. Scott Berry interviews Dr. Derek Angus, Distinguished Professor and Chair of Critical Care Medicine at the University of Pittsburgh and Senior Editor at JAMA. The discussion addresses the decades-long controversy surrounding steroid use in community-acquired pneumonia (CAP) and sepsis. The episode delivers a chronological assessment of the evidence base—summarizing trial results from pivotal studies, including CAPE COD, REMAP-CAP, ADRENAL, and multiple French trials led by Dr. Djillali Annane. Dr. Angus analyzes why discrepancies persist in outcomes, clinical recommendations, and international guidelines, and underscores the challenge of heterogeneous treatment effects. The episode closes with an argument for adaptive trial designs, Bayesian inference, and embedded randomization within learning health systems as critical tools for clarifying complex response patterns and improving patient care.Key HighlightsHistorical evolution of clinical trials studying steroid regimens for CAP/sepsisReview of CAPE COD, REMAP-CAP, ADRENAL, and Annane-led French trials showing conflicting signals.Discussion of persistent heterogeneity in trial populations, interventions, and endpoints.Identification of methodological limitations—control contamination, endpoint definitions, varying inclusion criteria.Exploration of Bayesian and adaptive trial design, and operationalization of learning health systems to resolve evidence gaps.For more, visit: https://www.berryconsultants.com/

  --------  

  41:58

  --------

  41:58
• The Mystery of Clinical Trial Simulation

  Dr. Scott Berry hosts this episode of "In the Interim…", opening with statistical analysis of elite athletes before focusing on the misunderstood role of clinical trial simulation. He distinguishes simulation as a predictive tool from its use as an in-silico process that enables trial design exploration, iteration, and optimization. Clinical trial simulation provides a mechanism for iterative comparison of multiple designs, driven by ongoing team feedback and evolving trial objectives. Scott stresses that rigid simulation plans are “not productive,” since the most effective designs typically emerge when stakeholders view real trial examples and suggest new design options in real time. The ICECAP trial serves as a key illustration, where the final design was shaped by simulation-informed team input across multiple iterations, from three tested durations to ten with response adaptive randomization. Scott also discusses the creation of the FACTS software, highlighting its ability to test alternative designs rapidly, present side-by-side comparisons, and conduct counterfactual analyses—revealing what different trial configurations would have produced using the same simulated datasets.Key HighlightsSimulation contrasted as a predictive tool versus engine for iterative design evaluation.Emphasizes design process as team-driven and iterative, not prescriptive.Use of concrete example trials enhances communication across multidisciplinary teams.FACTS software enables design flexibility, in silico iteration, and comparative scenario analysis.ICECAP trial as an instance of simulation-informed design adaptation.For more visit: https://www.berryconsultants.com/

  --------  

  41:38

  --------

  41:38

More Health & Wellness podcasts

Trending Health & Wellness podcasts

About In the Interim...

In the Interim...: Podcasts in Family