January 8, 2020: Registration Opens for 13th Annual Conference on Statistical Issues in Clinical Trials

Registration opened on January 1 for the 13th Annual University of Pennsylvania Conference on Statistical Issues in Clinical Trials. The theme of this year’s conference is “Cluster Randomized Clinical Trials: Challenges and Opportunities.”

The conference will be held on April 29 at the Smilow Center for Translational Research on the campus of the University of Pennsylvania Perelman School of Medicine in Philadelphia. Cosponsors include the American Statistical Association, the Society for Clinical Trials, and the National Institute of Statistical Sciences.

During the methods portion of the program, NIH Collaboratory investigator David Murray will present “Overview: Innovations in the Design and Analysis of Group- or Cluster-Randomized Trials.” The program also includes presentations on the uses of network- and individual-level information in design and analysis, the complexity introduced by noncompliance, current issues in stepped-wedge designs, and various applications of statistical techniques in cluster randomized studies.

Registration is required for this daylong event.

November 8, 2019: Lumbar Imaging with Reporting of Epidemiology: Initial Results and Some Lessons Learned (Jeffrey Jarvik, MD, MPH, Patrick Heagerty, PhD)


Jeffrey (Jerry) G. Jarvik MD MPH
Professor, Radiology, Neurological Surgery and Health Services
Adjunct Professor, Pharmacy and Orthopedics & Sports Medicine
University of Washington

Patrick Heagerty, PhD
Professor and Chair
Department of Biostatistics
University of Washington


Lumbar Imaging with Reporting of Epidemiology: Initial Results and Some Lessons Learned


Embedded pragmatic clinical trials; Radiology imaging; LIRE; Stepped-wedge; Cluster randomization; Epidemiology; Back pain

Key Points

  • The LIRE Demonstration Project evaluated whether prevalence benchmark data inserted into lumbar spine imaging reports would reduce overall spine-related healthcare utilization for patients referred from primary care.
  • The inserted intervention text urges caution when interpreting the presence of certain findings that are common in normal, pain-free volunteers.
  • While the study team found no decrease in spine-related healthcare utilization for the overall cohort, there was a small but potentially important effect on reducing opioid prescriptions.

Discussion Themes

A characteristic of stepped-wedge study design is that it yields two comparisons: between-group comparisons (clinic A vs clinic B) and within-group comparisons. But temporal trends can have an impact and must be adjusted for in the analysis.

For what type of intervention would a stepped-wedge design be suitable?

The hope is for a wider dissemination about interventions where radiologic testing is done and incidental findings are common.

Read more about the LIRE Demonstration Project.

#pctGR, #PragmaticTrials, @Collaboratory1

October 30, 2019: Baseline Covariate Imbalance Influences Treatment Effect Bias in Cluster Randomized Trials

In a study supported by the NIH Collaboratory, researchers found that imbalance in individual-level baseline covariates influences bias in the observed treatment effect in cluster randomized trials. Using race as an example, the study highlights the importance of reducing covariate imbalance in the design stage of cluster randomized trials and of using statistical analysis techniques to minimize the resulting bias.

The innovative study, published in Contemporary Clinical Trials, used computer simulation models validated by real-data simulations from a large clinical trial to examine the influence of baseline covariate imbalance on treatment effect bias. They found that bias was proportional to the degree of baseline covariate imbalance and the covariate effect size. In the simulations, trials with larger numbers of clusters had less covariate imbalance. Statistical models that adjusted for important baseline confounders were more effective than unadjusted models in minimizing bias.

The authors recommend several design approaches and statistical analysis techniques for both reducing covariate imbalance and minimizing bias. Using the results of available prior data can help researchers identify important baseline confounders when designing cluster randomized trials.

This work was supported within the NIH Collaboratory by the NIH Common Fund through a cooperative agreement from the Office of Strategic Coordination within the Office of the NIH Director, and by a research supplement from the NIH Common Fund to promote diversity in health-related research.

October 18, 2019: Playing with FHIR–Innovative Use Cases for the New REDCap EHR Integration Module (Paul Harris, PhD)


Paul A. Harris, PhD
Director, Office of Research Informatics
Professor of Biomedical Informatics, Biostatistics, and Biomedical Engineering
Vanderbilt University Medical Center


Playing with FHIR–Innovative Use Cases for the New REDCap EHR Integration Module


Fast Healthcare Interoperability Resources; FHIR; Data interoperability; Electronic health record; EHR; Electronic data capture; Clinical data; Research informatics

Key Points

  • REDCap (Research Electronic Data Capture) is a robust, web-based data exchange platform developed at Vanderbilt to assist the research community in implementation efforts.
  • The REDCap consortium has more than a million users. The platform is available at no cost to academic, nonprofit, and government organizations who join the consortium.
  • Innovative use cases are being conducted with REDCap and an Epic EHR system to increase data flow and remove dependency on a data warehouse.

Discussion Themes

How can we harmonize the REDCap approach with PCORnet’s common data model (CDM)?

FHIR is an HL7 standard for exchanging healthcare information electronically. Another use case integrates FHIR to democratize EHR extraction methods to improve efficiency in multisite clinical data collection.

How can researchers manage many-to-one mapping; for example, if the electronic case report form (CRF) has one field value but there are many values in the record?

Read more about the REDCap project.

#pctGR, @Collaboratory1

August 5, 2019: New Section of Living Textbook Addresses Missing Data in Intention-to-Treat Analyses

A new section of the NIH Collaboratory’s Living Textbook of Pragmatic Clinical Trials discusses challenges associated with missing data that result from noncompliance, crossover, and dropout.

Many randomized controlled trials use an intention-to-treat (ITT) analysis to measure the real-world effects of the intervention. The newly published section, Missing Data and Intention-to-Treat Analyses, considers the population-level causal effects in these trials when there is noncompliance or missing outcome data.

“One rationale for the ITT approach is that it evaluates the real-world effects of the intervention. However, a common misconception is that the ITT analysis will be unbiased regardless of crossover or missing data.”

The new section also introduces a white paper from the NIH Collaboratory’s Biostatistics and Study Design Core, “Analyses of Randomized Controlled Trials in the Presence of Noncompliance and Study Dropout.” This working document offers analysts a more detailed discussion of treatment effects in ITT analyses, including a case example and recommended strategies for estimating and reporting both ITT effects and average causal effects.

The Biostatistics and Study Design Core works with the Demonstration Project teams to create guidance and technical documents regarding study design and biostatistical issues relevant to pragmatic clinical trials.

April 15, 2019: Registration Now Open for Workshop on the Design & Analysis of Embedded Pragmatic Clinical Trials (ePCT)

The NIH Health Care Systems Research Collaboratory is hosting a one-day workshop on the Design & Analysis of Embedded Pragmatic Clinical Trials (ePCTs) on May 2, 2019, in the Lister Hill Auditorium on the NIH Campus.

The workshop will include a series of moderated discussions that focus on issues of measuring trial outcomes from available data sources, potential randomization strategies, specific ePCT design considerations, and unique challenges associated with ePCTs. Panel discussions will utilize case examples from the Collaboratory repertoire and beyond to illustrate how clinical investigators and biostatisticians work to address research questions posed by specific trials.

The Workshop Website provides information on meeting logistics, agenda, and registration. There is also an option to attend the workshop remotely via the NIH Videoconference Center, and those details are also available at the Workshop Website.

February 21, 2019: Living Textbook Offers New Content on Design and Analysis of Pragmatic Clinical Trials

Members of the NIH Collaboratory’s Biostatistics and Study Design Core contributed 3 new sections to the Living Textbook exploring issues in the design and analysis of pragmatic clinical trials. The new sections offer insights into emerging issues in embedded pragmatic clinical trials and lessons learned from the NIH Collaboratory’s first round of Demonstration Projects.

  • The Designing to Avoid Identification Bias section addresses a type of selection bias that can occur in pragmatic clinical trials that use information from electronic health records to determine study population eligibility and in which the study intervention influences who undergoes screening or receives a diagnosis in clinical care.
  • The Alternative Cluster Randomized Designs section describes alternative design choices for cluster randomized trials and their implications for statistical power and sample size calculations. Modified cluster randomized designs, such as cluster randomization with crossover, may reduce the sample size required for a pragmatic clinical trial and may be particularly feasible in trials embedded in healthcare systems with electronic health records.
  • Case Study: STOP CRC Trial explores challenges in design and analysis that were faced in the Strategies and Opportunities to Stop Colorectal Cancer in Priority Populations (STOP CRC) trial, one of the NIH Collaboratory Demonstration Projects. The case study illustrates how the study team dealt with pragmatic issues during the planning and conduct of the trial.

In addition to contributing content to the Living Textbook, the Biostatistics and Study Design Core works with the NIH Collaboratory Demonstration Projects to address challenges in their statistical plans and study designs during the planning phase and to develop guidance and technical documents related to study design and biostatistical issues relevant to pragmatic clinical trials.

October 1, 2018: Dr. Greg Simon Uses a Pie Eating Contest Analogy to Explain the Intraclass Correlation Coefficient

In a new video, Dr. Greg Simon explains the intraclass correlation coefficient (ICC) with an analogy to a pie eating contest. The ICC is a descriptive statistic that measures the correlations among members of a group, and it is an important tool for cluster-randomized pragmatic trials because this calculation helps determine the sample size needed to detect an effect.

Greg Simon from NIH Collaboratory on Vimeo.

“When we randomize treatments by doctors, clinics, or even whole health systems, we need to think about how things cluster, and the intraclass correlation coefficient is the measure of that clustering. When we think about sample sizes in pragmatic clinical trials, it’s important to understand what an intraclass correlation coefficient actually is.”

For most pragmatic trials, the ICC will be between 0 and 1. If the outcomes in a group are completely correlated (ICC=1), then all participants within the group are likely to have the same outcome. When ICC=1, sampling one participant from the cluster is as informative as sampling the whole cluster, and many clusters will be needed to detect an effect. If there is no correlation among members of the groups (ICC=0), then the available sample size for the study is essentially the number of participants.

For more on the ICC, see the Intraclass Correlation section in the Living Textbook or this working document from the Collaboratory’s Biostatistics and Study Design Core.

July 30, 2018: Registration Open for 3rd Seattle Symposium on Health Care Data Analytics

Registration is open for the 3rd Seattle Symposium on Health Care Data Analytics. The symposium will bring together biostatisticians, health informaticists, epidemiologists, and other data scientists to discuss health research and methods that involve large health care databases.

Experts involved in national research initiatives that use large health care databases will discuss methodological challenges encountered in this setting and share ideas for addressing them. Speakers will share their research on:

  • statistical approaches to learning from electronic health care data;
  • methods for precision medicine; and
  • health policy.

Space is limited, and registration is required.

The event is sponsored by the Biostatistics Unit at Kaiser Permanente Washington Health Research Institute and the Department of Biostatistics at the University of Washington.

March 21, 2018: Dr. Rob Califf to Speak on Data Science at March 23 Grand Rounds

Robert Califf, MD, former FDA Commissioner and current Vice Chancellor for Health Data Science at Duke University School of Medicine, will present at NIH Collaboratory Grand Rounds on Friday, March 23 at 1 pm ET. The webinar will be broadcast live and is open to the public. Following the presentation, Dr. Califf will answer questions from the Grand Rounds audience.

As Director of Duke Forge, Duke’s interdisciplinary center for actionable health data science, Dr. Califf is currently working on initiatives designed to harness biostatics, machine learning, and sophisticated informatics approaches to improve health and healthcare. Dr. Califf is also an adjunct professor of medicine at Stanford University and is employed by Verily Life Sciences as a scientific advisor. Verily, part of the Alphabet (Google) family of companies, is aimed at transforming the growth of health-related data into practical applications.

Dr. Califf has been a pioneer in the fields of clinical, translational, and outcomes research, and the NIH Collaboratory looks forward to hearing his thoughts on the pragmatic applications of data that will advance health and health care strategies and practice.

Topic: Data Science in the Era of Data Ubiquity

Date: Friday, March 23, 2018, 1:00-2:00 p.m. ET

Meeting Info: To check whether you have the appropriate players installed for UCF (Universal Communications Format) rich media files, go to https://dukemed.webex.com/dukemed/systemdiagnosis.php.

To join the online meeting:
Go to https://dukemed.webex.com/dukemed/j.php?MTID=m1a4a0665a615ae0382440edecedbdd33