NYC ASA: Network and Multivariate Meta-Analysis

American Statistical Association
New York City
Metropolitan Area Chapter

Virtual Short Course

September 21 & 22, 2023
12:00 - 3:15 PM

The New York Metro Area Chapter of the American Statistical Association

Is Pleased to Invite You to a Virtual Short Course

Network and Multivariate Meta-Analysis

by

Joseph C. Cappelleri, Ph.D., M.P.H., M.S.
Executive Director of Biostatistics at Pfizer Inc

Haitao Chu, M.D., Ph.D.
Senior Director of Biostatistics at Pfizer Inc

Yong Chen, Ph.D.
Professor of Biostatistics at University of Pennsylvania

Description
Comparative effectiveness research aims to inform healthcare decisions concerning the benefits and risks of different prevention strategies, diagnostic instruments, and treatment options. Meta-analysis is a statistical method that combines results of multiple independent studies to improve statistical power and to reduce certain biases compared with individual studies. Meta-analysis also has the capacity to contrast results from different studies and identify patterns and sources of disagreement among those results. The increasing number of prevention strategies, assessment instruments, and treatment options for a given disease condition have generated a need to simultaneously compare multiple options in clinical research and practice. As such, network meta-analysis and multivariate meta-analysis have become increasing important tools for clinical decision-making.

Network meta-analysis provides an integrated and unified method that incorporates all direct and indirect comparative evidence about treatments. The evaluation of networks presents special challenges and caveats, which will be highlighted in this course. The fundamentals and concepts on network meta-analysis, which consumes about one-third of this short course, will be motivated by instructive and concrete examples.

In situations where data from studies are heterogeneously reported when data are missing for one or more outcomes of interest, synthesizing such data can lead to disconnected networks of evidence, increased uncertainty, and potentially biased estimates, which can have severe implications for decision-making. To overcome this issue, strength can be borrowed between outcomes of interest in multivariate network meta-analyses, another topic in the short course.

This short course will extend its focus on the most recent and advanced developments for multivariate and network meta-analysis methods. In doing so, the short course will offer a comprehensive overview of new approaches, modeling, and applications on multivariate and network meta-analysis. Specifically, the instructors will discuss the contrast-based and arm-based network meta-analysis methods for multiple treatment comparisons; multivariate methods to visualize, detect, and correct for publication biases; multivariate methods to compare diagnostic accuracy of more than two tests using network meta-analysis; and multivariate meta-analysis methods for estimating complier average causal effect (CACE) in randomized clinical trials with noncompliance. Case studies will be used to illustrate the principles and statistical methods introduced in this course.

After attending this short course, participants should be able to discuss the value of network meta-analysis (indirect and mixed treatment comparisons) for coherent decision-making; identify the concepts and assumptions of network meta-analysis, such as homogeneity, similarity and consistency; recognize the basic framework of statistical models for network meta-analysis; and describe characteristics for assessing the credibility of a network meta-analysis. In addition, participants should be able to estimate CACE from a meta-analysis of RCTs with complete or incomplete compliance data using the R package BayesCACE.

Instructors' Biography
Dr. Joseph C. Cappelleri is an executive director of biostatistics in the Statistical Research and Data Science Center at Pfizer Inc, where he has been employed for the past 27 years and is a recipient of the Craig A. Saxton Clinical Development Excellence Award. As an adjunct professor, he has served on the faculties at Brown University (biostatistics), Tufts Medical Center (medicine), and the University of Connecticut (statistics). He has co-authored approximately 650 publications (Google Scholar: citations = 28,445; h-index = 68; i10-index = 246), along with about twice as many external presentations. His research over the years has focused on clinical and methodological topics including meta-analysis, regression-discontinuity designs, health economics, and health measurement scales. Dr. Cappelleri is the lead author of the book Patient-Reported Outcomes: Measurement, Implementation and Interpretation and has co-authored or co-edited four other books (Statistical Topics in Health Economics and Outcomes Research, Phase II Clinical Development of New Drugs, Design and Analysis of Subgroups with Biopharmaceutical Applications, A Practical Approach to Quantitative Validation of Patient-Reported Outcomes: A Simulation-Based Guide Using SAS). Dr. Cappelleri earned his M.S. in statistics from the City University of New York (Baruch College), Ph.D. in psychometrics from Cornell University, and M.P.H. in epidemiology from Harvard University. He is past president of the New England Statistical Society, elected Fellow of the American Statistical Association (ASA), elected recipient of the Long-Term Excellence Award from the Health Policy Statistics Section of the ASA, elected member of the Society for Research Synthesis Methodology, and elected recipient of the ISPOR Avedis Donabedian Outcomes Research Lifetime Achievement Award.

Dr. Haitao Chu is a Senior Director in Statistical Research and Data Science Center, Pfizer Inc. He has over 20 years of leadership experience in the academic institutions and pharmaceutical industry. He has been influential externally, with decades of research, mentoring and teaching experience at major institutions, including Johns Hopkins University, University of North Carolina-Chapel Hill, and University of Minnesota. He has been awarded numerous federal methodology grants as the principal investigator, and has served on editorial boards of major journals, including Journal of the American Statistical Association (JASA), American Journal of Epidemiology, Statistics in Medicine, and Scientific Reports. He is an elected Fellow of the American Statistical Association and holds a Ph.D. degree in Biostatistics from Emory University, and an M.D. degree in Preventive Medicine from Sichuan University. Haitao has published over 240 peer-reviewed journal articles on pertinent statistical and biomedical topics. His current research areas include Bayesian methods, research synthesis methods, real world evidence, precision medicine and health technology assessment.

Dr. Yong Chen is Professor of Biostatistics at the Department of Biostatistics, Epidemiology, and Informatics at the University of Pennsylvania (Penn). He directs a Computing, Inference and Learning Lab at University of Pennsylvania, which focuses on integrating fundamental principles and wisdoms of statistics into quantitative methods for tackling key challenges in modern biomedical data. Dr. Chen is an expert in synthesis of evidence from multiple data sources, including systematic review and meta-analysis, distributed algorithms, and data integration, with applications to comparative effectiveness studies, health policy, and precision medicine. He has published over 170 peer-reviewed papers in a wide spectrum of methodological and clinical areas. In 2021, Dr. Chen was awarded the Observational Health Data Sciences and Informatics (OHDSI) Titan Award for Methodological Research on his contributions to developing effective and efficient privacy-preserving distributed algorithms for data integration. During the pandemic, Dr. Chen is serving as Director of Biostatistics Core for PedPASC of the RECOVER COVID initiative which a national multi-center RWD-based study on Post-Acute Sequelae of SARS CoV-2 infection (PASC), involving more than 13 million patients across more than 10 health systems. Dr. Chen's research has been continuously supported by NIH, AHRQ and PCORI. He is currently the PI of six research awards from NIH and PCORI on real-world data, evidence synthesis, knowledge discovery, and drug repositioning. He is an elected fellow of the American Statistical Association, the American Medical Informatics Association, Elected Member of the International Statistical Institute, and Elected Member of the Society for Research Synthesis Methodology.

Syllabus

DAY 1
THURSDAY, SEPTEMBER 21, 2023
12:00 - 3:15 pm

Instructor: Joseph C. Cappelleri (100 minutes)
Basics of network meta-analysis
Evidence networks
Risk of bias
Quality of evidence and strength of recommendation

10-minute Break

Heterogeneity, transitivity, inconsistency, bias
Models for network meta-analysis
Bayesian approach
Assess the relevance and credibility of a network meta-analysis

10-minute Break

Instructor: Yong Chen (75 minutes)
Network meta-analysis with multivariate outcomes
Publication bias
a) A historical review of methods that account for publication bias
b) Methods to quantify the evidence of publication bias in univariate meta-analysis
c) Methods to account for publication bias in multivariate meta-analysis: visualization, testing, quantification

DAY 2
FRIDAY, SEPTEMBER 22, 2023
12:00 - 3:15 pm

Instructor: Yong Chen (50 minutes)
Meta-analysis of diagnostic accuracy studies - comparing different diagnostic tests
Network meta-analysis of diagnostic tests - comparing multiple diagnostic tests at a time

10-minute Break

Instructor: Haitao Chu (125 minutes)
Arm-based network meta-analysis
a) Limitations of contrast-based network meta-analysis
b) Arm-based network meta-analysis
c) Model fitting, implementation, and case studies

10-minute Break

Causal inference in meta-analysis: accounting for noncompliance
a) Multivariate meta-analysis methods estimating complier average causal effect (CACE) in randomized clinical trials with noncompliance
b) Generalized linear latent and mixed model approach
c) Bayesian hierarchical model approach

Date and Time
Thursday & Friday, September 21 & 22, 2023
12:00 - 3:15 P.M. (US ET)

Virtual via Zoom

For Questions
Contact the Chapter

American Statistical Association New York City Metropolitan Area Chapter Virtual Short Course September 21 & 22, 2023 12:00 - 3:15 PM

American Statistical Association
New York City
Metropolitan Area Chapter

Virtual Short Course

September 21 & 22, 2023
12:00 - 3:15 PM