Statistics in Clinical Development of Cancer Drugs
Description
Cancer clinical trials have become increasingly complex, requiring statistical methodologies that are both rigorous and flexible across diverse study designs. This book provides a comprehensive and practice-oriented overview of the statistical methods underpinning modern oncology drug development, covering the full continuum from early-phase studies through confirmatory trials and regulatory submission.
Organized by development phase, the text presents principled approaches to dose-escalation and dose-optimization, proof-of-concept decision-making, and master protocol designs. It further details methodologies for late-stage trials, including sample size determination, group-sequential monitoring, time-to-event analysis, multiplicity adjustment, and adaptive designs, with particular attention to challenges such as delayed treatment effects.
In addition to confirmatory trial methodology, the book addresses advanced analytical topics, including subgroup evaluation, treatment switching, multi-phase treatment strategies, and bias adjustment techniques. Contemporary issues in oncology research-such as the estimand framework, real-world evidence, seamless and platform trials, and emerging applications of artificial intelligence and machine learning-are also discussed.
Accessible yet rigorous, this book is an essential resource for biostatisticians, clinical researchers, and graduate students who want to design smarter trials, make better decisions, and accelerate the development of life-saving cancer therapies.
More details
Persons
Dr. Madan G. Kundu is a PhD-trained biostatistician with over 12 years of experience in oncology clinical trials spanning both solid tumors and hematologic malignancies. He currently serves as Director of Biostatistics at Daiichi Sankyo and has previously held statistical roles at Novartis Oncology and AbbVie Inc. Dr. Kundu serves as the project statistician for an oncology compound, where he leads cross-functional teams across biostatistics, statistical programming, and data management. His work focuses on the application and advancement of statistical methods to support clinical development and regulatory decision-making in oncology. His methodological research interests include classification and regression trees (CART), survival data analysis, longitudinal data analysis, surrogate endpoints, delayed treatment effects, weighted log-rank tests, MaxCombo tests, group-sequential designs, information fraction, and functional data analysis. He has authored more than 35 peer-reviewed publications with over 1,200 citations. Dr. Kundu serves as Associate Editor for Contemporary Clinical Trials, Contemporary Clinical Trials Communications, and BMC Cancer, and is an active reviewer for several leading statistical and clinical journals. In addition to his research contributions, he has developed an R package and multiple Shiny applications to support statistical methodology and promote accessible tools for the broader research community.
Samiran Ghosh is Professor and Chair of the Department of Biostatistics and Data Science at the UTHealth Houston School of Public Health in Houston, USA. He also holds the title of UTHealth Houston Distinguished Chair in Population Health. Before joining UTHealth, he served for more than ten years as the Charles H. Gershenson Distinguished Faculty Fellow at Wayne State University. His methodological research spans a broad range of areas, including implementation science, Bayesian and adaptive clinical trials, precision medicine, cluster-randomized trials, and advanced trial designs such as Sequential Multiple Assignment Randomized Trials (SMART), Multiphase Optimization Strategy (MOST), Just-in-Time Adaptive Interventions (JITAI), enrichment trials, and N-of-1 trials. His work covers multiple phases of clinical research, including efficacy, effectiveness, and implementation science. He is also developing methodologies for integrating real-world data (RWD) into clinical trials to reduce the burden of large sample sizes. However, this integration poses several challenges, including issues related to data quality, heterogeneity, relevance, and bias or confounding. In cancer-related research, his interests include cancer screening, survivorship, and the prevention and treatment of various cancers. He regularly serves as a reviewer for the National Institutes of Health, Patient-Centered Outcomes Research Institute, and the Congressionally Directed Medical Research Programs of the U.S. Department of Defense. He is a Fellow of the American Statistical Association.
Content
Section 1: Introduction .- Chapter 1: Overview of cancer trials.- Chapter 2: Application of Estimands framework.- Section 2: Statistical methods for Early phase trials .- Chapter 3: Dose-escalation designs.- Chapter 4: Proof-of-concept and Dose-optimization designs.- Section 3: Late phase .- Chapter 5: Designing pivotal cancer trial along with sample size.- Chapter 6: Complex designs.- Chapter 7: Non-proportionality and other challenges related to immunotherapy.- Chapter 8: Post-hoc analyses (specific to time-to-event endpoint).- Section 4: Additional topics .- Chapter 9: Quantitative decision making and Event projection.- Chapter 10: AI/ML methods and precision medicine.- Chapter 11: Basket and umbrella trials.- Appendices.