Short Course 1(half-day): AI for Clinical Trials and Humanized AI for Future Healthcare

8:30am-12:00pm, August 13, 2025, MCHU 201

Instructor: Mark Chang, PhD

Mark Chang, PhD, is the founder of AGInception. He is an elected fellow of the American Statistical Association with over 25 years of experience as a statistician in the biopharmaceutical industry and academia, where he previously held various positions from Scientific Fellow to Senior Vice President. As an Adjunct Professor for Boston University, he has guided his students on doctoral thesis topics of Adaptive Clinical Trial Design and Artificial Intelligence. He has broad research interests, including adaptive clinical trials, AI, principles of scientific methods, paradoxes, issues and methods in modern biostatistics, and AI software development. He is the inventor and owner of two US patents on AI. His recent publications include research papers and two books on AI: (1) Artificial Intelligence for Drug development, Precision Medicine, and Healthcare (2020), and (2) Foundation, Architecture, and Prototyping of Humanized AI (2023). Dr. Chang has served on editorial boards for statistical journals and is actively engaged in statistical communities promoting biostatistics, including teaching numerous courses on adaptive clinical trial designs and AI/ML. He is a co-founder of the International Society for Biopharmaceutical Statistics.

Abstract

Machine Learning (ML) in clinical trials and Humanized AI (HAI) are playing increasingly vital roles in both healthcare and daily life. This short course consists of two parts, drawing from the instructor’s books: Artificial Intelligence for Drug Development, Precision Medicine, and Healthcare (2020), Humanized AI – Foundation, Architecture, and Prototyping (2023), and Critical Thinking and Creative Analogies in Statistics, Science, and Technology–Essential Skills in the AI Era (Expect Oct, 2025)

The first part explores the evolving landscape of AI/ML in drug development and healthcare, highlighting key challenges, including regulatory considerations. We will compare classical statistical approaches with AI/ML, illustrating the benefits of this paradigm shift through real-world examples. A hands-on demonstration in R will showcase an AI-driven approach to rare disease clinical trials.

The second part delves into Artificial General Intelligence (AGI) and Humanized AI, examining their transformative impact on healthcare and everyday life. We will discuss how to steer HAI development in a positive direction, contrasting big-data-driven approaches with emerging small-data-based methods. Key topics include attention, learning, and response mechanisms, supported by practical HAI demonstrations.

This course is designed for both those seeking a broad overview of AI’s role in healthcare and those interested in hands-on applications.

Section Type: ½ day short course

Target Audience

This introductory course is designed primarily for clinical statisticians, from junior-level professionals to heads of biometrics. A secondary audience includes statisticians, data scientists, and other professionals working across various sectors of the pharmaceutical industry.

Detailed Outline:

1. AI, ML, and Classical Statistics

○ Key similarities and differences between AI, ML, and classical statistics

○ Controversies and challenges in statistics with potential resolutions

2. Machine Learning Mechanisms

○ Overview of five ML paradigms:

1. Supervised learning
   

2. Unsupervised learning
   

3. Reinforcement learning
   

4. Collective intelligence learning
   

5. Evolutionary learning
   

3. AI in Pharmaceuticals

○ The pharmaceutical AI landscape

○ Similarity-based ML and its applications in drug development and medical science

4. Humanized AI (HAI) and the Future of AI

○ Defining HAI: machine-race humans

○ Evolution of key AI architectures (CNN, RNN, GPT, DeepSeek, self-attention, diffusion model...)

○ AGI and Core architectures of HAI

○ Addressing critical issues: understanding, self-awareness, morality, creativity, imitation, imagination, and cognitive learning

○ Prototyping demonstrations showcasing HAI applications

Goals / Expected Outcomes：

This course aims to provide a comprehensive understanding of the AI/ML landscape in the pharmaceutical industry, with a particular focus on its applications and challenges in clinical development. Rather than diving directly into technical methods, we will first establish a solid understanding of the underlying problems AI seeks to address.

By the end of the course, attendees will:

1. Grasp key AI/ML concepts and their relevance to clinical trials.
   

2. Recognize the major challenges in AI-driven clinical development.
   

3. Develop foundational skills in applying ML methods using R.
   

4. Begin formulating strategies for integrating AI into clinical trials.
   

5. Gain a broader perspective on the future of AI and its potential impact on healthcare and drug development.
   

This course balances theoretical insights with practical applications, equipping participants with the knowledge to critically assess and implement AI solutions in their respective fields.

Short Course 2(half-day): Introduction to Meta-analysis with Application in Clinical Trials

1:30pm-5:00pm, August 13, 2025, MCHU 201

Instructor: Zhaohui Liu, Bristol Myers Squibb (BMS).

Zhaohui Liu, Bristol Myers Squibb (BMS).Dr Liu is a Director in Global Biometrics and Data Science (GBDS) of BMS. After graduating from University of Connecticut, where he witnessed the MCMC breakthrough from its cradle and was taught by a few Bayesian champions, Zhaohui has been working in the US pharmaceutical industry, first at Novartis, and then at BMS, for more than 20 years with experience in all phases of clinical trials.

Abstract

How to integrate clinical evidence from various sources to make coherent and robust statistical inference so that sporadic data points can inform decision makers a unified story with statistical rigor? Meta-analysis arose with this backdrop. In this short course we will discuss its key concepts, methods, in both frequentist and Bayesian approaches, focusing mainly with examples in the context of clinical trials.

In Part 1 of the course, basic concepts, inference, examples from clinical trials setting, and programming implementation will be introduced. After brief layout of the scenario necessitating meta-analysis, we will introduce key concepts and inference methods such as continuous, binary, and time-to-event data, fixed-effect model, random effect model, measures of heterogeneity, and a few further topics, e.g., prediction, treatment difference, subgroup analysis, power consideration etc., if time permits.

In Part 2, we will shift gear into Bayesian paradigm with basic concepts, key methods, and worked examples. The advantage of Bayesian approach is its versatility in leveraging historical information by informed or non-informed priors to account for uncertainty. Meta-Analytic-Predictive (MAP) method for informative prior will also be discussed for the continuous, binary, and time-to-event data.

In the last part, we will delve into topics like model checking, diagnostics and influence analysis. Statistics is hard science, but statisticians performing data analysis need to work as a skillful physician treating patients. Mechanistical manual following can automatically produce results. However, are these conclusions valid or robust? Will the latest reported clinical trial readout derail the conclusion if it were included in the meta-analysis? Off-shelf ready-to-use statistical software packages and timeline pressure for significant p-value may entice people to jump into conclusions immediately without carefully checking the assumptions. This in turn may either lead to inflated results or to discard potentially meaningful findings. How should a statistician in the clinical trial setting facing these challenges proceed?

• basic concepts, inference, examples from clinical trials setting, and programming implementation
• Bayesian paradigm with basic concepts, key methods, and worked examples.

• topics like model checking, diagnostics and influence analysis.

Short Course 3(full-day): Revolutionizing Drug Development with Bayesian Adaptive Designs: Simple, Efficient, Superior

8:30am-5:00pm, August 13, 2025, MCHU 202

Instructor: J. Jack Lee, Ph.D.

J. Jack Lee, Ph.D. is Professor of Biostatistics and Kenedy Foundation Chair in Cancer Research. His areas of statistical research include design and analysis of clinical trials, Bayesian adaptive designs, statistical computation/graphics, drug combination studies, and biomarkers identification and validation. He is an elected Fellow of American Statistical Association, Society for Clinical Trials, and American Association for the Advancement of Science. He is a Statistical Editor of Cancer Prevention Research and serves on the Statistical Editorial Board of Journal of the National Cancer Institute. He has more than 500 publications in statistical and medical journals. He co-authored two books entitled: “Bayesian Adaptive Methods for Clinical Trials” and “Model-Assisted Bayesian Designs for Dose Finding and Optimization: Methods and Applications.”

Abstract

Department of Biostatistics, University of Texas MD Anderson Cancer Center

It is well known that the current drug development process is lengthy, costly, and has a high failure rate. How can we improve this from a statistical point of view? Current medical research is dominated by the frequentist approach, which relies on p-values, confidence intervals, null hypothesis significance testing, etc. This approach is rigid, addresses key questions indirectly, and violates the likelihood principle.

On the other hand, the Bayesian approach directly models the parameter of interest by forming its prior belief and using observed data to update this belief by constructing the posterior distribution. It conforms to the likelihood principle and provides a better statistical inferential framework. The Bayesian approach is intuitive, innately adaptive, can incorporate all available information for efficient estimation, and is uniquely suitable for drug development.

In this short course, we will first compare and contrast the frequentist and Bayesian approaches. We will highlight the strengths of the Bayesian approach, such as the importance of incorporating the prior distribution and using posterior probability for statistical inference. We will introduce Bayesian adaptive designs, particularly model-assisted designs, which are a new class of designs developed to simplify the implementation of adaptive designs in practice. Model-assisted designs are derived from rigorous statistical theory, thus possessing superior operating characteristics and great flexibility, while being easy to implement with pre-calculated boundaries. These designs follow the new KISS principle: Keep It Simple and Smart, making them ideal for drug development.

The main application areas include adaptive dose-finding, adaptive toxicity and efficacy evaluation, dose optimization, posterior probability, and predictive probability for interim monitoring of study endpoints, outcome-adaptive randomization, hierarchical models, multi-arm, multi-stage designs, and platform designs, among others. Useful model-assisted designs for early-phase clinical trials to determine the maximum tolerated dose (MTD) and optimal biological dose (OBD) will be introduced. These include the Bayesian Optimal INterval (BOIN) design, Time-To-Event (TITE)-BOIN design, BOIN-COMB, U-BOIN design, BOIN12 design, and TITE-BOIN12 design. The Bayesian Optimal Phase 2 (BOP2) design and 2-Arm BOP2 design will be introduced to evaluate simple and complex efficacy and/or toxicity endpoints.

We will also discuss Bayesian adaptive platform designs with applications in master protocols, including umbrella trials and basket trials. Lessons learned from real trial examples and practical considerations for conducting adaptive designs will be shared. Additionally, easy-to-use Shiny applications on the web and downloadable standalone programs will be introduced to facilitate the study design and conduct of Bayesian adaptive designs. They are freely available at https://trialdesign.org and https://biostatistics.mdanderson.org/softwaredownload/.

References:

Berry SM, Carlin BP, Lee JJ, and Mueller P. Bayesian Adaptive Methods for Clinical Trials. Boca Raton, FL United States of America: CRC Press; 2010.

Yuan Y, Lin R, Lee JJ. Model-Assisted Bayesian Designs for Dose Finding and Optimization: Methods and Applications. Boca Raton, FL United States of America: CRC Press; 2023.