Chair: Herbert Pang (Genentech)

Instructor: Mark Chang (Boston University)

Artificial intelligence (AI) or machine learning (ML) has been used in drug discovery in biopharmaceutical companies for nearly 20 years. Recently AI has also been used for the disease diagnosis and prognosis in healthcare. In clinical trial design, analysis of clinical trial data, and prediction of individual patient outcomes for precision medicine, similarity based machine learning (SBML) has been proposed for clinical trials for oncology and rare disease without the requirement of big data.  The course will focus on supervised learning, including similarity-based machine learning and deep learning neural networks. We will also introduce unsupervised, reinforcement, and evolutionary learning methods. The short course aims at conceptual clarity and mathematical simplicity. Provide R code for implementation with examples. The course materials are based on instructor’s upcoming book in Feb 2020: Artificial Intelligence in Drug Development, Precision Medicine, and Healthcare.

The course will cover:
(1) Deep Learning Neural Networks: Convolutional Neural Network (CNN); Recurrent Neural Network (RNN); Long Short-term Memory Networks (LSTMs); Deep Belief Network (DBN)
(2) Similarity-Based Machine Learning; Kernel Method; Nearest-Neighbors Method; Support Vector Machine
(3) Overview of unsupervised, Reinforcement, Collective Intelligence, and Evolutionary Learning Methods
(4) Future of AI in Drug Development

Goals: Attendees will learn common AI methods in drug development with R for clinical trial and beyond and be able to interpret the results.

Mark Chang, PhD
Boston University

Mark Chang is the founder of AGInception for AGI research. He is a fellow of the American Statistical Association and an adjunct professor of Biostatistics at Boston University. He is a co-founder of the International Society for Biopharmaceutical Statistics, was co-chair of the Biotechnology Industry Organization (BIO) Adaptive Design Working Group, and a member of the Multiregional Clinical Trial (MRCT) Expert Group. Chang has served associate editor for several statistical Journals. Chang’s research interests include adaptive designs and artificial intelligence. He has published 10 books, including Adaptive Design Methods for Clinical Trial (Chow and Chang, 2006), Adaptive Design Theory and Implementation using SAS and R (2007), Modern Issues and Methods in Biostatistics (2011), Monte Carlo Simulations for the Pharmaceutical Industry (2012), Paradoxes in Scientific Inference (2012), Principles of Scientific Methods (2014), Innovative Strategies, Statistical Solutions, and Simulations for Modern Clinical Trials (2019), and Artificial Intelligence for Drug Development, Precision Medicine and Healthcare (2020). Chang has previously worked as Sr. Vice President, Strategic Statistical Consulting at Veristat and served various strategic roles including Vice President of Biometrics at AMAG Pharmaceuticals and scientific fellow at Millennium/Takeda Pharmaceuticals.