SESSION G

TITLE: Artificial Intelligence for Medicine & Health
INSTRUCTOR: Professor Mark Chang, Boston University
MODERATOR: Wenjin Wang

 

Abstract:

Artificial intelligence (AI) or machine learning (ML) has been used in drug discovery for many years under name of bioinformatics, such as sequencing, annotating genomes, analysis of gene and protein expression and regulation, linking the biological and disease network to the symptoms and adverse events, identifying structure-activity relationships in discovery and designing new drugable molecules. AI has also been used for the prediction of cancer susceptibility (risk assessment), cancer recurrence/local control, and cancer survival. In analysis of clinical trial data, predicted individual patient outcomes for precision medicine, similarity-based machine learning (SBML) has recently been used in clinical trials for oncology and rare disease without the requirement of big data as most ML methods do. The introductory course will cover supervised, unsupervised, semi-supervised, and reinforcement learning methods, and swarm and evolutionary intelligences. It aims at conceptual clarity and mathematical simplicity. Provide R code for some of the supervised learning methods and discussion case studies.

Table of Contents:

  • Overview AI methods in Medicine and Health
  • Supervised Learning Method

Tree-Based Methods

Support Vector Machine

Artificial neural network for Deep Learning

Perceptron

Convolutional Neural Networks

Recursive Neural Networks

Long Short-Term Memory Networks

Deep Belief Network

  • Similarity Based Method:

Nearest-Neighbors Method

Kernel Method

Similarity-based machine learning

Implementation in R

Clinical Trial Examples

(4) Other AI methods and Future Perspectives

Unsupervised Learning

Reinforcement Learning,

Evolutionary Intelligence

Future perspectives

Goals: attendees will learn common AI methods in drug development and medicine, be able to use the AI methods with R for medicine, especially for clinical trials, and be able to interpret the results.

Instructors’ Biography:

Dr. Mark Chang is Sr. Vice President, Strategic Statistical Consulting at Veristat. Before joining Veristat, Chang was Vice President of Biometrics at AMAG Pharmaceuticals. Chang 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, 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 Journal of Pharmaceutical Statistics. He has been invited to serve as a co-chair on the scientific advisory board and organization committees for several national and international professional/academic conferences on statistics and clinical trial designs. He has given over 50 lectures, short courses, and invited speeches at national and international conferences. Dr. Chang is an expert in adaptive clinical trials and other innovative approach in drug development and has been invited to present adaptive design and biomarker topics at the US Food and Drug Administration. Chang has broad research interests. He has published 10 books, including Adaptive Design Theory and Implementation Using SAS and R, Paradoxes in Scientific Inferences, Modern Issues and Methods in Biostatistics, Monte Carlo Simulation for the Pharmaceutical Industry, Principles of Scientific Methods, and Innovative Strategies, Statistical Solutions and Simulations for Modern Clinical Trials.

This entry was posted in . Bookmark the permalink.

Leave a Reply

Your email address will not be published. Required fields are marked *