<P><STRONG>1.</STRONG> <STRONG>Using Real-world Evidence to Transform Drug Development: Opportunities and Challenges</STRONG><BR><I>Harry Yang<BR><BR></I>Introduction<BR>Traditional Drug Development Paradigm<BR>Drug Development Progress<BR>Limitations of Traditional Randomized Controlled Trials<BR>Real World Data and Real World Evidence<BR>Real World Data<BR>Real World Evidence<BR>Differences between RWE and Outcomes of RCT<BR>Regulatory Perspective<BR>Productivity Challenge<BR>FDA Critical Path Initiative<BR>Regulatory Perspectives Pertaining to RWE<BR>Historical Approval Based on RWE<BR>Access to RWD<BR>Opportunities of RWE in Drug Development<BR>Early Discovery<BR>Clinical Study Design and Feasibility<BR>Study Execution<BR>Marketing Application<BR>Product Launch<BR>Product Lifecycle Management<BR>Challenges with RWE <BR>Data Access and Quality<BR>Technological Barriers<BR>Methodological Challenges<BR>Lack of Data Talents<BR>Regulatory Risks<BR>Concluding Remarks</P><OL><P></P></OL><P></P><B><P>2. Evidence derived from real world data: utility, constraints and cautions<BR></B><I>Deepak Khatry<BR></I><I> <BR></I>What is RWD in the context of drug development and clinical practice<BR>Why is RWD important? <BR>For what purposes can RWD be useful? <BR>What study designs and statistical methods will be necessary to ensure high quality RWE? <BR>Some application examples </P><P></P><B><P>3. Real-world evidence from population-based cancer registry <BR></B><I>Binbing Yu <BR></I><BR>Introduction <BR>Statistical methods for population-based cancer registry <BR>Application to small cell lung cancer survival<BR>Discussions </P><P></P><B><P>4. External Control using RWE and Historical Data in Clinical Development <BR></B><I>Qing Li, Guang Chen, Jianchang Lin, Andy Chi and Simon Davies<BR></I><BR>Introduction of using RWE and Historical Data in Clinical Development <BR>Single Arm Trial Using External Control for Initial Indication <BR>Comparison Across Trials with External Control for Label Expansion <BR>Important Considerations When Designing Studies and Analyzing Data Using<BR>External Control in Clinical Development </P><P></P><B><P>5. Bayesian method for assessing drug safety using real-world evidence <BR></B><I>Binbing Yu <BR></I><BR>Introduction<BR>Bayesian sensitivity analysis for unobserved confounders<BR>Bayesian evidence synthesis using meta-analysis<BR>Discussion </P><P><STRONG>6. Real-World Evidence for Coverage and Payment Decisions <BR></STRONG><EM>Saurabh Aggarwal*, Hui Huang*, Ozlem Topaloglu, Ross Selby<BR></EM><BR>Introduction<BR>Defining value<BR>Contracting trend/value-based agreement<BR>Importance of RWE for demonstrating value<BR>Use of RWE by payers and health technology assessment agencies</P><P></P><B><P>7: Causal Inference for Observational Studies/Real-World Data <BR></B><I>Bo Lu<BR><BR></I>Causal Inference with Real-World Data<BR>Propensity Score Adjustment for Observational Studies<BR>Sensitivity Analysis for Hidden Bias<BR>Case study: Propensity Score Matching Design and Sensitivity Analysis for Trauma Care Evaluation </P><P></P><B><P>8. Introduction to Artificial Intelligence and Deep Learning with a Case Study in Analyzing Electronic Health Records for Drug Development <BR></B><I>Xiaomao Li and Qi Tang <BR><BR></I>Introduction to AI and overview of break-throughts of AI in drug development<BR>A minimalist overview of deep learning methods<BR>Introduction of the big data in clinical space: electronic health record <BR>A case study of using deep learning to analyze HER <BR>Introduction to Python and cloud computing</P>