Skip to main content

AI for Reliable and Equitable Real World Evidence Generation in Medicine

AI for Reliable and Equitable Real World Evidence Generation in Medicine
July 9, 2024

The "AI for Reliable and Equitable Real World Evidence Generation in Medicine" workshop is dedicated to advancing the understanding and exploring the transformative role of artificial intelligence (AI) in analyzing real-world data (RWD) for real-world evidence (RWE) generation, leading to evidence-based medicine (EBM). Focused on leading-edge research and innovation, the workshop will feature research papers and panel discussions that delve into key aspects of machine learning innovations and applications in RWE generation from EHRs and claims, including structured data, natural language processing (NLP) of clinical notes, medical imaging, and waveform data processing from wearable devices. The workshop will feature both innovative AI methodology as well as their applications to real-world problems and their impact on transforming evidence-based medicine. The workshop seeks to facilitate in-depth discussions on the integration of AI technologies to enhance the reliability and equity of RWE generation. The workshop serves as a platform for engaging multiple stakeholders across healthcare research, including researchers, clinicians, pharmaceutical and industry professionals to delve into the intricacies of these advanced methodologies, fostering dialogue and collaboration. Attendees can anticipate in-depth discussions, presentations, and networking opportunities, gaining valuable insights into the forefront of AI-driven strategies shaping the future of these discoveries.


AI encompasses statistical and computational machine learning, deep learning, and generative AI (e.g., Large Language Model, Diffusion Models, etc), all are welcomed approaches. We include innovative AI methods as well as application of AI methods to the field of evidence generation for real-world effectiveness, safety, and equity research.


  • Causal AI in Healthcare: Exploring methods and applications integrating causal inference and machine learning to address selection bias and confounding bias in observational studies using real-world data, with a focus on comparative effectiveness and safety research
  • Multi-modality data integration and analysis: Multi-modality data acquisition, standardization, integration, and analysis frameworks and methods to provide more comprehensive understanding of patient health and equity in healthcare systems
  • Federated Causal Inference in Health Care: Federated causal inference for comparative studies using observational data, with a focus on addressing confounding bias, violation of overlap, and patient population difference across multiple data sources
  • Real-World Evidence (RWE) Generation from Multi-modality Data: Advancements in AI for analyzing multi-modality data and the advantages of multi-modality data for improving the reliability of RWE
  • Personalized Treatment Effect Estimation: Utilizing heterogeneous and individualized treatment effect estimation for personalized treatment planning, leveraging machine learning algorithms to tailor healthcare to individual patient needs
  • Impact of RWE on Evidence-Based Medicine (EBM): Review and discuss how AI innovations and applications in RWE generation from EHRs and claims data have impacted EBM, especially during COVID-19, and how they will shape the future of health care.
  • Assessing Health Disparities and Inequities: Quantifying the impact of social and environmental determinants of health (SEDOH) on healthcare resource allocation and health outcome to identify root causes of disparities through Causal AI






10 minutes

Podium presentation 

Welcome Address

Linying Zhang

50 Minutes

Podium presentation

Opening Keynote

George Hripcsak

60 minutes

Research presentation

Spotlight presentation

Authors of 4 accepted papers

15 minutes

Coffee Break

Connect and collaborate


80 minutes

Podium presentation

4 Rising Star Presentations on AI in Medicine

Michael Oberst, Zhiyu Wan, Vicky Tiase, Laura Wiley

20 minutes


Reflection Panel on Real-World Evidence with AI

George Hripcsak, Scott L. Duvall, David K. Vawdrey, Adam Wilcox, Linying Zhang

20 minutes

Podium presentation

Closing Keynote

Scott L. Duvall

Keynote Speakers

Opening Keynote

George Hripcsak, MD, MS

Vivian Beaumont Allen Professor, Biomedical Informatics, Columbia University

Dr. George Hripcsak, MD, MS, is interested in the clinical information stored in electronic health records and in the development of next-generation health record systems. Health record data are sparse, irregularly sampled, complex, and biased. Using nonlinear time series analysis methods borrowed from statistical physics, machine learning, knowledge engineering, and natural language processing, he is developing the methods necessary to support clinical research and patient safety initiatives using health record data. Dr. Hripcsak also has a long track record of developing, implementing, and studying informatics interventions to improve health care. He has published frequently on evaluation in biomedical informatics, leveraging his training in biostatistics. Dr. Hripcsak is Vivian Beaumont Allen Professor at Columbia University’s Department of Biomedical Informatics. He is a board-certified internist with degrees in chemistry, medicine, and biostatistics. He leads the Observational Health Data Sciences and Informatics (OHDSI) coordinating center; OHDSI is an international network with thousands of collaborators and health records on almost one billion patients. In precision medicine, he serves as a PI on Columbia’s eMERGE grant, Columbia’s regional recruitment center for the All of Us Research Program, and Columbia’s role on the All of Us Data and Research Center. He co-chaired the Meaningful Use Workgroup of U.S. Department of Health and Human Services’s Office of the National Coordinator of Health Information Technology. Dr. Hripcsak is a member of the National Academy of Medicine, the American College of Medical Informatics, the International Academy of Health Sciences Informatics, and the New York Academy of Medicine. He was awarded the 2022 Morris F. Collen Award of Excellence by the American College of Medical Informatics. He has over 500 publications.

Closing Keynote

Scott L. DuVall, PhD

Director, VA Informatics and Computing Infrastructure, VA Salt Lake City; Professor, Department of Internal Medicine - Epidemiology, University of Utah

Driven by a passion for leveraging data to make a meaningful impact, Scott L. DuVall, PhD, continues to push the boundaries of medical informatics and data science to benefit Veterans and the broader medical community. Dr. DuVall serves as the Director of the Department of Veterans Affairs (VA) Informatics and Computing Infrastructure (VINCI), a resource center that offers secure computing environments, analytic tools, support services, and a nation-wide view of VA electronic medical record and administrative claims data to more than 10,000 VA-credentialed researchers. Dr. DuVall spearheads the VA Office of Research and Development (ORD) initiative to "Put VA Data to Work for Veterans" that encompasses curating and standardizing data, linking and integrating external data sources, extracting clinical, social, and demographic information using natural language processing, and developing and implementing rigorous methods for reliable real-world evidence. Under his leadership, the VINCI team puts these data to work to enhance Veteran health by leading, enabling, and supporting clinical decision making and scientific discovery. Dr. DuVall is a Professor in the University of Utah School of Medicine within the Department of Internal Medicine Division of Epidemiology. His research focuses on the development and application of informatics tools and advanced analytical methods on electronic health care data in pharmacoepidemiology and outcomes research. He also directs a federally certified service recharge center within the University of Utah Health Science Core Facilities that offers data science and advanced analysis, computer-aided medical record review, natural language processing, and software development services. Dr. DuVall received a Bachelor of Science in Computer Science and a Doctor of Philosophy in Biomedical Informatics.


Michael Oberst, PhD
Assistant Professor Computer Science Johns Hopkins University
Zhiyu Wan, PhD
Postdoctoral research fellow Biomedical Informatics Vanderbilt University
Victoria Tiase, PhD, RN-BC, FAMIA, FNAP, FAAN
Assistant Professor Biomedical Informatics University of Utah
Laura Wiley, PhD, MS
Associate Professor, Biomedical Informatics Chief Data Scientist Health Data Compass University of Colorado Anschutz Medical Campus


Scott L. DuVall, PhD
Director, VA Informatics and Computing Infrastructure, Professor VA Salt Lake City Health Care System, Department of Internal Medicine Division of Epidemiology University of Utah
George Hripcsak, MD, MS
Professor, Biomedical Informatics Columbia University
David K. Vawdrey, PhD
Chief Data Informatics Officer Steele Institute for Health Innovation, Geisinger
Adam Wilcox, PhD
Professor, Medicine Director, Center for Applied Clinical Informatics Washington University in St. Louis
Linying Zhang, PhD
Assistant Professor, Biostatistics Washington University in St. Louis