Real World Data and AI: successes, challenges, and opportunities with Dr. Jiang Bian Chief Data Scientist at Regenstrief, Chief Data Scientist at IU Health, and Associate Dean of Data Science and Vice Chair for Translational Informatics in the Department of Biostatistics and Health Data Science at the IU School of Medicine
Bio: Dr. Bian specializes in biomedical informatics and health data science, interdisciplinary fields focused on leveraging data, information, and knowledge to drive scientific discovery, problem-solving, and decision-making, all aimed at improving human health. He has a diverse background in data harmonization and integration, AI/machine learning, causal AI, natural language processing, ontology development and evaluation, and software engineering. Dr. Bian brings extensive experience in developing real-world data infrastructure, informatics tools, and systems, as well as applying advanced AI and data science methods to analyze and interpret multimodal clinical and biomedical data. Dr. Bian serves as Chief Data Scientist at Regenstrief, Chief Data Scientist at IU Health, and Associate Dean of Data Science and Vice Chair for Translational Informatics in the Department of Biostatistics and Health Data Science at the IU School of Medicine.
Microsoft Teams meeting
Join: https://teams.microsoft.com/meet/213173981068428?p=5DIIAOUUGJhFHXwHXO
Meeting ID: 213 173 981 068 428
Passcode: tu6Qr3sg
2026-09-02 09:30:00 2026-09-02 10:20:00 America/Indiana/Indianapolis Real World Data and AI: successes, challenges, and opportunities with Dr. Jiang Bian Chief Data Scientist at Regenstrief, Chief Data Scientist at IU Health, and Associate Dean of Data Science and Vice Chair for Translational Informatics in the Department of Biostatistics and Health Data Science at the IU School of Medicine Abstract: This presentation examines practical methods-and some AI tools-for transforming real-world data (RWD) into credible real-world evidence (RWE). It highlights the central role of data science in overcoming common obstacles in electronic health records (EHR) and claims data (e.g., missingness, measurement error, and coding variability). Using case studies focused on GLP-1 receptor agonists (GLP-1RAs), the talk illustrates how rigorous study design and causal inference-particularly target trial emulation-can be used to assess the effectiveness and safety of GLP-1RAs. The presentation emphasizes when and how RWE can complement randomized controlled trials-and where it can mislead without careful attention to potential biases, many of which originate from data limitations. MJIS 1001 and via Teams