The University of Michigan Department of Biostatistics is pleased to host Tianxi Cai, PhD (Harvard University), recipient of the 2025 Jeremy Taylor Outstanding Research Mentor Award, for a featured academic seminar on Thursday, January 22 at 3:30 p.m. Dr. Cai is an internationally recognized leader in statistical learning, risk prediction, and the integration of electronic health records with genomic and clinical data. Her lecture will draw on her pioneering work in translational data science and precision medicine, reflecting both her methodological impact and her deep commitment to mentoring the next generation of statistical scientists. A reception will follow the seminar. The reception is open only to those who attend the lecture.Toward Durable AI in Healthcare: Generalizable Learning from Imperfect EHR DataElectronic Health Record (EHR) data offers a promising foundation for real-world evidence, yet its utility is often severely limited by the reality of fragmented, imperfect data and significant heterogeneity across health systems. These inherent data flaws create major bottlenecks in generating evidence efficiently, often resulting in fragile models that are highly susceptible to data shift and rapid aging. Consequently, the challenge lies not just in accessing data, but in efficiently transforming these messy, disparate sources into reliable, enduring AI solutions.This presentation outlines a comprehensive strategy to overcome these limitations and derive robust clinical insights from imperfect data. We will discuss how representation learning can address data sparsity and fragmentation by extracting stable latent features from incomplete patient histories. To tackle system heterogeneity and ensure model longevity, we introduce robust transfer learning frameworks designed to immunize algorithms against distributional shifts. Furthermore, we demonstrate how leveraging knowledge networks can bridge gaps in fragmented data by grounding models in broader biomedical context. Complementing these structural approaches, we touch upon the use of Large Language Models (LLMs) to identify clinical outcomes not directly available in structured fields, solving the problem of unobserved endpoints. By integrating these diverse methodologies, we aim to establish a blueprint for efficiently building AI ecosystems that remain reliable and durable despite the complexities of real-world healthcare data.