TRAIL4HEALTH Seminar Series

AI is rapidly transforming society and has emerged as the defining technology of our generation. Its influence spans across industries, with significant implications for scientific research, healthcare, and drug development. In this work, we review the historical progression of AI and its growing role in pharmaceutical research, highlighting how AI-driven methodologies are revolutionizing drug discovery and development processes. As the integration of AI in biostatistics and clinical research deepens, scientists must cultivate essential skills to remain effective in this evolving landscape. We discuss four critical competencies for scientists working in the AI era: AI Mindsets, AI Communication, AI Integration, and AI-Enabled Innovation. Looking ahead, we explore the potential future impact of AI on the pharmaceutical data analytics ecosystem. The convergence of AI with biostatistics presents both challenges and opportunities, requiring a thoughtful balance between leveraging AI’s capabilities and maintaining rigorous scientific and ethical standards. By embracing AI-driven approaches while upholding core statistical principles, the next generation of scientists can contribute to more efficient, data-driven advancements in clinical research. This discussion aims to provide insights into the evolving role of AI in biostatistics and inspire forward-thinking strategies for navigating the intersection of AI and scientific discovery in the pharmaceutical industry.

Dr. Haoda Fu is Head of Exploratory Biostatistics in Amgen, before that he was an Associate Vice President and an Enterprise Lead for Machine Learning, Artificial Intelligence, from Eli Lilly and Company. Dr. Haoda Fu is a Fellow of ASA (American Statistical Association), and IMS Fellow (Institute of Mathematical Statistics). He is also an adjunct professor of biostatistics department, Univ. of North Carolina Chapel Hill and Indiana University School of Medicine. Dr. Fu received his Ph.D. in statistics from University of Wisconsin - Madison in 2007 and joined Lilly after that. Since he joined Lilly, he is very active in statistics and data science methodology research. He has more than 100 publications in the areas, such as Bayesian adaptive design, survival analysis, recurrent event modeling, personalized medicine, indirect and mixed treatment comparison, joint modeling, Bayesian decision making, and rare events analysis. In recent years, his research area focuses on machine learning and artificial intelligence. His research has been published in various top journals including JASA, JRSS-B, Biometrika, Biometrics, ACM, IEEE, JAMA, Annals of Internal Medicine etc. He has been teaching topics of machine learning and AI in large industry conferences including teaching this topic in FDA workshop. He was board of directors for statistics organizations and program chairs, committee chairs such as ICSA, ENAR, and ASA Biopharm session. He is a COPSS Snedecor Awards committee member from 2022-2026, and also served as an associate editor for JASA theory and method from 2023, and JASA application and case study from 2025-2027.

Advances in single-cell RNA sequencing and multimodal technologies have opened new opportunities for inferring gene networks and regulatory relationships in specific cell types, enriching our understanding of cell-type-specific biological functions. However, unique data characteristics such as sequencing depth variation, high data sparsity, and measurement error present significant challenges. In this talk, I will present two statistical methods that address these challenges. CS-CORE infers cell-type-specific gene co-expressions from scRNA-seq data and scMultiMap maps enhancer-gene pairs from paired scRNA-seq and scATAC-seq data. Both methods achieve accurate type-I error control, high reproducibility, scalability, and provide new insights into Alzheimer’s disease mechanisms.

Dr. Zhang is the Goizueta Foundation Chair Professor of Information Systems & Operations Management (ISOM) at the Goizueta Business School of Emory University. She also hold a secondary appointment in the Department of Biostatistics & Bioinformatics at the Rollins School of Public Health. Her research interests involve the statistical analysis of networks, graphs and tensor data, with applications in business, neuroscience and social science. 

Understanding the causal mechanisms of complex diseases requires integrating high-dimensional multi-omics data with advanced computational frameworks. In this talk, I will present how to leverage genomic large language models (LLMs) and Bayesian causal inference to bridge the gap in identifying underlying causal pathways in complex diseases. First, I introduce EpiGePT, a context-specific genomic LLM capable of imputing and predicting epigenomic features across diverse biological contexts, outperforming existing models in out-of-sample prediction. Then, I will showcase how epiBrainLLM identifies genotype-brain-clinical pathways in Alzheimer’s disease (AD), revealing novel associations between imputed genomic features and various AD phenotypes, including imaging phenotypes and clinical phenotypes. Finally, I present CausalBGM, an AI-powered Bayesian generative modeling framework that enables robust causal effect estimation with the presence of high-dimensional covariates. Together, these methods offer a new paradigm for causal discovery in biomedical research, combining interpretability, predictive accuracy, and uncertainty quantification.

Dr. Qiao Liu is an Assistant Professor in the Department of Biostatistics at Yale University. His research lies at the intersection of AI and statistical science, two transformative forces shaping modern data science. His group develop AI-powered computational frameworks grounded in statistical rigor, aiming to provide insights from massive and complex biomedical datasets. His recent works focus on leveraging generative AI to address fundamental challenges in high-dimensional data analysis, including causal inference, unsupervised learning, and Bayesian computation. These methodological innovations are motivated by pressing problems in computational biology, where data are massive, complex, and heterogeneous. His group works extensively with single-cell genomics, multi-omics, pharmacogenomics, and large-scale clinical datasets to uncover biological insights. Dr. Liu has authored over 40 publications in leading journals and conferences. His contributions have been recognized with prestigious honors, including the NIH Pathway to Independence Award.

As the intelligence of everyday smart devices continues to evolve, they have moved beyond simple tracking of behaviors to glimpses of our broader health and well-being. The possibility of a truly intelligent system for continuous health monitoring and intervention is no longer science fiction. How to make this vision a reality?

In this talk, I will outline an ecosystem that unites AI, end-users, and health experts. I will share our work in building rich passive sensing datasets, human-centered algorithms, and benchmark platforms that push the field toward more robust, trustworthy, and deployable health prediction pipelines. With the rise of large language models (LLMs), I will further show how technologies can move beyond passive monitoring to actively promoting individuals’ daily well-being and supporting clinicians in making more informed medical decisions. By cultivating an organic human-AI ecosystem, we are approaching a future where AI systems can sense, empower, and augment our health and well-being in everyday life.

Dr. Xuhai “Orson” Xu is an Assistant Professor at Columbia University’s Department of Biomedical Informatics and Computer Science (courtesy), and a Visiting Faculty at Google, where he leads research at the crossroads of human-computer interaction, applied AI, and health. His work develops deployable AI algorithms and intelligent interventions that harness everyday sensor data and health records to monitor and improve well-being, while his human-centered pipeline unites AI, clinicians, patients, and the broader general population in a collaborative ecosystem for improved care. Dr. Xu's work has been recognized through numerous awards and widespread media coverage for its groundbreaking contributions to digital health and human-computer interaction, including several Best Paper and Best Artifact awards at top-tier venues such as ACM CHI and IMWUT, the Innovation and Technology Award, and media posts such as the Washington Post, Scientific American, and ACM News. 

Patient portal messages have become an important channel for patient-provider communication. However, there are well documented disparities in rates of portal use. Additionally, prior work has shown that even when minority and Medicaid patients send portal messages, they are less likely to receive responses from attending physicians, seemingly driven by lower prioritization in message triage. Using natural language processing, we analyze the text of patient portal messages from a large academic health system to understand what drives these differences, enabling us to separate three potential mechanisms: differences in the underlying request of the message (e.g., medication question, referral request), differences in the way the messages are written, and non-clinical bias. We find that, while the category of message request is a significant predictor of care team response, it cannot explain observed differences across demographic groups. On the other hand, the way the message is written – including message characteristics such as length and formality – accounts for nearly half of the observed differences in care team response. Our findings identify a clear mechanism underlying disparities in care team response, highlighting avenues for mitigating them and deepening our understanding of care disparities broadly.

Dr. Tang’s research examines how digital technologies are reshaping health care delivery and how health care organizations and policy should adapt in response. His AI-related work focuses on both understanding the effects of AI as a technology and using it as a research tool for analyzing unstructured data sources, such as electronic health records.