Seminars

Abstract: The standard approach to task fMRI analysis was established more than 25 years ago, and the ease of creating models using common software packages belies the difficulties inherent in developing valid models of task fMRI data.  After working through an example where minor differences in modeling led to major irreproducibility, I will focus on two specific aspects of fMRI modeling. First I will discuss the importance of modeling of response times in fMRI analysis, and how differences between modeling approaches can lead to very different interpretations of the results.  Then I will discuss how misplaced concerns about orthogonality in fMRI models have led to problematic modeling choices, specifically in the context of the monetary incentive delay task.  I will conclude by arguing for a causally-informed approach to developing statistical models for neuroimaging data.

Bio: I grew up in a small town in Texas and attended Baylor University. After completing my PhD in experimental psychology at the University of Illinois in Urbana-Champaign, I spent four years as a postdoc at Stanford. I have held faculty positions at Massachusetts General Hospital/Harvard Medical School, UCLA, and the University of Texas. I joined the Stanford faculty in 2014.

Abstract: Most clinical AI models forecast risk but do not leverage full clinical context or explain why a clinician should care about a prediction. In this talk I will describe our work on AI systems that identify and explain what matters for an individual patient in real time. We train models on full electronic health record timelines to recognize surprising, important, and high-risk events as they unfold. Rather than flooding clinicians with low value alerts we can bring contextually valuable information to a clinician’s attention. In parallel, we build models that can read physiologic data like ECGs and justify their conclusions using learned clinical prototypes. The model points to concrete, human interpretable patterns rather than providing only an opaque label. Together, these approaches move us toward context aware, multimodal decision support that is not just accurate but aligned with how clinicians actually think and act at the bedside.

Bio: Brett Beaulieu-Jones, PhD is an Assistant Professor at the University of Chicago. His research seeks to understand the relationship between technology and health care delivery, including the deployment of machine learning and informatics tools, and the extraction of robust insights from real-world biomedical data. Dr. Beaulieu-Jones received a National Institutes of Health Pathway to Independence Award from the National Institute of Neurological Disorders and Stroke. He has had multiple publications recognized among the American Medical Informatics Association’s Year in Review top 10 papers in clinical informatics. He earned his PhD in genomics and computational biology from the Perelman School of Medicine at the University of Pennsylvania in 2017. His thesis, which was recognized by the American Medical Informatics Association, focused on the development and application of machine learning and informatics methods to clinical data to identify biologically or clinically interesting patient subpopulations. He then completed a postdoctoral fellowship and served as a junior faculty member in the Department of Biomedical Informatics at Harvard Medical School. He served as the general chair for the Machine Learning for Health (ML4H) workshop at NeurIPS, is a founding organizer for the Symposium on Artificial Intelligence for Learning Health Systems and is the chair of the Association for Health Learning and Inference (AHLI, parent organization of ML4H and the Conference on Health, Inference, and Learning). He has a strong interest in entrepreneurship and has helped start and lead venture backed companies from founding to acquisition.

Abstract: TBA

Bio: Yonghyun Nam is a Research Assistant Professor of Informatics at the University of Pennsylvania’s Perelman School of Medicine. His research focuses on integrating multi-omics data—including genomics, proteomics, and electronic health records—to advance risk prediction for complex diseases. He develops machine learning frameworks that combine polygenic risk scores, proteomic biomarkers, and network-based models to identify individuals at elevated risk for a range of complex disorders.

Abstract: TBA

Bio: TBA

Abstract: TBA

Bio: TBA

Abstract: TBA

Bio: TBA

Abstract: TBA

Bio: TBA

Abstract: Understanding tumor heterogeneity remains one of the greatest challenges in cancer biology and precision medicine. My research integrates high-throughput single-cell analysis, microfluidics, and artificial intelligence to dissect cellular heterogeneity, cancer cell migration, and therapeutic resistance. We developed microfluidics capable of analyzing limited cell numbers for single-cell RNA-Seq and profiled 666 circulating tumor cells (CTCs) from 21 breast cancer patients, revealing distinct CTC subpopulations with potential implications for treatment selection. In parallel, we engineered high-throughput microfluidic systems that enable quantitative analysis of tens of thousands of migrating cancer cells per chip. Using scalable injection molding fabrication and robotic automation, we performed large-scale screening of 2,726 compounds, identifying promising inhibitors of cancer cell migration and metastasis. To address therapy resistance, we established an image-based single-cell morphological profiling pipeline to characterize polyploid giant cancer cells (PGCCs), a subpopulation that survives chemotherapy and regenerates tumor cells. High-throughput screening identified several anti-PGCC compounds that overcome treatment-induced resistance in breast cancer models. Building upon these experimental datasets, we developed deep learning–based virtual screening models that integrate chemical, morphological, and literature-derived features to perform in silico prediction of >24,000 small molecules. This AI framework enables efficient exploration and prioritization of potential candidates within a vast search space. Together, these technologies establish a powerful multidisciplinary platform to decode cancer cell heterogeneity, uncover therapeutic vulnerabilities, and accelerate the discovery of precision treatments.

Bio: Yu-Chih Chen received his dual bachelor degrees in Electrical Engineering and Law from the National Taiwan University, Taipei in 2008, his Ph.D. degree in Electrical & Computer Engineering at the University of Michigan, Ann Arbor in 2014, where he continued to work as a research faculty in both Electrical & Computer Engineering Department and Forbes Institute for Cancer Discovery. He is currently an assistant professor in the Department of Computational and Systems Biology and UPMC Hillman Cancer Center at the University of Pittsburgh School of Medicine. He is also affiliated with Joint CMU-Pitt Ph.D. Program in Computational Biology. He is the recipient of Taiwan Semiconductor Manufacturing Company (TSMC) Outstanding Student Research Award (2008), Orenstein Ph.D. Fellowship (2009), Best Post-Doctoral Speaker Award in Microfluidics in Biomedical Sciences Training Program, UMich (2015), Emerging Forbes Scholar selected by Forbes Institute for Cancer Discovery (2017), and Hillman Early Career Fellow for Innovative Cancer Research (2021). His current research focuses on high-throughput single-cell analysis and deep learning for cancer precision medicine.

Abstract: TBA

Bio: TBA