YSPH Biostatistics Seminar: “Machine Learning for Biomarker Discovery in Clinical Neuroscience: Examples and Lessons"

NOTE: BIS 525 students are required to attend in person. Others are invited to attend in person, but may also attend via Zoom.

SPEAKER: Zhe Chen, PhD, Associate Professor, Departments of Psychiatry and Neuroscience, New York University

TITLE: “Machine Learning for Biomarker Discovery in Clinical Neuroscience: Examples and Lessons"

ABSTRACT: Data science and machine learning have become increasingly important in clinical neuroscience and medicine, supporting advances in biomarker discovery, predictive analytics, and data augmentation. However, several challenges commonly arise in practical applications, including small or unbalanced sample sizes, the curse of dimensionality, and the need for robust independent validation. In this talk, I will illustrate these issues through several research projects and outline strategies for feature engineering and data augmentation that facilitate scientific discovery using neuroimaging and clinical data. Examples will be drawn from studies on SUDEP (Sudden Unexpected Death in Epilepsy), SUDC (Sudden Unexpected Death in Children), and chronic pain. Finally, I will discuss the broader challenges and future outlook for clinical applications, focusing on interpretability, interoperability, clinical viability, and research rigor.

YSPH values inclusion and access for all participants. If you have questions about accessibility or would like to request an accommodation, please contact Charmila Fernandes at Charmila.fernandes@yale.edu. We will try to provide accommodations requested by November 13, 2025.