Abstract

AI and big data have significantly enhanced the field of population health. In her presentation, Dr. Ye will explore her research in three pivotal areas: (1) probabilistic disease surveillance systems; (2) the use of transfer learning to enable efficient knowledge sharing across various healthcare systems and continuous knowledge updating; (3) the implementation of large language models and foundational models for predictive analytics. She will conclude by addressing the ongoing challenges and the potential future pathways for AI in population health.

Bio
Dr. Ye Ye, an alumna of our ISP program at the University of Pittsburgh, now serves as an Assistant Professor in the Department of Biomedical Informatics. She holds a PhD in Intelligent Systems, an MS in Public Health, and a BMED in Preventive Medicine. Her research, which bridges AI and population health, focuses on developing machine learning models for disease surveillance, healthcare utilization, and population health management. Dr. Ye’s work is supported by a K99/R00 grant from the National Library of Medicine (NLM), which aims to enhance the reusability of computable biomedical knowledge through transfer learning. She is involved in several notable projects, including with the Models of Infectious Disease Agent Study Coordination Center (NIGMS), the Automated Surveillance of Overlapping Outbreaks (NLM), and the National Mesothelioma Virtual Bank (CDC).

Dr. Ye was recognized as one of the top five finalists in the American Medical Informatics Association Doctoral Dissertation Competition in 2019 and has received awards such as the Analyst Track Best Paper Award at the 12th IEEE International Conference on Healthcare Informatics, where she was the corresponding author. She has also received the University of Pittsburgh Innovator Award and contributed to research that earned the CDC Best Statistical Science Theoretical Paper Award. Additionally, she serves on the editorial boards of the Artificial Intelligence in Medicine and the Journal of Biomedical Informatics.