Identifying Recurrent Non-Hodgkin Lymphoma in Structured and Unstructured Electronic Health Data
Data Science Seminar Series
April 3, 2024 | 11:00 AM – 12:00 PM
Virtual
In this webinar, University of Massachusetts Chan Medical School’s Drs. Mara Meyer Epstein and Feifan Liu will present algorithms designed to identify patients experiencing non-Hodgkin lymphoma (NHL) recurrence.
They will present the initial results of their rule-based algorithm against domain expert chart reviews, as well as describe their multi-task, multi-modal learning architecture. They’ll explain how the design makes model training data-efficient and generalizable.
Accurate cancer recurrence assessments are essential for cancer outcomes studies. Recurrence rates vary from 20-35% among survivors of common histologic subtypes of NHL; however, recurrent NHL is not reportable to cancer registries.
To address this, Drs. Epstein and Liu’s algorithms use longitudinally collected electronic health record and health claims data from two U.S. healthcare delivery systems, and one insurer, serving diverse populations.
About the Speakers
Mara Epstein, Sc.D., Sc.M.
Dr. Epstein is a cancer epidemiologist and faculty member in the Division of Health Systems Science at UMass Chan Medical School, where her research focuses on hematological cancers, particularly multiple myeloma and monoclonal gammopathy of undetermined significance. She utilizes electronic health records and health claims data to conduct epidemiologic research.
Feifan Liu, Ph.D.
Dr. Liu is an associate professor in the Department of Population and Quantitative Health Sciences at UMass Chan Medical School and founding director of the AI for Health lab. His research focuses on applying natural language processing and machine learning to analyze clinical data for cancer treatment, HIV, suicide prevention, and other health domains, with emphasis on AI interpretability, generalizability, and fairness.
About the Data Science Seminar Series
CBIIT’s Data Science Seminar Series is dedicating its 2026 events to spotlighting the use of AI in cancer research and care. Brought to you by CBIIT and NCI's Division of Cancer Treatment and Diagnosis AI working group, the upcoming webinars will explore a variety of questions, such as the following:
- How can AI be used for diagnosis, treatment, or omics research?
- What are the related laws and ethical considerations for AI?
- How can we empower an AI-ready cancer research community through workforce development, collaborations, and funding?
To view upcoming speakers or recordings of past presentations, visit the Data Science Seminar Series page.