Identifying Recurrent Non-Hodgkin Lymphoma in Structured and Unstructured Electronic Health Data

April 3, 2024 | 11:00 AM – 12:00 PM

Virtual

Add to Outlook Calendar

Register

Watch the recording

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.

To view upcoming speakers or recordings of past presentations, visit the CBIIT Data Science Seminar Series webpage. The Data Science Seminar Series presents talks from innovators in the cancer research and informatics communities both within and outside of NCI.