Streamlining Temporal Information Extraction: Integrating Rule-Based Methods into MedspaCy for Clinical Application

Presentation Time: 05:00 PM - 06:30 PM

Abstract Keywords: Natural Language Processing, Information Extraction, Data Mining
Primary Track: Applications
Programmatic Theme: Clinical Informatics

Electronic health records (EHRs) contain detailed records of a patient’s health over time, making it crucial to accurately identify the timing of a clinical event. In this work, we introduce a rule-based temporal entity extraction package for medspaCy, which can adapt to any spaCy-styled tokenizers, as well as handle additional types of implicit expressions.

Speaker(s):
Mengke Hu, PHD
University of Utah

Author(s):
Mengke Hu, PhD - University of Utah; Alec Chapman, MS - University of Utah; Patrick Alba, MS - United States Department of Veterans Affairs; Jianlin Shi, MD, PhD - The Division of Epidemiology, School of Medicine, University of Utah; VA Salt Lake City Healthcare System;