Description
Attributes of clinical concepts, such as severity and negation modifiers of clinical problems in the clinical text, are vital elements for clinical natural language processing (NLP). A high-performance, easy-to-use toolkit to automatically recognize attribute information of clinical concepts from the clinical text is highly desirable. Here we introduce CLAMP-ATR (Attribute), a newly developed comprehensive pipeline for attribute recognition with the CLAMP NLP toolkit. It not only achieved high-performance on attribute recognition across different corpora but also made customization easier by providing a Docker container for training deep learning models and a GUI interface for building pipelines.
Learning Objective: Deep learning based NLP pipeline to recognize concepts and attributes from clinical texts;
High performance and easy-to-use clinical NLP software;
A GPU-friendly Docker container to train deep learning models;
Authors:
Jingqi Wang (Presenter)
UTHealth
Yaoyun Zhang, UTHealth
Hua Xu, UTHealth
Presentation Materials: