skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: PathRepHAN: Hierarchical attention networks for pathology report classification

Abstract

Developers at ORNL explored how a deep learning (DL) approach based on hierarchical attention networks (HANs) can improve model performance for multiple information extraction tasks from unstructured cancer pathology reports compared to conventional methods that do not sufficiently capture syntactic and semantic contexts from free-text documents. The HAN was implemented for 2 information extraction tasks: (1) primary site, matched to 12 International Classification of Diseases for Oncology topography codes (7 breast, 5 lung primary sites), and (2) histological grade classification, matched to G1–G4. Our results demonstrate that for both information tasks, HAN performed significantly better compared to the conventional ML and DL techniques.

Authors:
 [1];  [1];  [1];  [1];  [2];  [2];  [2]
  1. Oak Ridge National Laboratory
  2. University of Tennessee-Knoxville
Publication Date:
Research Org.:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1503171
Report Number(s):
PathRepHAN; 005840WKSTN00
DOE Contract Number:  
AC05-00OR22725
Resource Type:
Software
Software Revision:
00
Software Package Number:
005840
Software CPU:
WKSTN
Open Source:
Yes
Source Code Available:
Yes
Country of Publication:
United States

Citation Formats

Ramanathan, Arvind, Christian, James B, Tourassi, Georgia, Yoon, Hong Jun, Qiu, John X, Young, Michael T, and Shang, Gao. PathRepHAN: Hierarchical attention networks for pathology report classification. Computer software. https://www.osti.gov//servlets/purl/1503171. Vers. 00. USDOE. 9 Feb. 2018. Web.
Ramanathan, Arvind, Christian, James B, Tourassi, Georgia, Yoon, Hong Jun, Qiu, John X, Young, Michael T, & Shang, Gao. (2018, February 9). PathRepHAN: Hierarchical attention networks for pathology report classification (Version 00) [Computer software]. https://www.osti.gov//servlets/purl/1503171.
Ramanathan, Arvind, Christian, James B, Tourassi, Georgia, Yoon, Hong Jun, Qiu, John X, Young, Michael T, and Shang, Gao. PathRepHAN: Hierarchical attention networks for pathology report classification. Computer software. Version 00. February 9, 2018. https://www.osti.gov//servlets/purl/1503171.
@misc{osti_1503171,
title = {PathRepHAN: Hierarchical attention networks for pathology report classification, Version 00},
author = {Ramanathan, Arvind and Christian, James B and Tourassi, Georgia and Yoon, Hong Jun and Qiu, John X and Young, Michael T and Shang, Gao},
abstractNote = {Developers at ORNL explored how a deep learning (DL) approach based on hierarchical attention networks (HANs) can improve model performance for multiple information extraction tasks from unstructured cancer pathology reports compared to conventional methods that do not sufficiently capture syntactic and semantic contexts from free-text documents. The HAN was implemented for 2 information extraction tasks: (1) primary site, matched to 12 International Classification of Diseases for Oncology topography codes (7 breast, 5 lung primary sites), and (2) histological grade classification, matched to G1–G4. Our results demonstrate that for both information tasks, HAN performed significantly better compared to the conventional ML and DL techniques.},
url = {https://www.osti.gov//servlets/purl/1503171},
doi = {},
year = {2018},
month = {2},
note =
}