Hierarchical attention networks for information extraction from cancer pathology reports
- Computational Science and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA
- Surveillance Informatics Branch, Division of Cancer Control and Population Sciences, National Cancer Institute, Bethesda, MD, USA
We 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. Data for our analyses were obtained from 942 deidentified pathology reports collected by the National Cancer Institute Surveillance, Epidemiology, and End Results program. 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. Model performance metrics were compared to conventional machine learning (ML) approaches including naive Bayes, logistic regression, support vector machine, random forest, and extreme gradient boosting, and other DL models, including a recurrent neural network (RNN), a recurrent neural network with attention (RNN w/A), and a convolutional neural network. Our results demonstrate that for both information tasks, HAN performed significantly better compared to the conventional ML and DL techniques. In particular, across the 2 tasks, the mean micro and macro F-scores for the HAN with pretraining were (0.852,0.708), compared to naive Bayes (0.518, 0.213), logistic regression (0.682, 0.453), support vector machine (0.634, 0.434), random forest (0.698, 0.508), extreme gradient boosting (0.696, 0.522), RNN (0.505, 0.301), RNN w/A (0.637, 0.471), and convolutional neural network (0.714, 0.460). HAN-based DL models show promise in information abstraction tasks within unstructured clinical pathology reports.
- Research Organization:
- Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States). Oak Ridge Leadership Computing Facility (OLCF); National Cancer Inst., Bethesda, MD (United States)
- Sponsoring Organization:
- USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR); USDOE National Nuclear Security Administration (NNSA); National Inst. of Health (NIH) (United States)
- Grant/Contract Number:
- AC05-00OR22725; AC02-06CH11357; AC52-07NA27344; AC52-06NA25396
- OSTI ID:
- 1430375
- Alternate ID(s):
- OSTI ID: 1474695
- Journal Information:
- Journal of the American Medical Informatics Association, Journal Name: Journal of the American Medical Informatics Association Vol. 25 Journal Issue: 3; ISSN 1067-5027
- Publisher:
- Oxford University PressCopyright Statement
- Country of Publication:
- United Kingdom
- Language:
- English
Web of Science
Similar Records
Deep Learning Based Superconducting Radio-Frequency Cavity Fault Classification at Jefferson Laboratory
Jet charge and machine learning